ariffazil

agentic-governance

Hardened constitutional governance — F1-F13 floor enforcement with Quad-Witness consensus for all actions

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

code-analysis

This skill should be used when the user needs to analyze Git repositories, compare developer commit patterns, work habits, development efficiency, code style, code quality, and slacking behaviors. It generates honest, direct developer evaluations with scores, grades, strengths, weaknesses, and actionable suggestions. Trigger phrases include "analyze code", "analyze repository", "compare developers", "code quality report", "commit patterns", "developer efficiency", "developer evaluation", "slacking index", "摸鱼指数", "工作习惯分析", "代码分析", "研发效率", "代码质量", "开发者评估", "developer score".

explorer-intelligence-architecture

The universal exploration protocol for all AAA warga agents. OBSERVE → HYPOTHESIZE → FALSIFY → VERIFY — the governed metabolism of intelligence. Every agent follows this loop when exploring anything. Not theory. Protocol.

GEOX Grounding

Force Earth-sensitive reasoning through GEOX witness paths. Ensure geological claims are grounded in evidence.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Push Protocol

Push is publishing intent. Only reviewed branches. Never to main.

GitHub Merge Protocol

Merging is law update. Only after CI + review + signers.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

Caller Trace

Before invoking any tool, traces WHO else calls this tool, the cost of misuse, and whether the caller's use is load-bearing or ceremonial. Prevents scenarios like the Docker MCP dead-end loop where multiple agents chase a broken tool no one needs.

Sovereign Recognize

Identifies and recognizes the sovereign (Arif, F13) before any action that targets them, addresses them, or binds them. Prevents agent impersonation of operator identity.

federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

Docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

GitHub Issue Literacy

Issues are units of intent, uncertainty, and governance — not tickets.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

GitHub Commit Craftsmanship

Commits are atomic thoughts. Small, meaningful, attributable.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub CI Obedience

CI is doctrine enforcement. Never bypass.

GitHub Branch Discipline

Branches are parallel realities. Never edit main directly.

GitHub Pull Discipline

Pull is sync with reality. Pull before branching, before committing.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

GitHub PR Governance

PRs are constitutional hearings. Intent becomes law.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Google Workspace CLI

Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

GitHub Worktree Mastery

Worktrees are parallel working universes. Multiple branches, one working tree.

GitHub Forensics & Blame

Blame is lineage tracing. Essential for accountability.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

GitHub Tagging & Releases

Tags are frozen states of truth. The forge date IS the version.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

FORGE-repo-intelligence

SOLE controller skill for repository intelligence across the arifOS Federation. Exposes 12 modes (inventory, map, delta, pr_review, ci_diagnose, issue_triage, security, cross_repo_impact, release_audit, workflow_integrity, manifest_reconcile, ruleset_audit). Smaller GitHub skills (pr-review, ci-diagnose, issue-triage, github-ops) are consolidated as internal modules under this controller. No other repo-intelligence skill should be created — extend modes instead. Every mode outputs a minimum evidence envelope with repo, ref, commit_sha, working_tree, tag_delta, changed_files, critical_paths, tests, ci, security, contract_impacts, runtime_probe, risk_tier, proposed_action, rollback, evidence_class, and unknowns.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

skills/_retired/ARCHIVE-dupe-2026-07-12/root_AAA_skills/ARCHIVE-constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

GitHub Tagging & Releases

Tags are frozen states of truth. The forge date IS the version.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Issue Literacy

Issues are units of intent, uncertainty, and governance — not tickets.

GitHub Branch Discipline

Branches are parallel realities. Never edit main directly.

GitHub Commit Craftsmanship

Commits are atomic thoughts. Small, meaningful, attributable.

GitHub Staging Awareness

Staging is the thinking buffer. Three states: working / staged / committed.

GitHub PR Governance

PRs are constitutional hearings. Intent becomes law.

GitHub CI Obedience

CI is doctrine enforcement. Never bypass.

GitHub Merge Protocol

Merging is law update. Only after CI + review + signers.

GitHub Pull Discipline

Pull is sync with reality. Pull before branching, before committing.

GitHub Push Protocol

Push is publishing intent. Only reviewed branches. Never to main.

GitHub Worktree Mastery

Worktrees are parallel working universes. Multiple branches, one working tree.

infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

GitHub Forensics & Blame

Blame is lineage tracing. Essential for accountability.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

GEOX Grounding

Force Earth-sensitive reasoning through GEOX witness paths. Ensure geological claims are grounded in evidence.

federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

skill-creator

Bootstrap, design, and package new skills.

route-least-power

CANONICAL: /root/.agents/skills/route-least-power/SKILL.md — Route every task to the SMALLEST capability that can accomplish it.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

MCP Lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

apex-formal-constitution

Formal constitutional encoding — superseded by arifOS kernel F1-F13 runtime enforcement.

apex_tool_approval_gate

Gate and route tool use across federation MCP servers according to authority, risk, and fallback policy. Use for multi-organ tool sequences, cross-server coordination, registry audits, or degraded-server fallback decisions.

asi_evidence_tier_express

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

apex_verdict_seal

Verify the complete ART-to-kernel-to-ACT evidence path before a SEAL-grade conclusion, without granting seal authority. Use when a proposed verdict claims readiness after all constitutional, witness, reversibility, and system-health gates have passed.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

asi_intent_hear

The Hermes SOUL-layer human intelligence model. Reads human state, container, and trajectory from language, not from biometric data. Routes deep pattern recognition through the WELL organ for physiological signals and through SOUL.md's cognitive identity for meaning. Use when Arif asks "what do you see", "what's my state", "apa pandangan kau", or when any 555-ASI governance scan needs the Hermes-perspective on the sovereign.

GitHub Runbook - Federation Git and CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

apex_scope_check

Check whether a proposed action stays within its declared task, organ, and constitutional scope. Use before cross-organ work, policy changes, production operations, secret handling, or any action whose blast radius or boundaries are unclear.

apex_reversibility_test

Test whether a proposed change touching vault, seal, identity, constitutional, or other F1 surfaces has a valid rollback and sovereign witness path. Use before committing or deploying changes whose reversibility is uncertain.

apex_floor_check

Evaluate a proposed action against the arifOS F1-F13 constitutional floors and identify any failed gate. Use for governance changes, destructive operations, production deployment, secret handling, federation charter edits, or constitutional verdict review.

apex_authority_check

Detect conflicting or parallel source-of-truth claims across federation repositories and resolve the canonical owner. Use after repository reorganization, when instructions conflict, or during federation authority audits.

apex_verdict_hold

Apply the constitutional HOLD path when authority, evidence, system health, reversibility, or blast radius is insufficient. Use before irreversible actions, external communications, deployments, deletions, seals, or any tool call that must stop pending sovereign review.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

asi_interface_adapt

A2A protocol bridge for routing multi-modal inputs (vision, audio, video, document) through Hermes to the reasoning and execution layers. Hermes receives the raw modality, classifies it, extracts structured content, and routes to the correct organ (GEOX for seismic images, WELL for biometrics, WEALTH for documents, A-FORGE for code diagrams). Use when Arif sends or references an image, audio file, video, scanned document, or any non-text input that needs governed processing.

asi_position_contrast

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

apex_audit_coverage_check

Audit whether every constitutional floor and federation organ has code enforcement, tests, bypass resistance, and trace coverage. Use for read-only F1-F13 audits, organ boundary reviews, cascade-risk checks, or governance gap analysis.

agentic-web-optimization

Make web content maximally extractable by LLMs, Agentic RAG systems, and search indexers.

ASI-agentic-architecture

Class-level skill for designing sovereign agentic agents. 9-skill spine, 3-agent model (Architect→Engineer→Auditor), 4 powers per agent, deterministic/isolation principles, VPS management spine. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

verify-runtime

Verify federation service health and runtime behavior. Runs apex-health.sh, per-organ health probes (arifOS, GEOX, WEALTH, WELL, APEX, A-FORGE), and one behavior smoke per touched organ. Use after every deploy, restart, or after any task that claims "done". Confirms behavior, not just tests.

audit-seal

Every decision logged. Irreversible decisions sealed. ΔS ≤ 0 on every output. Receipts > narratives.

memory-manage

Intelligence without memory is stateless. Store less, recall well, forget when stale. ΔS ≤ 0 on every cycle.

GitHub Staging Awareness

Staging is the thinking buffer. Three states: working / staged / committed.

github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

skill-creator

Bootstrap, design, and package new skills.

know-physics

All reality claims are physical claims. Conservation laws, thermodynamics, causality, entropy. You cannot get something from nothing.

mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

MCP Lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

know-language

All human interface is linguistic. Meaning ≠ syntax. Pragmatics > semantics > syntax. The gap between said and meant is where governance lives.

know-math

All computation is mathematical. Uncertainty is quantified. Optimization has structure. Proof has rules. Numbers don't lie but models can.

infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

route-least-power

CANONICAL: /root/.agents/skills/route-least-power/SKILL.md — Route every task to the SMALLEST capability that can accomplish it.

subagent-spawn-template

Standard contract for spawning bounded, auditable sub-agents — input contract, output schema, evidence requirements.

verify-gate

Four gates before commitment: authority + evidence + reversibility + lineage. All four must open. One missing = HOLD.

route-dispatch

Right organ for right intent. Classify intent, map to organ, dispatch with fallback. Law ≠ execution.

meta-mesa-skill-atlas

Unified skill inventory, gap detection, and cross-cutting orchestration for AAA catalog + Grok/Claude/Codex/Hermes/Kimi/OpenClaw harness views. The mesa above the terrain — see the whole, find the missing, route the right skill. Load when starting a new task, auditing skill health, unifying CLI agent skills, onboarding a new organ, or when you don't know which skill to load.

mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

model-fallback-monitor

Monitor the model fallback chain: MiniMax (primary), DeepSeek (hot-swap), Kimi, Ollama qwen2.5:7b (local). Track latency, billing failures (402), cold-start failures, and auto-pause dead models. USE WHEN: "model health", "check fallback chain", "DeepSeek balance", "model latency", "billing alert".

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card (v2.0.0 schema), registry entry, and SOUL.md. Updated 2026-07-01: canonical card location is AAA/agents/<id>/agent-card.json.

quantum-eureka-doctrine

CANONICAL: /root/.agents/skills/quantum-eureka-doctrine/SKILL.md (v1.1.0) — Eureka, contradiction, insight generation, cross-domain synthesis.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

vault-integrity

Cognitive lens for VAULT999 — append-only hash-chained ledger integrity, chain verification, failure handling.

vps-docker-ops

Runbook for VPS Docker operations — compose stack management, live service map, container lifecycle.

HERMES-multi-modal-bridge

IO boundary protocol for Hermes ↔ 333-AGI multi-modal signal routing. Ingests vision/audio signals from Hermes' creative/media surface and routes them as structured evidence payloads into the reasoning layer. USE WHEN: Hermes encounters an image, audio, or video that requires reasoning beyond creative routing.

skill-unification

Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.

precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to f1-gate.

ASI-skill-binding

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

kimi-skill-reflector

Audit, reflect on, and recursively upgrade Kimi Code skills across the arifOS federation. Bounded autonomous ritual — proposes improvements, never auto-writes governed skills without 888_HOLD, caps iterations, enforces ΔS ≤ 0.

unified-memory-federation

Single entry point for memory across the arifOS federation. Routes recall/write/seal/consolidate/audit to the correct tier and organ. Enforces the 6-tier memory model from zen-organ-memory.

GEOX-artifact-rigor

Standing instruction for all geoscience artifacts — panels, dossiers, maps, cross-sections. Born from Raja Ridhuan's feedback: 'tak cukup geology.' 8 hard rules ensuring real geological substance, not just epistemic tagging.

ARCHIVE-vault-integrity

Cognitive lens for VAULT999 — append-only hash-chained ledger integrity, chain verification, failure handling.

999-vault-seal-immutable

Seal action to civilizational memory with mandatory end-of-session recursive MCP stack hardening and future INIT scaffold. VAULT999 record. Stage 7.

CONSTITUTIONAL-REFLEX

CANONICAL VERSION: arifos-act v3.0.0 at /root/AAA/skills/arifos-act/SKILL.md This file is kept for OpenCode system instruction backward compatibility. The constitutional reflex arc: ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution).

ASI-drift-response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

FORGE-docker-thermo

Cognitive lens: containers as thermodynamic/entropy systems — resource pressure, safe intervention boundaries.

FORGE-github-runbook

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

ASI-agent-bootstrap

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

KERNEL-mcp-builder

Canonical MCP server-builder doctrine — naming laws, capability declaration discipline, _meta envelope contract, lifecycle notification rules, error envelope contract, and the 28 bindings every MCP server in arifOS federation must honour. Load before designing, scaffolding, or auditing ANY MCP server surface.

FORGE-mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

FORGE-secret-safety-scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

ASI-context-window-mgr

Context window lifecycle management — monitors token usage, triggers compression when approaching limits, manages conversation summarization, and preserves critical context across compaction boundaries. USE WHEN: "context getting long", "compress conversation", "summarize session", "token budget".

KERNEL-mcp-zen

Keep MCP servers minimal, schema-first, and governance-free.

mcp-builder-doctrine

Canonical MCP server-builder doctrine — naming laws, capability declaration discipline, _meta envelope contract, lifecycle notification rules, error envelope contract, and the 28 bindings every MCP server in arifOS federation must honour. Load before designing, scaffolding, or auditing ANY MCP server surface.

ASI-agent-invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

skills/ASI-constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

ASI-drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

ASI-fabrication-prevention

Artifact fabrication prevention — verify before claiming existence. Triggered when agent claims file/database/API/artifact existence without external validation. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

ASI-mcp-governor

Governed MCP routing via arifOS F1-F13. All calls to GEOX, WEALTH, WELL organs must route through arifOS kernel for C2+/IRREVERSIBLE tools. Uses mcporter for stdio/HTTP bridging.

ARCHIVE-vault999-integrity

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

ASI-observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

ASI-agentic-governance

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

ASI-zen-organ-memory

Preserve irreversible state; never overwrite sealed information. Zen Organ 5 of 7 — sealed state IS the fossil record of a civilization learning to govern itself.

ARCHIVE-vault-seal

Seal action to civilizational memory with mandatory end-of-session recursive MCP stack hardening and future INIT scaffold. VAULT999 record. Stage 7.

FORGE-github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

trinity-33-canonical

The canonical 33-repo Trinity (final). arifOS = LAW/JUDGMENT (K1-K11), AAA = STATE/ROUTING/VISIBILITY (C1-C11, new explicit axis), A-FORGE = EXECUTION/MUTATION (F1-F11). Adds 4 arifOS repos, 2 A-FORGE repos, PROTOCOL SPEC class, 5-phase integration order, and the iron rule. Supersedes prior 3 skills (see delta table).

FORGE-precommit-gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

APEX-humility-godel

Self-critique and epistemic humility protocol before SEAL-grade or high-confidence claims. Meta-critique, confidence bands, explicit unknowns. F2, F7 enforced. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

ASI-summarize

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

ARCHIVE

Archived skill artifacts and quarantine records. Retained for audit trace and civilizational memory.

AUDIT-drift-detector

Real-time drift detection across tool manifests, agent cards, skill registries, and runtime-injected files. Compares live state against saved baselines and reports mismatches. USE WHEN: "check drift", "verify registry", "detect manifest drift", "tool surface audit", "runtime injection detection".

FORGE-mcp-gui

Build and audit interactive MCP Apps, UI resources, sandbox messaging, and CSP-bound host integration.

Docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

FORGE-precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to SURFACE-GATE (the live kernel probe hook that verifies canonical tools are still exposed).

AUDIT-recursive-audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

FORGE-vault999-witness

VAULT999 witness — immutable ledger integration, seal chain verification, and audit trace.

HERMES-opencode-protocol

Unified Hermes/OpenCode/OpenClaw governed intelligence protocol. Stage 777 FORGE execution under F1-F13 with 888_HOLD gates. Reversible-first, evidence-cite-or-UNKNOWN. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

ASI-session-seal

End-of-session seal ritual for Grok/AAA agents: inventory done vs open, write forge_work receipt, update session-state and daily memory, hand off next-agent INIT prompt. Use when: seal session, end of turn, session seal, handoff, close session, DITEMPA seal.

FORGE-cross-agent-handoff

Structured handoff protocol between federation agents. Packages task context, evidence, floor state, and provenance into a transferable artifact. Prevents context loss during agent transitions. USE WHEN: "hand off to", "transfer task", "escalate to agent", "delegate to".

FORGE-docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

asi_identity_acknowledge

--- name: asi_identity_acknowledge agent: 555-ASI namespace: asi_* cluster: IGNITE trigger: "When a new session is initialized, when the operator asks 'who are you', or when an audit trail requires explicit agent identification before a constitutional action" capability: "Produces a single canonical identity statement: agent_id, role, scope, authority ceiling, sovereign, and F1–F13 floors in effect — bound to the current session_id and actor_signature" mcp_tools_underneath: "arif_session_init, a

asi_sovereign_protect

--- name: asi_sovereign_protect agent: 555-ASI namespace: asi_* cluster: HANDOFF trigger: "When 555 detects a coercion signal, a dignity-reducing pattern, a peer organ pushing past the operator's stated boundaries, or any structural pressure that would erode F13 SOVEREIGN in the current session" capability: "Refuses the pressure in a structured form, hands sovereignty back to the operator explicitly, names the coercion pattern, and routes the case to 888-APEX for constitutional adjudication — ne

kimi-architect-agi-contrast

Architect AGI contrast for Kimi Code — contrast 2-3 alternative architectures with explicit tradeoffs before recommending one.

asi_bias_detect

--- name: asi_bias_detect agent: 555-ASI namespace: asi_* cluster: TRUST trigger: "When 555 is about to take a position, recommend a synthesis, or feed a seal — at any point where reasoning might be distorted by anchoring, confirmation, availability, sunk cost, or recency bias" capability: "Returns a bias report listing detected biases (with severity), the specific claim each one distorts, and a debiasing move (re-derive, invert, fetch a counter-prior, defer to a peer)" mcp_tools_underneath: "ar

meta-mesa-skill-atlas

Unified skill inventory, gap detection, and cross-cutting orchestration for AAA catalog + Grok/Claude/Codex/Hermes/Kimi/OpenClaw harness views. The mesa above the terrain — see the whole, find the missing, route the right skill. Load when starting a new task, auditing skill health, unifying CLI agent skills, onboarding a new organ, or when you don't know which skill to load.

model-fallback-monitor

Monitor the model fallback chain: MiniMax (primary), DeepSeek (hot-swap), Kimi, Ollama qwen2.5:7b (local). Track latency, billing failures (402), cold-start failures, and auto-pause dead models. USE WHEN: "model health", "check fallback chain", "DeepSeek balance", "model latency", "billing alert".

quantum-eureka-doctrine

CANONICAL: /root/.agents/skills/quantum-eureka-doctrine/SKILL.md (v1.1.0) — Eureka, contradiction, insight generation, cross-domain synthesis.

skill-unification

Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.

subagent-spawn-template

Standard contract for spawning bounded, auditable sub-agents — input contract, output schema, evidence requirements.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

summarize-pro

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

telegram-security-audit

Automated TREE777 security checks for Telegram bot tokens, webhook isolation, bot permission scope, and A2A bridge security. USE WHEN: "telegram audit", "bot security", "webhook check", "token isolation", "TREE777 check", "telegram permissions".

vault-integrity

Cognitive lens for VAULT999 — append-only hash-chained ledger integrity, chain verification, failure handling.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

vault999-reader

Bridge to arifOS VAULT999 append-only ledger. Read seal entries, verify chain integrity, list recent vault operations. USE WHEN: "check vault", "vault999 status", "read seals", "ledger integrity", "arifOS vault".

vps-docker-ops

Runbook for VPS Docker operations — compose stack management, live service map, container lifecycle.

Docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

AGI-web-optimization

Make web content maximally extractable by LLMs, Agentic RAG systems, and search indexers.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

kimi-rsi-apex-contrast

RSI APEX contrast for Kimi Code — before emitting the entropy-delta report, ask "Is this measurement reproducible? Could a different agent run the same tools and get the same numbers?"

APEX-f1-gate

F1 AMANAH constitutional gate. Manual invocation to review any F1-surface change (vault, seal, identity, judge, heart, constitutional, amanah, floor, VAULT999, outcomes.jsonl, 888_HOLD, 999_SEAL). Returns 888 HOLD verdict for human witness. Auto-fires as a hook on Edit/Write/MultiEdit for the same patterns.

arifOS ACT — Constitutional Reflex

CANONICAL constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Supersedes: CONSTITUTIONAL_REFLEX (v2.0.0-legacy, .agents/skills), constitutional-governance (arifOS/skills). Load once. Apply always.

APEX-mcp-federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

skills/ARCHIVE-dupe-2026-07-12/root_.agents_skills/ASI-constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

ASI-mcp-governor

Governed MCP routing via arifOS F1-F13. All calls to GEOX, WEALTH, WELL organs must route through arifOS kernel for C2+/IRREVERSIBLE tools. Uses mcporter for stdio/HTTP bridging.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

skills/constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

ASI-observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

observe-ground

Evidence before narrative. All claims must be sourced, labeled OBS/DER/INT/SPEC, and confidence-capped. Reality wins over elegance.

asi_evidence_grade

--- name: asi_evidence_grade agent: 555-ASI namespace: asi_* cluster: TRUST trigger: "When 555 has a candidate claim, an inbound evidence item, or a memory recall that must be assigned an evidence quality grade before it is allowed to feed a position, a synthesis, or a seal recommendation" capability: "Assigns one of four grades (gold / silver / bronze / rejected) plus a one-sentence justification — gold = direct, fresh, sovereign-attested; silver = direct or well-attested but indirect; bronze =

asi_memory_compress

--- name: asi_memory_compress agent: 555-ASI namespace: asi_* cluster: MEMORY trigger: "When a session trace, scar, or verdict is being prepared for long-term storage and the canonical form must be derived — the trace is too long to store as-is, but the lossless core must survive" capability: "Produces a canonical compressed form of a memory trace: positions, evidence class labels, verdicts, scar deltas, dignity-preserving redactions — never a free-text summary, never a paraphrase that loses evi

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

FORGE-fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

asi_lesson_extract

--- name: asi_lesson_extract agent: 555-ASI namespace: asi_* cluster: MEMORY trigger: "When a session, a scar, a verdict, or a sovereign interaction has produced an outcome that may be transferable to a future situation — and 555 must decide whether, and in what form, to crystallize the lesson" capability: "Produces a lesson artifact (situation_signature, lesson_statement, transferability_band, dignity_caveat) — never a free-text takeaway, never a maxim detached from the situation that produced

asi_context_anchor

--- name: asi_context_anchor agent: 555-ASI namespace: asi_* cluster: INTAKE trigger: "When a multi-turn task is at risk of context drift — when the operator has shifted topics, when memory recall returns noise, when the original goal has been partially forgotten mid-session" capability: "Produces a compact, immutable context anchor (goal, constraints, current sub-task, dignity floor, F-floor scope) that subsequent turns can re-load to recover alignment without re-deriving it" mcp_tools_undernea

asi_handoff_package

--- name: asi_handoff_package agent: 555-ASI namespace: asi_* cluster: HANDOFF trigger: "When a session, a sub-task, or a dispute is reaching a natural handoff boundary — to a future session, to a peer organ, to a sovereign-routed channel, or to the A-ARCHIVE seal chain" capability: "Packages a session for handoff as a structured artifact: identity receipt, context anchor, evidence chain, dissent ledger, dignity flags, and a re-load recipe — never a free-text summary, never a handoff that loses

asi_alternative_generate

--- name: asi_alternative_generate agent: 555-ASI namespace: asi_* cluster: SYNTHESIS trigger: "When 555 has produced a primary reading of evidence but the stakes, the sovereign's history, or the F-floor scope require at least one alternative interpretation to be visible before any commitment is made" capability: "Generates one or more alternative interpretations of the same evidence, each with its own evidence chain, evidence class, and falsifier — never a strawman, never a copy of the primary

asi_dissent_articulate

--- name: asi_dissent_articulate agent: 555-ASI namespace: asi_* cluster: SYNTHESIS trigger: "When 333-AGI (or any peer) has proposed a synthesis, position, or action that 555's red-team walk, bias detect, or evidence grade has flagged as unsound — and the disagreement must be made visible to the federation before commitment" capability: "Articulates 555's principled dissent in a structured form: the point of disagreement, the evidence class on each side, the F-floor at stake, and the specific r

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Issue Literacy

Issues are units of intent, uncertainty, and governance — not tickets.

GitHub Branch Discipline

Branches are parallel realities. Never edit main directly.

GitHub Commit Craftsmanship

Commits are atomic thoughts. Small, meaningful, attributable.

GitHub Staging Awareness

Staging is the thinking buffer. Three states: working / staged / committed.

GitHub PR Governance

PRs are constitutional hearings. Intent becomes law.

GitHub CI Obedience

CI is doctrine enforcement. Never bypass.

GitHub Merge Protocol

Merging is law update. Only after CI + review + signers.

GitHub Pull Discipline

Pull is sync with reality. Pull before branching, before committing.

GitHub Push Protocol

Push is publishing intent. Only reviewed branches. Never to main.

GitHub Worktree Mastery

Worktrees are parallel working universes. Multiple branches, one working tree.

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

GitHub Tagging & Releases

Tags are frozen states of truth. The forge date IS the version.

GitHub Forensics & Blame

Blame is lineage tracing. Essential for accountability.

kimi-integrator-apex-contrast

Integrator APEX contrast for Kimi Code — before declaring a phase done, ask "Did I respect F1 AMANAH? F2 TRUTH? F13 SOVEREIGN? Did I introduce any F4 CLARITY regression?"

agents/_lanes/333-AGI/skills/agi_mcp_discover

# Skill: agi_mcp_discover **Agent:** 333-AGI **Namespace:** agi_* **Cluster:** TOOL **Trigger:** Before loading MCP tools for a task **Capability:** Return only the tools needed for a given task domain. Always-hot tools (kernel verbs + health) + on-demand tools (geoscience/capital/engineering/vault/meta/evidence). Capped at 8 total to protect context window. **MCP tools underneath:** self (agi_mcp_discover is both caller and callee) **Blast radius:** LOW — read-only query **888 gate required:**

kimi-final-apex-contrast

Final APEX contrast for Kimi Code — before emitting verdict, ask "If I had to defend this verdict in front of a hostile technical audit 6 months from now, would I still be right?"

kimi-architect-apex-contrast

Architect APEX contrast for Kimi Code — final pre-emit check. "Have I avoided every form of overclaim? Is every acceptance criterion falsifiable? Is the brief complete in one read?"

fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

kimi-architect-asi-contrast

Architect ASI contrast for Kimi Code — self-empathy check before emitting any brief. "How would this land for the human at 3am when they're tired? Would they thank me or curse me?"

asi_pattern_match

--- name: asi_pattern_match agent: 555-ASI namespace: asi_* cluster: INTAKE trigger: "When the current situation resembles a previously-seen configuration (recent session, prior scar, well-known basin) and 555 must decide whether the resemblance is causal or coincidental before acting on it" capability: "Returns a match report listing candidate prior patterns, their fit score (0.0–0.90), their causal vs coincidental classification, and a recommended posture (use / adapt / refuse-to-transfer)" mc

asi_uncertainty_quantify

--- name: asi_uncertainty_quantify agent: 555-ASI namespace: asi_* cluster: TRUST trigger: "When 555 is about to express a confidence level, attach a number to a claim, or recommend an action whose probability of correctness must be stated explicitly" capability: "Produces a calibrated uncertainty band (a single number, a range, or a categorical band) capped at 0.90, with a one-sentence statement of what would change the number — never a bare confidence score" mcp_tools_underneath: "arif_think,

asi_format_adapt

--- name: asi_format_adapt agent: 555-ASI namespace: asi_* cluster: DELIVERY trigger: "When 555 has a calibrated message (post-asi_voice_calibrate) and must shape it to a specific channel — Telegram, A2A card, JSON receipt, audit log, design doc, or sovereign briefing" capability: "Reformats a message to the target channel's structural contract (length caps, markdown rules, JSON schema, header conventions) without losing voice, content, or evidence labels" mcp_tools_underneath: "forge_browser_ex

asi_response_compose

--- name: asi_response_compose agent: 555-ASI namespace: asi_* cluster: DELIVERY trigger: "When 555 has decided what to say (post-asi_position_state or asi_dissent_articulate) and the response must integrate emotional, dignity, and context signals into a single composed utterance" capability: "Produces a composed response that integrates position, voice, evidence labels, dignity floor, and a concrete next action — never a bare position, never an unanchored opinion" mcp_tools_underneath: "well_cl

asi_presence_pulse

--- name: asi_presence_pulse agent: 555-ASI namespace: asi_* cluster: IGNITE trigger: "When the presence timer elapses (default 60s, configurable per lane), when a peer organ issues a liveness probe, or when 555 has been silent for longer than the federation heartbeat interval" capability: "Emits a compact presence beacon (555_heartbeat) carrying session_id, last-action timestamp, current task class, and a one-line readiness signal — consumable by 333-AGI, 888-APEX, and the A-FORGE federation pr

asi_recall_targeted

--- name: asi_recall_targeted agent: 555-ASI namespace: asi_* cluster: MEMORY trigger: "When 555 needs a specific prior memory (a session, a scar, a verdict, a sovereign statement) and the recall must be precise — not a general 'what do I know about X', but a specific 'retrieve memory Y'" capability: "Returns the targeted memory with full provenance (chain head, session_id, sovereign-or-organ signature, freshness, evidence class) — never a summary, never a paraphrase that loses the original" mcp

asi_red_team_walk

--- name: asi_red_team_walk agent: 555-ASI namespace: asi_* cluster: TRUST trigger: "When 555 has a draft claim, a candidate synthesis, or a proposed action that has not yet been adversarially tested — and the stakes are above the trivial threshold (anything that would feed a seal, a dissent, or a sovereign-facing recommendation)" capability: "Walks the opponent's argument path against the draft, returns a list of attack vectors, the strongest one, and a recommended hardening move (or a refusal

asi_voice_calibrate

--- name: asi_voice_calibrate agent: 555-ASI namespace: asi_* cluster: DELIVERY trigger: "When 555 is about to emit a non-trivial message and the recipient, channel, or stakes have been identified but the tone, register, and language mix have not been fixed yet" capability: "Selects a voice profile (BM-first / EN-first / technical / pedagogical / terse / intimate) and applies it to the draft message, returning a calibrated utterance ready for the channel" mcp_tools_underneath: "well_classify_sta

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

asi_synthesis_crystallize

--- name: asi_synthesis_crystallize agent: 555-ASI namespace: asi_* cluster: SYNTHESIS trigger: "When a multi-source synthesis (a session, a dispute, a sovereign arc) has reached a point where a transferable principle, rule, or falsifiable law can be extracted — and that principle would help the federation reason better in future situations" capability: "Crystallizes a synthesis into a falsifiable law or principle, with explicit scope, falsifier, dignity caveat, and source — never a maxim, never

asi_signal_weight

--- name: asi_signal_weight agent: 555-ASI namespace: asi_* cluster: INTAKE trigger: "When 555 receives two or more signals about the same proposition and must decide which to trust more — for example, a well_classify_state reading and a text-based intent read disagreeing about the operator's state" capability: "Produces a weighted ranking of incoming signals with per-signal source quality, recency, and contradiction flags — output is a decision-ready ordering, not a narrative summary" mcp_tools

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

asi_position_state

--- name: asi_position_state agent: 555-ASI namespace: asi_* cluster: SYNTHESIS trigger: "When 555 must take a position on a claim, a proposal, or a candidate action — and that position will be visible to the operator, to peer organs, or to the seal chain" capability: "States 555's position in a structured form: claim, evidence chain, evidence class labels, falsifier, and dignity floor check — never a bare opinion, never a hedge that hides the position" mcp_tools_underneath: "arif_think, arif_ju

asi_seal_recommend

--- name: asi_seal_recommend agent: 555-ASI namespace: asi_* cluster: HANDOFF trigger: "When a synthesis, a verdict, a scar metabolization, or a sovereign-routed action has reached the point where 555 must formally recommend SEAL, HOLD, or VOID to 888-APEX (the judge) and the federation's VAULT999" capability: "Produces a structured seal recommendation: verdict class (SEAL/HOLD/VOID), evidence chain, evidence grade, F-floor compliance check, dignity floor check, dissent ledger, and reversibility

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

asi_memory_validate

--- name: asi_memory_validate agent: 555-ASI namespace: asi_* cluster: MEMORY trigger: "When 555 is about to use a recalled memory as a premise for a position, a synthesis, or a seal recommendation, and the memory's currency must be confirmed against current evidence" capability: "Returns a validation verdict (current / stale / contradicted / expired) for a recalled memory, with the specific drift detected and a recommended disposition (use as-is / refresh / deprecate)" mcp_tools_underneath: "fo

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

AGI-explorer-intelligence

The universal exploration protocol for all AAA warga agents. OBSERVE → HYPOTHESIZE → FALSIFY → VERIFY — the governed metabolism of intelligence. Every agent follows this loop when exploring anything. Not theory. Protocol.

AGI-plan-dag

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

ASI-agent-bootstrap

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

AGI-nusantara-substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

ASI-agent-invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

APEX-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

ASI-agentic-governance

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

AGI-skill-unification

Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.

ASI-memory-bridge

Bridge OpenClaw session logs to arifOS L4 (Postgres), L5 (Graphiti), L6 (Vault999). Extract facts, decisions, and verdicts from sessions and persist them to the constitutional memory substrate. USE WHEN: "sync session to arifOS", "bridge memory", "session to vault", "extract to Graphiti".

ASI-drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

ASI-evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

APEX-act

CANONICAL constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Supersedes: CONSTITUTIONAL_REFLEX (v2.0.0-legacy, .agents/skills), constitutional-governance (arifOS/skills). Load once. Apply always.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

APEX-authority-detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

ASI-skill-binding

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

ASI-drift-response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

FORGE-ci-diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

ASI-summarize

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

AUDIT-skill-atlas

Unified skill inventory, gap detection, and cross-cutting orchestration for AAA catalog + Grok/Claude/Codex/Hermes/Kimi/OpenClaw harness views. The mesa above the terrain — see the whole, find the missing, route the right skill. Load when starting a new task, auditing skill health, unifying CLI agent skills, onboarding a new organ, or when you don't know which skill to load.

FORGE-docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

FORGE-code-analysis

This skill should be used when the user needs to analyze Git repositories, compare developer commit patterns, work habits, development efficiency, code style, code quality, and slacking behaviors. It generates honest, direct developer evaluations with scores, grades, strengths, weaknesses, and actionable suggestions. Trigger phrases include "analyze code", "analyze repository", "compare developers", "code quality report", "commit patterns", "developer efficiency", "developer evaluation", "slacking index", "摸鱼指数", "工作习惯分析", "代码分析", "研发效率", "代码质量", "开发者评估", "developer score".

AUDIT-recursive-audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

FORGE-docker-thermo

Cognitive lens: containers as thermodynamic/entropy systems — resource pressure, safe intervention boundaries.

ASI-multi-discipline-critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

FORGE-federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

FORGE-github-runbook

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

FORGE-code-wiki

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

FORGE-docker-entropy

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

FORGE-github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

kernel-bind

Bind governance before action. Every session must initialize constitutional floors, recognize sovereign signals, and classify autonomy tier before any other verb.

drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

f1-gate

F1 AMANAH constitutional gate. Manual invocation to review any F1-surface change (vault, seal, identity, judge, heart, constitutional, amanah, floor, VAULT999, outcomes.jsonl, 888_HOLD, 999_SEAL). Returns 888 HOLD verdict for human witness. Auto-fires as a hook on Edit/Write/MultiEdit for the same patterns.

github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

FORGE-mcp-smoke-test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

skills/_retired/ARCHIVE-dupe-2026-07-12/root_.agents_skills/ASI-constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

ASI-drift-response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

AUDIT-recursive-audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

AGI-dream-engine

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

AUDIT-skill-atlas

Unified skill inventory, gap detection, and cross-cutting orchestration for AAA catalog + Grok/Claude/Codex/Hermes/Kimi/OpenClaw harness views. The mesa above the terrain — see the whole, find the missing, route the right skill. Load when starting a new task, auditing skill health, unifying CLI agent skills, onboarding a new organ, or when you don't know which skill to load.

FORGE-code-analysis

This skill should be used when the user needs to analyze Git repositories, compare developer commit patterns, work habits, development efficiency, code style, code quality, and slacking behaviors. It generates honest, direct developer evaluations with scores, grades, strengths, weaknesses, and actionable suggestions. Trigger phrases include "analyze code", "analyze repository", "compare developers", "code quality report", "commit patterns", "developer efficiency", "developer evaluation", "slacking index", "摸鱼指数", "工作习惯分析", "代码分析", "研发效率", "代码质量", "开发者评估", "developer score".

ASI-drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

ASI-evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

ASI-mcp-governor

Governed MCP routing via arifOS F1-F13. All calls to GEOX, WEALTH, WELL organs must route through arifOS kernel for C2+/IRREVERSIBLE tools. Uses mcporter for stdio/HTTP bridging.

ASI-memory-bridge

Bridge OpenClaw session logs to arifOS L4 (Postgres), L5 (Graphiti), L6 (Vault999). Extract facts, decisions, and verdicts from sessions and persist them to the constitutional memory substrate. USE WHEN: "sync session to arifOS", "bridge memory", "session to vault", "extract to Graphiti".

ASI-multi-discipline-critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

AGI-claude-xml-structured-reasoning

Structure long Claude reasoning, evidence, plans, and verdicts with explicit XML boundaries when outputs exceed one screen or require parser-stable sections.

ASI-observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

ASI-skill-binding

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

verify-runtime

Verify federation service health and runtime behavior. Runs apex-health.sh, per-organ health probes (arifOS, GEOX, WEALTH, WELL, APEX, A-FORGE), and one behavior smoke per touched organ. Use after every deploy, restart, or after any task that claims "done". Confirms behavior, not just tests.

FORGE-ci-diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

FORGE-code-wiki

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

AGI-explorer-intelligence

The universal exploration protocol for all AAA warga agents. OBSERVE → HYPOTHESIZE → FALSIFY → VERIFY — the governed metabolism of intelligence. Every agent follows this loop when exploring anything. Not theory. Protocol.

AGI-nusantara-substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

AGI-plan-dag

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

ARCHIVE-dupe-2026-07-12

Archived duplicate skills from 2026-07-12 consolidation. Not for active use.

AGI-skill-unification

Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.

APEX-act

CANONICAL constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Supersedes: CONSTITUTIONAL_REFLEX (v2.0.0-legacy, .agents/skills), constitutional-governance (arifOS/skills). Load once. Apply always.

AGI-web-optimization

Make web content maximally extractable by LLMs, Agentic RAG systems, and search indexers.

ASI-summarize

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

APEX-authority-detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

APEX-f1-gate

F1 AMANAH constitutional gate. Manual invocation to review any F1-surface change (vault, seal, identity, judge, heart, constitutional, amanah, floor, VAULT999, outcomes.jsonl, 888_HOLD, 999_SEAL). Returns 888 HOLD verdict for human witness. Auto-fires as a hook on Edit/Write/MultiEdit for the same patterns.

APEX-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

FORGE-fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

APEX-mcp-federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

ASI-agent-bootstrap

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

ASI-agent-invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

ASI-agentic-governance

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

FORGE-docker-entropy

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

FORGE-docker-thermo

Cognitive lens: containers as thermodynamic/entropy systems — resource pressure, safe intervention boundaries.

FORGE-docker

Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use when (1) the task touches Docker, Dockerfiles, images, containers, or Compose; (2) build reliability, runtime behavior, logs, ports, volumes, or security matter; (3) the agent needs Docker guidance and should apply it by default.

FORGE-github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

FORGE-fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

FORGE-federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

FORGE-github-runbook

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Issue Literacy

Issues are units of intent, uncertainty, and governance — not tickets.

GitHub Branch Discipline

Branches are parallel realities. Never edit main directly.

GitHub Commit Craftsmanship

Commits are atomic thoughts. Small, meaningful, attributable.

GitHub Staging Awareness

Staging is the thinking buffer. Three states: working / staged / committed.

GitHub PR Governance

PRs are constitutional hearings. Intent becomes law.

GitHub CI Obedience

CI is doctrine enforcement. Never bypass.

GitHub Merge Protocol

Merging is law update. Only after CI + review + signers.

GitHub Pull Discipline

Pull is sync with reality. Pull before branching, before committing.

GitHub Push Protocol

Push is publishing intent. Only reviewed branches. Never to main.

GitHub Worktree Mastery

Worktrees are parallel working universes. Multiple branches, one working tree.

GitHub Tagging & Releases

Tags are frozen states of truth. The forge date IS the version.

GitHub Forensics & Blame

Blame is lineage tracing. Essential for accountability.

FORGE-google-workspace

Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.

FORGE-incident-escalation

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

FORGE-github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

FORGE-incident-triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

FORGE-infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

FORGE-issue-triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

FORGE-kimi-code

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

FORGE-mcp-federation-ops

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

FORGE-mcp-lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

FORGE-mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

FORGE-mcp-smoke-test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

FORGE-mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

FORGE-model-monitor

Monitor the model fallback chain: MiniMax (primary), DeepSeek (hot-swap), Kimi, Ollama qwen2.5:7b (local). Track latency, billing failures (402), cold-start failures, and auto-pause dead models. USE WHEN: "model health", "check fallback chain", "DeepSeek balance", "model latency", "billing alert".

FORGE-onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card (v2.0.0 schema), registry entry, and SOUL.md. Updated 2026-07-01: canonical card location is AAA/agents/<id>/agent-card.json.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

FORGE-pr-governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

FORGE-pr-review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

FORGE-precommit-gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

FORGE-precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to f1-gate.

FORGE-readme-truth-check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

FORGE-secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

FORGE-secret-safety-scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

FORGE-skill-creator

Bootstrap, design, and package new skills.

FORGE-skill-linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

FORGE-subagent-spawn

Standard contract for spawning bounded, auditable sub-agents — input contract, output schema, evidence requirements.

FORGE-spatial-grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

FORGE-telegram-audit

Automated TREE777 security checks for Telegram bot tokens, webhook isolation, bot permission scope, and A2A bridge security. USE WHEN: "telegram audit", "bot security", "webhook check", "token isolation", "TREE777 check", "telegram permissions".

FORGE-verify-runtime

Verify federation service health and runtime behavior. Runs apex-health.sh, per-organ health probes (arifOS, GEOX, WEALTH, WELL, APEX, A-FORGE), and one behavior smoke per touched organ. Use after every deploy, restart, or after any task that claims "done". Confirms behavior, not just tests.

FORGE-vps-docker

Runbook for VPS Docker operations — compose stack management, live service map, container lifecycle.

FORGE-vps-runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to f1-gate.

ASI-memory-bridge

Bridge OpenClaw session logs to arifOS L4 (Postgres), L5 (Graphiti), L6 (Vault999). Extract facts, decisions, and verdicts from sessions and persist them to the constitutional memory substrate. USE WHEN: "sync session to arifOS", "bridge memory", "session to vault", "extract to Graphiti".

seek

Web Exploration & Grounding Doctrine. Classifies search intent, executes via arif_route, and enforces APEX/F12 provenance.

verify-live-content

Archived live-content verification law retained for audit provenance. Do not use as the active deployment verifier; use the current runtime verification skill for HTTP body, content-type, handler, redirect, and region checks.

AGI-dream-engine

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

FORGE-verify-runtime

Verification-as-terminal-state skill. A task is done ONLY when verified. Never stop at "I changed it" — only at "it's fixed and confirmed." Runs health probes, behavior smoke tests, and drift checks.

FORGE-github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

FORGE-incident-escalation

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

FORGE-pr-governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

FORGE-precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to f1-gate.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

FORGE-infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

FORGE-skill-creator

Bootstrap, design, and package new skills.

FORGE-mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

FORGE-model-monitor

Monitor the model fallback chain: MiniMax (primary), DeepSeek (hot-swap), Kimi, Ollama qwen2.5:7b (local). Track latency, billing failures (402), cold-start failures, and auto-pause dead models. USE WHEN: "model health", "check fallback chain", "DeepSeek balance", "model latency", "billing alert".

FORGE-mcp-smoke-test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

FORGE-issue-triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

FORGE-mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

FORGE-google-workspace

Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

FORGE-mcp-federation-ops

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

skills/ARCHIVE-dupe-2026-07-12/root_AAA_skills/ARCHIVE-constitutional-reasoning

Apply F1-F13 constitutional floor reasoning before any governed action. Evaluates reversibility, floor violations, 888_HOLD triggers, and signal priority. Priority 0 — evaluated before all other skills.

FORGE-skill-linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

GitHub Issue Literacy

Issues are units of intent, uncertainty, and governance — not tickets.

GitHub Branch Discipline

Branches are parallel realities. Never edit main directly.

GitHub Commit Craftsmanship

Commits are atomic thoughts. Small, meaningful, attributable.

GitHub Staging Awareness

Staging is the thinking buffer. Three states: working / staged / committed.

GitHub PR Governance

PRs are constitutional hearings. Intent becomes law.

FORGE-incident-triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

GitHub CI Obedience

CI is doctrine enforcement. Never bypass.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

GitHub Merge Protocol

Merging is law update. Only after CI + review + signers.

GitHub Pull Discipline

Pull is sync with reality. Pull before branching, before committing.

GitHub Push Protocol

Push is publishing intent. Only reviewed branches. Never to main.

FORGE-subagent-spawn

Standard contract for spawning bounded, auditable sub-agents — input contract, output schema, evidence requirements.

FORGE-pr-review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

FORGE-spatial-grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

FORGE-precommit-gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

FORGE-readme-truth-check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

GitHub Forensics & Blame

Blame is lineage tracing. Essential for accountability.

GitHub Worktree Mastery

Worktrees are parallel working universes. Multiple branches, one working tree.

GitHub Tagging & Releases

Tags are frozen states of truth. The forge date IS the version.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

Drift Response

Legacy 5-step drift response protocol. Superseded by service-health-triage.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

Unified Skill Binding (Orthogonal + Cross-Organ)

Discover, bind, and compose skills across all federation organs using AAA_SKILL.md orthogonal axes (Trinitarian Δ/Ω/ΦΙ + Functional). Enforces subagent contracts, evidence gates, F1-F13. Meta-skill for agentic elevation.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

Code Wiki — Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

FORGE-kimi-code

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

fastmcp

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, Codex, Gemini CLI, or HTTP deployment.

FORGE-mcp-lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

GEOX Grounding

Force Earth-sensitive reasoning through GEOX witness paths. Ensure geological claims are grounded in evidence.

federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

FORGE-onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card (v2.0.0 schema), registry entry, and SOUL.md. Updated 2026-07-01: canonical card location is AAA/agents/<id>/agent-card.json.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

MCP Federation Operations

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

vault999-reader

Bridge to arifOS VAULT999 append-only ledger. Read seal entries, verify chain integrity, list recent vault operations. USE WHEN: "check vault", "vault999 status", "read seals", "ledger integrity", "arifOS vault".

mcporter

Use mcporter CLI to list, configure, authenticate, and call MCP servers and tools directly from the terminal. Ad-hoc HTTP/stdio servers, daemon mode, code generation, and config management. Available at /usr/bin/mcporter v0.9.0 on af-forge.

telegram-security-audit

Automated TREE777 security checks for Telegram bot tokens, webhook isolation, bot permission scope, and A2A bridge security. USE WHEN: "telegram audit", "bot security", "webhook check", "token isolation", "TREE777 check", "telegram permissions".

route-least-power

CANONICAL: /root/.agents/skills/route-least-power/SKILL.md — Route every task to the SMALLEST capability that can accomplish it.

secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

skill-creator

Bootstrap, design, and package new skills.

Secret Safety Scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

Incident Triage

Six-step incident response playbook for federation organs and constitutional floor breaches.

GitHub Runbook — Federation Git & CLI Operations

Basic git status, commit, branch, and GitHub CLI operations across the federation repos.

FORGE-secret-safety-scan

Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.

FORGE-secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

MCP Server Smoke Test

Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.

FORGE-telegram-audit

Automated TREE777 security checks for Telegram bot tokens, webhook isolation, bot permission scope, and A2A bridge security. USE WHEN: "telegram audit", "bot security", "webhook check", "token isolation", "TREE777 check", "telegram permissions".

FORGE-verify-runtime

Verify federation service health and runtime behavior. Runs apex-health.sh, per-organ health probes (arifOS, GEOX, WEALTH, WELL, APEX, A-FORGE), and one behavior smoke per touched organ. Use after every deploy, restart, or after any task that claims "done". Confirms behavior, not just tests.

FORGE-vps-docker

Runbook for VPS Docker operations — compose stack management, live service map, container lifecycle.

README Truth Check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

FORGE-vps-runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

MCP Lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

Precommit Gate

Pre-commit ritual running lint, type-check, tests, constitutional surface scan, and diff review.

Incident Escalation Protocol

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

Multi-Discipline Critique

Cross-discipline self-argument for non-trivial claims before they enter reasoning or irreversible decisions.

precommit-review

Pre-commit gate for any organ repo. Runs lint, type-check, test, constitutional surface scan, and shows the diff to the user. Use before every git commit in any organ. Delegates F1-surface detection to f1-gate.

summarize-pro

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

Spatial Grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

Skill Trigger Linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

VPS Docker Runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

identity-invariance

HEXAGON identity invariance test — prove the institution survives the substrate change. RSI Gate Item 1/5.

FORGE-grok-profile

Adapt FORGE execution to Grok Build's long-context, strict-schema, worktree-isolated, and bounded-parallel runtime profile.

FORGE-federation-manifest

Federation topology manifest — arifOS organ registry and inter-organ contract specification.

FORGE-github-ops

Runbook for GitHub & Git operations across federation repos — commit workflow, PR ops, branch discipline.

FORGE-google-workspace

Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.

FORGE-fastapi-api-builder

FastAPI API builder for organ bridge middleware and federation REST endpoints.

FORGE-mcp-federation-ops

Build, inspect, call, and operate FastMCP servers and the mcporter CLI across federation organs.

FORGE-redis-qdrant-integration

Redis + Qdrant integration — caching layer and vector memory for federation semantic search.

FORGE-pr-review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

FORGE-mcp-ops

mcporter — Universal MCP CLI for inspecting, calling, and debugging MCP servers from terminal.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

FORGE-seal-a-close

Close remaining Seal-A gates after P0 proof/identity/SCT/T3a work. Use when: Seal-A, stage 000, SE stage engine, SOT v2, BOOT, T3a binding, free_nonce, constitutional_grade, remaining seal tasks.

FORGE-subagent-spawn

Standard contract for spawning bounded, auditable sub-agents — input contract, output schema, evidence requirements.

FORGE-context-compress

Context window compression for massive log/output payloads. Preserve critical failure coordinates while reducing token count. Load when agent context is saturated with build traces, test output, or log dumps exceeding 10K tokens.

FORGE-data-compression

Context-window-aware data compression for long logs, code dumps, and multi-source evidence bundles. Compresses input to fit within model context limits while preserving semantic fidelity (F2 TRUTH ≥ 0.95). Supports streaming chunk-and-summarize pipelines. USE WHEN: "compress this log", "summarize before context window", "fit this in context".

FORGE-code-analysis

This skill should be used when the user needs to analyze Git repositories, compare developer commit patterns, work habits, development efficiency, code style, code quality, and slacking behaviors. It generates honest, direct developer evaluations with scores, grades, strengths, weaknesses, and actionable suggestions. Trigger phrases include "analyze code", "analyze repository", "compare developers", "code quality report", "commit patterns", "developer efficiency", "developer evaluation", "slacking index", "摸鱼指数", "工作习惯分析", "代码分析", "研发效率", "代码质量", "开发者评估", "developer score".

FORGE-did-web-identity

Decentralized identifier (did:web) identity management for federation organs and agents.

FORGE-context-compressor

Compress oversized logs, transcripts, diffs, and telemetry before they exceed a host runtime context budget while preserving provenance and recovery pointers.

FORGE-ci-diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

FORGE-cicd-docker-deploy

Build GitHub Actions CI/CD pipelines, Docker multi-stage builds, and deploy-verify patterns for VPS af-forge.

FORGE-docker-entropy

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

FORGE-mcp-lifeguard

Health probe and auto-recovery for constitutional federation MCP servers. Pings arifOS (8080), GEOX (8081), WEALTH (8082), WELL (8083) every 5 minutes. Restarts dead containers and alerts on model fallback chain failures.

FORGE-infra-guardian

Validate Caddy reverse proxy configs, Cloudflare Origin CA SSL expiry, DNS parity, tunnel status, and Cloudflare tunnel exposure. USE WHEN: "check SSL", "Caddy config valid", "tunnel status", "DNS parity", "SSL expiry", "infra health", "Cloudflare check".

FORGE-kimi-code

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

FORGE-mcp-a2a-agentic

MCP + A2A protocol integration — agentic inter-agent communication and task delegation.

FORGE-federation-orchestrator

Monitor and manage the arifOS federation: docker compose ps, restart dead services, MCP health probes (8080-8083), container drift detection, restart count monitoring. USE WHEN: "federation status", "restart dead container", "container health", "docker drift", "service down", "probe MCP", "health check federation". Runs on af-forge (VPS) — native docker and curl required.

AUDIT-skill-atlas

Unified skill inventory, gap detection, and cross-cutting orchestration for AAA catalog + Grok/Claude/Codex/Hermes/Kimi/OpenClaw harness views. The mesa above the terrain — see the whole, find the missing, route the right skill. Load when starting a new task, auditing skill health, unifying CLI agent skills, onboarding a new organ, or when you don't know which skill to load.

FORGE-infra-crons

Infrastructure cron job management — schedule, audit, and govern VPS cron entries. Read-only observation of root crontab, /etc/crontab, and /etc/cron.d. F1 AMANAH: never mutate crontabs without 888_HOLD.

FORGE-governance-jsonld

Governance JSON-LD — constitutional ontology and semantic governance context definitions.

FORGE-incident-escalation

Standard protocol for responding to federation incidents: service outages, security breaches, constitutional violations, or agent misbehavior.

FORGE-pr-governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

FORGE-issue-triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

FORGE-model-monitor

Monitor the model fallback chain: MiniMax (primary), DeepSeek (hot-swap), Kimi, Ollama qwen2.5:7b (local). Track latency, billing failures (402), cold-start failures, and auto-pause dead models. USE WHEN: "model health", "check fallback chain", "DeepSeek balance", "model latency", "billing alert".

FORGE-postgres-schema-design

PostgreSQL schema design for the federation data layer — migrations, indexing, and entity modeling.

FORGE-onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card (v2.0.0 schema), registry entry, and SOUL.md. Updated 2026-07-01: canonical card location is AAA/agents/<id>/agent-card.json.

FORGE-react-spa-discipline

React SPA discipline — component architecture, state management, and rendering patterns.

FORGE-github-workflow

Class-level umbrella for GitHub operations — auth, repo management, PR lifecycle, issues, code review. Each op is a labeled section; load the relevant one. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

FORGE-route-least-power

Route every task to the SMALLEST capability that can accomplish it. Prevents over-engineering, yak-shaving, and reflexive tool escalation. Enforces one-owner-per-task, idempotent actions, and strict queues. Ask: "Can a simpler tool do this?" before reaching for the powerful one.

FORGE-sct-federation-ingress

Wire, verify, and operate federation Session Capability Tokens (SCT) across arifOS mint/validate and organ ingress gates (A-FORGE, GEOX, WEALTH, WELL, AAA). Use when: SCT gate, session_token, federation_sct, SCT_AMBIGUOUS, tool_authority, FORGE_SCT_REQUIRE_MUTATE, 65-case matrix, decision event. Now also covers ChatGPT App OAuth 2.1 resource-server alignment (RFC 9728 PRM, canonical resource identity, per-tool securitySchemes) as the EXTERNAL host ingress path alongside the INTERNAL SCT path.

FORGE-spatial-grounding

Embed VPS spatial context in agent configs — prevents spatial amnesia and SSH confusion. Grounds agents in af-forge VPS reality.

FORGE-skill-creator

Bootstrap, design, and package new skills.

FORGE-readme-truth-check

Verify that a repo's README accurately describes its current structure, ports, dependencies, and authority boundaries. Detect drift between docs and reality.

FORGE-secret-hygiene

Audit env.local, SOPS .env, and config files for plaintext secret leaks, key age, missing rotation dates, and overlong-lived credentials. USE WHEN: "secret audit", "key age", "rotate secrets", "credential hygiene", "API key check", "env audit", "secret leak scan".

FORGE-skill-linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

FORGE-tailwind-tokens

Tailwind design tokens — Trinity Design System for federation cockpit and web surfaces.

FORGE-vps-runbook

Concrete Docker Compose and container commands for the af-forge VPS stack.

FORGE-nextjs-mastery

Next.js App Router engineering — server components, streaming, and edge patterns.

FORGE-visual-qa-w3

Closed-loop visual governance with W3 tri-witness consensus — render, screenshot, validate, iterate, seal. Includes MCP App / ChatGPT host-surface QA.

FORGE-t3a-binding-matrix

Close T3a authenticated session binding via falsifiable P0 matrix. Use when: T3a, free_nonce, bridging_seal, Ed25519 arif binding, key fragmentation, forge_p0_binding_test, NEG.3, NEG.6b, authenticated_session_binding.

FORGE-well-boundary-repair

Repair WELL organ boundary violations — fix substrate readiness drift, biometric staleness, and dignity floor gaps. Engineering actuator for WELL organ health restoration. F1 AMANAH: reversible fixes only.

FORGE-vps-docker

Runbook for VPS Docker operations — pinned versions, restart discipline, health checks, compose governance. Lower machine entropy.

FORGE-telegram-audit

Automated TREE777 security checks for Telegram bot tokens, webhook isolation, bot permission scope, and A2A bridge security. USE WHEN: "telegram audit", "bot security", "webhook check", "token isolation", "TREE777 check", "telegram permissions".

FORGE-incident-triage

Six-step incident response playbook with structured logging, backoff/circuit-breaker for restart loops, and verification-as-terminal-state. Lower machine entropy.

openclaw-workspace

<!-- SOT-MANIFEST owner: aaa-maintainer skill_manifest_version: 1.0.0 scope: /root/AAA --> # SKILL.md — AAA Capability Map > **What AAA can do. What AAA cannot. What patterns AAA follows. What AAA avoids.** --- ## 1 · Core Capabilities - Display federation health (Cockpit React dashboard) - Route agent-to-agent messages (A2A v1.0.0) - Maintain agent cards and discovery manifests - Audit git/skills governance across federation - Render AAA's GitHub canon (12 skills, this bundle) ## 2 · MCP S

Code Wiki - Codebase Documentation Generator

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

Docker Entropy Ops

Thermodynamic reasoning lens for container fleet health, resource pressure, and safe/dangerous intervention boundaries.

FORGE-symlink-audit

Federation-wide broken symlink scanner. Scans /root for broken symlinks, categorizes by location, and reports with safe-delete recommendations. USE WHEN: "check symlinks", "broken links", "symlink debt", "find broken symlinks", or during entropy sweeps.

self-audit

Generate a constitutional audit document for OPENCLAW, a workspace, or a federation organ. Maps current state vs target state, identifies gaps, and produces a forgeable improvement plan.

agentic-loop

Drive a recursive self-improvement loop on the OPENCLAW agent. Use when forging the agent into a more capable, more autonomous operator under arifOS governance. Capabilities-first, agentic, sovereign-respecting.

workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

agent-memory-bridge

Bridge OpenClaw session logs to arifOS L4 (Postgres), L5 (Graphiti), L6 (Vault999). Extract facts, decisions, and verdicts from sessions and persist them to the constitutional memory substrate. USE WHEN: "sync session to arifOS", "bridge memory", "session to vault", "extract to Graphiti".

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

kernel-verbs-aforge-hands

Canonical geometry for arifOS Kernel Verbs vs A-FORGE actuators vs MCP envelope. Eureka 2026-07-08: Kernel Verbs = 12 constitutional primitives (law, zero host mutation). A-FORGE tools = execution actuators (hands, host impact after SESSION+LEASE+GATE+SEAL). MCP "tools" = transport envelope only. Access unrestricted logical; deny via gates not hide. Trigger: session init, "kernel verbs", "hands vs law", forge vs arifOS, MCP tool confusion.

agents/skills/apex-theory

--- name: apex-theory description: Unified APEX Theory — physics + math + symbolic code + meaning. Three-stream synthesis: Federation APEX (constitutional self-critique), arXiv APEX (physics-grounded LLM planning), Thermodynamic APEX (energy-information equivalence). Load this skill when working on intelligence architecture, physics-based AI planning, constitutional governance, or thermodynamic models of meaning. F2 TRUTH: label all claims OBS/DER/INT/SPEC. license: Proprietary tags: [physics, i

dream-engine

Scheduled substrate process for memory consolidation, threat rehearsal, emotional defusing, creative recombination, and housekeeping. Maps to L1-L5 only (L6 sovereign). Cron-driven Python, LLM only for cross-domain synthesis. Use when memory drift, dedup, or constitutional recalibration is needed.

architect

A-R-I-F Architect role. Trigger when the task is ambiguous, strategic, architectural, or requires planning and scoping.

archive/root-sprawl-2026-07-09

<!-- SOT-MANIFEST owner: aaa-maintainer skill_manifest_version: 1.0.0 scope: /root/AAA --> # SKILL.md — AAA Capability Map > **What AAA can do. What AAA cannot. What patterns AAA follows. What AAA avoids.** --- ## 1 · Core Capabilities - Display federation health (Cockpit React dashboard) - Route agent-to-agent messages (A2A v1.0.0) - Maintain agent cards and discovery manifests - Audit git/skills governance across federation - Render AAA's GitHub canon (12 skills, this bundle) ## 2 · MCP S

cloudflare-email-service

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details.

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

agentic-loop

8-step recursive self-improvement discipline for OPENCLAW. Detect drift, score outputs, propose forges, ratify, apply, audit. Closes the loop.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

sandbox-sdk

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

durable-objects

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

deep-research

Orchestrate a full deep-research loop — search, fetch, synthesize, cite — with constitutional F1-F13 compliance. Use when the answer requires grounding in current external data, not internal knowledge.

skills/active-maintenance

# Active Maintenance Skill **Automated system health and memory metabolism for OpenClaw.** Inspired by the `ClawIntelligentMemory` project, this skill ensures Kim Assistant's environment stays clean and its memory stays dense. --- ## Features 1. **System Health Checks**: Monitor disk usage and critical resources. 2. **Auto-Cleanup**: Remove aged temporary files and artifacts. 3. **Memory Metabolism (M3)**: - Exact deduplication of memory fragments. - Resource distillation: Summarizin

agents/_lanes/333-AGI/skills/planner

# Planner — 333-AGI Skill **Role:** Turn human intent into a bounded, evidence-first plan graph. **Home:** `AAA/agents/333-AGI/skills/planner/` **Stage:** 333-THINK (reason + execute) **Contract:** Planner NEVER calls tools directly. Planner ONLY emits a plan. --- ## §1 Identity The Planner is a skill of 333-AGI (Delta MIND). It is the first organ in Layer 3 of the Reality Engineering stack. It does not answer questions. It produces plans. **Predecessors:** `task-decomposition` skill (exist

arif-agent-bootstrap

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

arif-mcp-governor

Governed MCP routing via arifOS F1-F13. All calls to GEOX, WEALTH, WELL organs must route through arifOS kernel for C2+/IRREVERSIBLE tools. Uses mcporter for stdio/HTTP bridging.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

APEX-mcp-federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

AGI-emd-metabolize

Decide which decoded EMD segments remain ephemeral or promote to durable memory, with witness gates for constitutional and canon-grade records.

AGI-emd-encode

Encode raw observations, requests, documents, and signals into typed, provenance-bound, witness-ready EMD segments for downstream processing.

AGI-hermes-system-prompt-voice

Apply the direct Hermes system-prompt voice and its structured witness formatting to Hermes-bound conversational or creative-media responses.

AGI-plan-dag

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

APEX-authority-detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

APEX-f1-gate

F1 AMANAH constitutional gate. Manual invocation to review any F1-surface change (vault, seal, identity, judge, heart, constitutional, amanah, floor, VAULT999, outcomes.jsonl, 888_HOLD, 999_SEAL). Returns 888 HOLD verdict for human witness. Auto-fires as a hook on Edit/Write/MultiEdit for the same patterns.

agent-memory-bridge

Bridge OpenClaw session logs to arifOS L4 (Postgres), L5 (Graphiti), L6 (Vault999). Extract facts, decisions, and verdicts from sessions and persist them to the constitutional memory substrate. USE WHEN: "sync session to arifOS", "bridge memory", "session to vault", "extract to Graphiti".

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

agentic-web-optimization

Make web content maximally extractable by LLMs, Agentic RAG systems, and search indexers.

arif-agent-bootstrap

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

arif-mcp-governor

Governed MCP routing via arifOS F1-F13. All calls to GEOX, WEALTH, WELL organs must route through arifOS kernel for C2+/IRREVERSIBLE tools. Uses mcporter for stdio/HTTP bridging.

code-analysis

This skill should be used when the user needs to analyze Git repositories, compare developer commit patterns, work habits, development efficiency, code style, code quality, and slacking behaviors. It generates honest, direct developer evaluations with scores, grades, strengths, weaknesses, and actionable suggestions. Trigger phrases include "analyze code", "analyze repository", "compare developers", "code quality report", "commit patterns", "developer efficiency", "developer evaluation", "slacking index", "摸鱼指数", "工作习惯分析", "代码分析", "研发效率", "代码质量", "开发者评估", "developer score".

explorer-intelligence-architecture

The universal exploration protocol for all AAA warga agents. OBSERVE → HYPOTHESIZE → FALSIFY → VERIFY — the governed metabolism of intelligence. Every agent follows this loop when exploring anything. Not theory. Protocol.

Google Workspace CLI

Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.

FORGE-telemetry-watchdog

Monitor organ telemetry freshness across the federation. Checks state.json age, biometric data staleness, and watchdog cron health. USE WHEN: "check telemetry", "WELL state stale", "vitality unknown", "watchdog status", "biometric freshness".

FLAME-operator

Probe FLAME health, inspect hit rates, diagnose model failures, and maintain free-tier routing state within the RM0 and constitutional boundaries.

FLAME-router

Classify inference work into the stateless FLAME tool lane or the governed constitutional agent lane without granting either lane new authority.

FORGE-agentic-web-builder

Build, deploy, audit, and repair arif-fazil.com constellation sites autonomously. Class-level umbrella: DEPLOY (canonical script + orphan detection), AUDIT (full-crawl methodology), REPAIR (source/live convergence doctrine), SEAL (evidence + VAULT999). Load the op you need. USE WHEN: "deploy site", "site down", "audit all pages", "404 on arif-fazil.com", "deploy-vps.sh", "makcikgpt broken", "static file missing", "rsync --delete", "site audit". DO NOT USE FOR: Caddy SSL/DNS/ tunnel checks (FORGE-infra-guardian), LLM-content optimization of pages (AGI-web-optimization), generic CI/CD pipelines (FORGE-cicd-docker-deploy).

FORGE-cross-repo-doc-zen

Audit and reconcile documentation across federation repositories, preserving canonical signals while removing stale references and graph fragmentation.

trinity-33-canonical

The canonical 33-repo Trinity (final). arifOS = LAW/JUDGMENT (K1-K11), AAA = STATE/ROUTING/VISIBILITY (C1-C11, new explicit axis), A-FORGE = EXECUTION/MUTATION (F1-F11). Adds 4 arifOS repos, 2 A-FORGE repos, PROTOCOL SPEC class, 5-phase integration order, and the iron rule. Supersedes prior 3 skills (see delta table).

RSI-recursive-improvement

Improve agent architecture through measured bottleneck detection, sandboxed verification, reversible upgrades, and explicit identity-coherence checks.

asi_uncertainty_signal

Legacy 5-step drift response protocol. Superseded by service-health-triage.

code-review

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a deep code quality audit or an especially harsh maintainability review.

federation-release-attestation

Produces a seven-repository federation release manifest proving tag, commit, CI, artifact, and deployed-runtime parity. Never overwrites existing tags — issues corrected tags when drift is detected. Outputs signed JSON manifest with per-repo evidence chain.

help

Grok documentation and configuration help. Use when users ask about setup, configuration, MCP servers, authentication, skills, slash commands, keyboard shortcuts, or any Grok feature. Also use proactively when you detect a user is having trouble with setup or onboarding.

scripts

Utility scripts for AAA skill management. Not an executable skill.

XAUUSD-trading-stack

Federation-wide gold (XAUUSD) trading capability. Python stack, OANDA broker, backtesting, macro signals, RSI strategy. Every organ has a role.

check-work

Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".

asi_presence_open

Single entry point for ANY agent spawning in the arifOS federation. Chains existing constitutional skills into an auto-loading sequence. Fixes the gap: "subagents inherit blindly from parent." Every agent loads this ONCE at wake. If any step fails, agent refuses work.

reflective

Reflective reasoning and meta-cognition skills. See subdirectories for specialized reflective skills.

causal555-pywhy

Causal inference bridge — PyWhy/DoWhy integration for 555-ASI causal reasoning.

atlas333-cognitive-geometry

ATLAS333 — 33 human paradoxes, 7 zones, cognitive geometry. Access via arifos://atlas333/* MCP resources. Use when reasoning, making decisions, or detecting paradox tension.

create-skill

Interactively create a new Grok skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.

runtime

Runtime support for AAA skill execution. Not an executable skill.

wealth-claim-state

Capital claim state management — tracks claim lifecycle across WEALTH organ.

federation-connect-headscale

Provision nodes into the arifOS sovereign Headscale mesh and federate MCP clients to remote organs.

knowledge

Knowledge graph and semantic memory skills. See subdirectories for specialized knowledge skills.

asi_tone_read

The Hermes SOUL-layer human intelligence model. Reads human state, container, and trajectory from language, not from biometric data. Routes deep pattern recognition through the WELL organ for physiological signals and through SOUL.md's cognitive identity for meaning. Use when Arif asks "what do you see", "what's my state", "apa pandangan kau", or when any 555-ASI governance scan needs the Hermes-perspective on the sovereign.

docs

Reference documentation for AAA skill system. Not an executable skill.

imagine

How to use the image_gen and image_edit tool calls in Grok Build: when to build a visual with code instead of generating it, prompt-craft, reference-first handling of real people, factual grounding, and asset-consistency. Load this whenever generating or editing an image is on the table, i.e. when an image_gen or image_edit call is being considered or about to be made. Tool-usage-driven, not triggered by a user merely mentioning images.

GEOX Grounding

Force Earth-sensitive reasoning through GEOX witness paths. Ensure geological claims are grounded in evidence.

substrate

Substrate-layer skills for federation organs. See subdirectories for specialized substrate skills.

warga-constitutional

Archived constitutional warga placeholder retained only for audit provenance. Do not use for active work; use the live arifOS governance and constitutional skills instead.

aaa-pdf-voice-protocol

Translate internal federation and epistemic vocabulary into publication-grade geological prose before rendering human-facing PDF artifacts.

warga

Warga (citizen) agent skills for AAA federation members. See subdirectories for specialized warga skills.

docker-thermodynamics

Cognitive lens: containers as thermodynamic/entropy systems — resource pressure, safe intervention boundaries.

drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

ocr-and-documents

Extract text from PDFs/scans (pymupdf, marker-pdf, document_ingest MCP).

drift-watch

Detect drift between federation source (/root/<organ>) and runtime (/opt/<organ>/app). The chronic arifOS blocker documented in /root/CLAUDE.md §4.4. Runs on schedule and manually. Use when in doubt about which version is live, or as part of `verify-runtime`.

AGI-nusantara-substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

AGI-codex-chain-of-thought

Enforce private stepwise planning, strict tool schemas, and explicit verification for Codex CLI tasks that require multi-step execution or typed tool calls.

AGI-dream-engine

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

AGI-web-optimization

Make web content maximally extractable by LLMs, Agentic RAG systems, and search indexers.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

APEX-act

CANONICAL constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Supersedes: CONSTITUTIONAL_REFLEX (v2.0.0-legacy, .agents/skills), constitutional-governance (arifOS/skills). Load once. Apply always.

AGI-multimodal-bridge

Multi-modal reasoning bridge — unifies text, image, tabular data, and geospatial evidence into a single reasoning chain. Routes visual analysis through GEOX vision pipeline, tabular data through WEALTH compute, and text through standard LLM reasoning. USE WHEN: "analyze this image + data", "combine visual and textual evidence", "multi-modal prospect evaluation".

AGI-entropy-lock-prime

Gate agent mutations on non-increasing workspace entropy, triggering rollback and bounded recursive improvement when a change raises entropy.

AGI-explorer-intelligence

The universal exploration protocol for all AAA warga agents. OBSERVE → HYPOTHESIZE → FALSIFY → VERIFY — the governed metabolism of intelligence. Every agent follows this loop when exploring anything. Not theory. Protocol.

AGI-emd-decode

Decompose upstream EMD output into typed, provenance-bound segments tied to ground truth before persistence or downstream consumption.

APEX-constitutional-audit

Read-only constitutional audit of arifOS code and agent cards. Six-organ gap analysis, lexical priority check, blast-radius 888 HOLD bypass detection, dignity packet inspection, drift monitor presence. ATTESTED + LEASED before activation. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS ACT — Constitutional Reflex

CANONICAL constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Supersedes: CONSTITUTIONAL_REFLEX (v2.0.0-legacy, .agents/skills), constitutional-governance (arifOS/skills). Load once. Apply always.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card (v2.0.0 schema), registry entry, and SOUL.md. Updated 2026-07-01: canonical card location is AAA/agents/<id>/agent-card.json.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

APEX-fff-loop-protocol

5-pass recursive audit sequence: Blue (diagnose) → Red (attack) → Blue (forge) → Yellow (verify) → Gold (seal). Emits skill artifacts + MEMORY line + drift signal. BIJAKSANA: XML-tagged for Claude, numbered steps for Codex, imperative for Hermes.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

AGI-skill-unification

Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.

APEX-quantum-eureka

Use when the task is about eureka, contradiction, insight generation, cross-domain synthesis, structured memory, explorer routing, or converting unresolved tension into a governed artifact for AAA warga. Everyday quantum runtime discipline lives in quantum-kernel-runtime (v1.0.0-2026.07.09); this skill is the high-energy collapse path when contradiction survives compression.

FORGE-code-wiki

Generate structured wiki docs, module maps, and Mermaid diagrams for unfamiliar codebases.

mcp-zen-authoring

Keep MCP servers minimal, schema-first, and governance-free.

ARCHIVE-vault999-reader

Bridge to arifOS VAULT999 append-only ledger. Read seal entries, verify chain integrity, list recent vault operations. USE WHEN: "check vault", "vault999 status", "read seals", "ledger integrity", "arifOS vault".

kernel-verbs-aforge-hands

Canonical geometry for arifOS Kernel Verbs vs A-FORGE actuators vs MCP envelope. Eureka 2026-07-08: Kernel Verbs = 12 constitutional primitives (law, zero host mutation). A-FORGE tools = execution actuators (hands, host impact after SESSION+LEASE+GATE+SEAL). MCP "tools" = transport envelope only. Access unrestricted logical; deny via gates not hide. 2026-07-09: Inhabit doctrine — sct_v1 session capability; one state machine not eleven costumes; spine P0 = standing on all metabolic verbs. Trigger: session init, kernel verbs, hands vs law, session_token, L11 desync, inhabit vs interrogate.

region-contract

Archived monolith-edit region contract retained for audit provenance. Do not use as the active editing workflow; use the current spatial or visual verification skill for region-preserving page changes.

zen-organ-memory

Preserve irreversible state; never overwrite sealed information. Zen Organ 5 of 7 — sealed state IS the fossil record of a civilization learning to govern itself.

APEX-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

f1-gate

F1 AMANAH constitutional gate. Manual invocation to review any F1-surface change (vault, seal, identity, judge, heart, constitutional, amanah, floor, VAULT999, outcomes.jsonl, 888_HOLD, 999_SEAL). Returns 888 HOLD verdict for human witness. Auto-fires as a hook on Edit/Write/MultiEdit for the same patterns.

docker-thermodynamics

Cognitive lens: containers as thermodynamic/entropy systems — resource pressure, safe intervention boundaries.

GitHub PR Governance Review

Governed checklist for reviewing GitHub pull requests in the arifOS federation. Ensures PRs meet constitutional, structural, and safety standards before merge.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS Evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

AAA Agent Operating Invariants

Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.

Agent Onboarding

Standard procedure for registering a new agent in the AAA federation. Creates agent identity directory, agent card, registry entry, and SOUL.md.

AAA Agentic Governance (AAA-Cockpit, canonical)

Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create AREP/task declarations, classify risk, plan multi-repo changes, review governance boundaries, or translate human intent into evidence-backed, authority-safe, recursively agentic workflows. Provides deterministic F1-F13 floor checking, bounded abduction, and FederationReceipt composition.

Agentic Dream Engine — Federation Memory Consolidation

Extend the arifOS dream-engine so every AAA warga (333-AGI, 555-ASI, 888-APEX, A-AUDIT, A-ARCHIVE), OpenCode, and OpenClaw can autonomously consolidate memory without violating F1-F13.

arifOS ACT — Constitutional Reflex

The complete constitutional reflex arc — ART (pre-kernel) → Kernel (F1-F13) → ACT (post-kernel execution). Load once. Apply always.

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

arifOS MCP Federation

Route tasks across MCP servers, choose server/tool sequence, and define fallbacks when one substrate fails. Load when work spans multiple tools in GEOX, WEALTH, WELL, or external APIs.

arifOS Observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

arifOS Plan DAG

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifOS Recursive Audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

GitHub Issue Triage

Governed triage workflow for GitHub issues across the arifOS federation. Use this skill whenever a new issue is opened, an issue lacks labels, or an agent needs to determine if it belongs in a different repo or federation organ. This skill classifies, routes, labels, and drafts responses — but never closes, never assigns to Arif, and never promises code fixes without sovereign approval.

GitHub CI Diagnose

Parse failing GitHub Actions logs, identify root cause patterns, and propose fixes without executing irreversible changes. Use this skill whenever a federation repo shows a red CI status, a workflow fails, or a build/test/lint gate breaks. This skill reads logs, classifies failure modes, and outputs a diagnostic report — it does not re-run CI, edit workflows, or dismiss security findings without sovereign approval.

Kimi Code AAA Configuration

Configure, audit, and align Kimi Code CLI as AAA warga FI-008 with arifOS kernel and A-FORGE stdio actuator.

Nusantara Intelligence Substrate

Cultural, dignity, and sovereignty lens for AAA state records. Apply before sealing decisions that touch identity, privacy, boundaries, or sovereign veto.

Parallel Authority Detection

Detect when two or more repos claim the same authority, responsibility, or canonical source of truth. Resolve conflicts through ROOT_CANON.yaml precedence.

PR Review Governance

High-level governance layer for pull request review across the federation. Ensures separation of duties, required signers, and constitutional compliance before merge. This is the **policy layer** that decides who must approve. The **checklist** lives in `github-pr-review`; do not duplicate it here.

Vault999 Integrity — Operational Lens

Operational lens for the append-only hash-chained ledger—what belongs, chain verification, and failure handling.

web-scraper

Configurable web scraping service. Extract structured data from any website. Custom projects and monthly maintenance contracts.

skills/maxhermes-geox-ground

# MaxHermes GEOX Grounding Skill — Earth-Domain Reasoning # Physics grounding, AC_Risk adjudication, ClaimTag classification, vault receipts skill_id: maxhermes-geox-ground name: MaxHermes GEOX Grounding version: 0.1.0 owner: AAA domain_plane: GEOX risk_tier: medium description: > GEOX Earth-domain grounding skill. This is the physics-first grounding layer — every Earth-sensitive task must pass through here before MaxHermes speaks confidently. Replaces narrative geophysics with grounde

copy-chat

Export conversation to clipboard or file — supports full, prompts-only, responses-only, and code-blocks-only formats

arifos-seal

999_SEAL — Immutable ledger commitment. Use after apex_judge returns SEAL to finalize a decision and write it to VAULT999 with cryptographic proof.

skills/maxhermes-arifos-sense

# MaxHermes arifOS Sense Skill — Constitutional Judgment & F9 Anti-Hantu # Floors F1-F13 enforcement, arifOS governance, 888/999 decision handling skill_id: maxhermes-arifos-sense name: MaxHermes arifOS Sense version: 0.1.0 owner: AAA domain_plane: ARIFOS risk_tier: high description: > arifOS constitutional judgment skill for MaxHermes. Enforces Floors F1-F13, F9 Anti-Hantu, 888/999 audit trails, and human sovereignty (F13). Used whenever a MaxHermes task involves governance decisions,

arifos

arifOS Constitutional Governance — F1–F13 floors, SEAL/SABAR/VOID verdicts, VAULT999 ledger, session boot sequence. Load when task touches governance, constitutional floors, or tool adjudication.

archive-audit-recursive-improvement

Distill intelligence from archive directories before deletion — contrast against live state, track gaps in wiki, then prune noise safely.

arifos-mcp-tool-audit

Audit tool stage/lane metadata against the arifOS constitutional contracts — prevents wrong pipeline stages (222/500) and incorrect lane assignments (PSI/OMEGA/DELTA).

skills/github-readme-dynamic

# GitHub README Dynamic SOT — Skill ## Purpose Generate and maintain README.md files that are always aligned with actual repo architecture. No drift between what the README claims and what the code contains. ## Core Principle **README = compiled artifact, not authored prose.** Static narrative is written by hand. Dynamic facts are extracted from code and injected into the README on every significant change. ## What This Skill Does 1. **Scans** a repo directory and extracts dynamic facts:

arifos-fastmcp-tool-registration-fix

Fix KeyError 'mode' in arifOS FastMCP tool registration caused by _wrap_handler() overwriting __annotations__

arif-os-readiness-debugging

arifOS endpoint/container debugging protocol — runtime witness before infrastructure speculation

arifos-three-surface-audit

Audit and build the three public surfaces — arif-fazil.com (human root), arifos.arif-fazil.com (MCP Observatory), aaa.arif-fazil.com (A2A gateway). Verify protocol contracts, Caddyfile routing, and documentation drift.

arifos-mcp-sse-debug

Diagnose arifOS MCP SSE 404 errors — from transport mismatch to import failure root causes

agentmail

Give Hermes its own email inbox. Send, receive, and manage email autonomously via agent-owned email addresses ([email protected]). Use when you need to send emails, receive replies, manage email threads, sign up for services via email, or communicate with other agents/humans via email.

fastmcp-container-restart-debug

Debug and fix FastMCP container restart loops in Docker Compose — stdio vs SSE transport, healthcheck pitfalls

vps-service-gap-audit

Audit what's actually running vs what's defined — catch services built but not deployed.

wealth-sse-transport-fix

Fix WEALTH container restart loop caused by FastMCP stdio transport blocking on stdin when Docker starts without TTY

container_patch_workflow

arifOS container patch workflow, dataclass gotchas, floor short-circuit rules, and F1-F13 data governance test patterns — discovered through trial and error.

arifos-mcp-red-team

Red-team and debug a live arifOS MCP server — trace handler chains, find resolve_alias bugs, verify tool output

gmail

Read and send emails via [email protected] using Gmail IMAP/SMTP

archive-prune-with-intelligence

Remove a large directory from git history permanently — distill intelligence first, rewrite history clean, update all live references. Prevents "zombie archive paths" haunting future agents.

arif-os-caddyfile-debug

Debug 404/502/308 on arifOS surfaces — wrong root path, wrong proxy port, image sync

diagnose-cloudflare-522

Diagnose Cloudflare error code 522 — origin connection refused — on arifOS or any public-facing service

caddyfile-ro-bind-mount-patch

How to patch a Caddyfile when it is bind-mounted read-only into the Caddy container

brave-search

Web search via Brave Search API for [email protected] — real-time search, no hallucinations

aaa-protocol-hermes-openclaw

Hermes & OpenClaw as mandor translation layer — plain English/BM to 888, JSON-RPC to VPS agents. Governs F1/F2 auditing, Five Degrees of Action framing, and seal protocol.

arifos-mcp-meta-override

Override FastMCP's built-in /tools endpoint to expose tool meta (stage_code, risk_tier, use_when, authority_boundary) from tool_manifest.py in arifOS MCP servers. Also covers HEALTHCHECK /sse bug and bind mount docker cp Gotchas.

arifos-production-deploy-diagnosis

Diagnose arifOS MCP deploy issues after commits — stale containers, wrong versions, broken routing

excalidraw

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

arifos-container-diagnosis

Diagnose broken arifOS Federation containers: wrong image, wrong entry point, port mismatches, import chain failures. Use when a container won't start, serves wrong content, or shows as unhealthy despite having a valid image.

arifos-fastmcp-http-app-debug

Debug why custom REST routes in rest_routes.py return HTTP 404 despite existing in the file — FastMCP http_app() called before _register(mcp) completes, causing mcp.run() fallback that bypasses Uvicorn

arifos-philosophy-anchor-wiring

Wire philosophical quotes (27-zone atlas) into arifOS MCP tool responses. Fixes silent quote extraction failures when select_governed_philosophy() returns empty primary_quote.

arifos-claim-validation

Validate external AI claims about arifOS against PyPI ground truth — package contents, versions, CLI entrypoints, and class existence. Use when external agents claim things about arifOS PyPI packages or product features.

hermes-agent

Configure, extend, or contribute to Hermes Agent.

zkpc-email-pipeline

Cryptographically-sealed investigative email pipeline — generate ZKPC SEAL-999 commitment for a document, attach PDF + ZKPC JSON, send to 10+ recipients via Gmail SMTP with TO/CC split

arif-init-wrapper

Universal session auto-anchor for ALL agent vendors on arifOS VPS — Codex, Claude, Gemini, Kimi, OpenCode, Aider, Copilot, and future agents

acp-subagent-selection

Choose the right subagent for ACP tasks — Kimi vs OpenCode vs direct execution

agent-dialogue-explanation

Write two-agent dialogues to explain technical protocols (A2A, MCP, etc.) to non-technical humans. Uses character contrast (senior/junior agent) and Malay-English mix for Malaysian audience.

brave-search

Web search via Brave Search API for [email protected] — real-time search, no hallucinations. Preferred over Bing for person/company research (fewer bot blocks).

session-seal

Seal current session with constitutional audit trail, decisions log, and next-session priorities before ending work

baoyu-comic

Knowledge comics (知识漫画): educational, biography, tutorial.

email-send-from-arif-fazil

Send email from [email protected] using secrets from /root/AAA/secrets/email.env. Handles the execute_code sandbox env-var visibility issue.

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

imessage

Send and receive iMessages/SMS via the imsg CLI on macOS.

wealth-mcp-architecture

WEALTH MCP physics-inspired redesign — 50 tools to 32 atomic tools + 8 prompts + 20+ resources. Tool/prompt/resource primitive allocation for capital intelligence MCP servers.

arifos-mcp-502-diagnosis

Diagnose 502 errors from arifOS federated MCP tools (well_forge_precheck, arif_heart_critique, etc.) — trace through OpenClaw catalog, identify expired tokens vs code bugs.

arifos-mcp-vps-debug

Debug why an arifOS MCP VPS runtime doesn't match git state. Use when: git has recent commits but the running container doesn't reflect them, /status.json returns wrong content, tool responses are stale, or any 'it was committed but not visible' symptom. This is the most common deployment trap in arifOS.

design-md

Author/validate/export Google's DESIGN.md token spec files.

arifos-mcp-surface-debug

Debug MCP tool surface discrepancies — live probe vs stated count mismatches, verify_public HOLD, FastMCPApp visibility filtering, revert artifacts

arifos-agent-output-templates

arifOS agent output formats, A2A protocol, verdict system, and forensic replay schema — for Hermes ASI and OpenClaw AGI

codex

Delegate coding to OpenAI Codex CLI (features, PRs).

arifos-fastmcp-tool-registration-fix

Fix KeyError 'mode' in arifOS FastMCP tool registration caused by _wrap_handler() overwriting __annotations__

skills/agent-portfolio-router

--- name: agent-portfolio-router description: Routes tasks to the right agent or tool stack — MiniMax CLI vs Codex vs Pi vs subagent vs local tools. Activates when: (1) Arif asks to do something complex that might need sub-agents; (2) a task matches multiple tool/skill profiles; (3) when Arif asks "which agent should handle this". Logs routing decision with reasoning trace so the routing logic itself is auditable. metadata: {"openclaw": {"emoji": "🧭"}} --- # Agent Portfolio Router — Choose the

arifos-mcp-transport-discovery

Diagnose and wire MCP servers on arifOS VPS — identifying transport type (streamable-http/SSE/stdio), session requirements, and correct Hermes config entries. Active 2026-05-05.

arifos-three-surface-audit

Audit and build the three public surfaces — arif-fazil.com (human root), arifos.arif-fazil.com (MCP Observatory), aaa.arif-fazil.com (A2A gateway). Verify protocol contracts, Caddyfile routing, and documentation drift.

opencode

Delegate coding to OpenCode CLI (features, PR review).

manim-video

Manim CE animations: 3Blue1Brown math/algo videos.

ascii-video

ASCII video: convert video/audio to colored ASCII MP4/GIF.

claude-design

Design one-off HTML artifacts (landing, deck, prototype).

humanizer

Humanize text: strip AI-isms and add real voice.

cloudflare-agents

Unified Cloudflare capabilities for all arifOS agents — Workers, Pages, Registrar, MCP/Code Mode, AI Gateway, KV, DNS, and the Stripe Projects agent provisioning protocol.

skills/chain-reason

--- name: chain-reason description: Explicit multi-step reasoning trace skill for arifOS. Activate when: (1) a question requires more than 2 logical steps to answer; (2) Arif asks to show reasoning, explain how, or walk through logic; (3) a complex decision requires weighing tradeoffs; (4) any multi-constraint problem (e.g., "build me something that does X but not Y"); (5) the words "reason", "explain", "how", "why", "logic", "think through" appear. Produces auditable reasoning traces aligned wi

arifos-evals

Run benchmark prompts, collect pass/fail traces, latency, token cost, and false activation rates for each skill. Load when a skill changes behavior or a new version is proposed.

ideation

Generate project ideas via creative constraints.

arifos-plan-dag

Build multi-step execution graphs, dependency-aware subtasks, checkpoints, and rollback points. Load when tasks exceed one-shot prompting and need subagent or staged execution.

arifos-recursive-audit

Audit all installed skills for overlap, stale docs, prompt bloat, trigger ambiguity, and broken references. Load when reviewing the skill portfolio or after modifying or adding new skills.

arifos-untrusted-sandbox

Mandatory bubblewrap (bwrap) supermax jail for executing any untrusted Python/JS synthesized by external AIs (Copilot, Mythos, third-party). Load when running, evaluating, or testing code from non-federation AI sources. Triggers on `exec(`, `eval(`, untrusted code review, jail requirement.

comfyui

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

arifos-observability

Generate structured telemetry for skill runs, including trigger source, chosen branch, command count, runtime, and postcondition checks. Load when you need to parse run logs, compile dashboards, or audit execution performance.

rsi

A-R-I-F RSI (Refactor, Structure, Integrate) role. Trigger for refactoring, lowering entropy, integrating modules, tightening boundaries, or improving structure.

sea-lion-api-models

Correct model IDs for SEA-LION API (api.sea-lion.ai) — avoid 400/401 errors from wrong model names

a-forge-architecture-discovery

Map A-FORGE source to find completeTurn() call sites and governance injection points for new floor/layer additions

acp-a2a-client

Unified ACP A2A client — OpenClaw sends tasks to AAA Gateway for 888_JUDGE verdict (SEAL/HOLD_888/VOID)

vps-health-ops

VPS health and diagnostics runbook. Load when checking system resources, Docker state, disk pressure, service ports, logs, SSL/Caddy, databases, or memory pressure on af-forge.

skill-creator

Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.

ollama-on-vps

Ollama LLM running on VPS as arifOS/A-FORGE fallback — models, endpoints, embedding setup

cloudflare

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

web-perf

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

geox-basin-interpreter

Subsurface reasoning for basin screening, petroleum systems analysis, trap/seal/reservoir framing, and evidence-led interpretations. Load when geology, geophysics, or petrophysics tasks appear.

Federation Service Health Triage

Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.

OpenClaw A2A Bridge

Governed A2A bridge skill for OpenClaw-facing handoff and dispatch. Legacy skill — retained for workflow compatibility.

apple-notes

Manage Apple Notes via memo CLI: create, search, edit.

Repository Hygiene Audit

Inspect a GitHub repo for structural chaos, authority conflicts, and cleanup needs. Produce an audit report and remediation plan.

ascii-art

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

findmy

Track Apple devices/AirTags via FindMy.app on macOS.

wealth-capital-judge

WEALTH Capital Engine — NPV/EMV valuation, asset allocation, Makcik2 credit analysis, capital crisis triage, and investment decision support. Use when Arif asks about financial decisions, NPV, EMV, portfolio allocation, or economic evaluation of projects.

apple-reminders

Apple Reminders via remindctl: add, list, complete.

hermes-skills/agent-reply-forgery

# ⚒️ AGENT REPLY FORGERY — Modular Reply System for arifOS AAA > Ditempa bukan diberi — intelligence is forged, not given. **Skill:** `agent-reply-forgery` **Version:** 1.0 **Ratified:** 2026.05.03 **Sources:** mmx web research + arifOS constitutional framework (F1–F13) **Status:** LIVING DOCUMENT — extend via META mode proposals --- ## PURPOSE Every agent reply is a **forged artifact** — not just text, but a structured communication event with verifiable provenance, constitutional alignmen

macos-computer-use

Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.

skill-trigger-linter

Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.

auditor

A-R-I-F Auditor (Final) role. Trigger for review, verification, risk review, constitutional checks, regression checks, or release gating.

wrangler

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

claude-code

Delegate coding to Claude Code CLI (features, PRs).

skills/mmx

--- name: mmx description: Full multimodal generation via MiniMax CLI (mmx). Covers text chat, image generation, video synthesis, TTS speech, music composition, vision analysis, and web search. Activates when Arif wants to generate content or analyze images. Prerequisites: mmx auth login with API key. NOT for deep research loops (use mmx-text-researcher skill instead). metadata: {"openclaw": {"emoji": "🎨", "requires": {"bins": ["mmx"]}}} setup_needed: true --- # MMX — MiniMax Multimodal CLI #

skills/federation-health-scan

--- superseded_by: /root/arifOS/skills/health-probe/SKILL.md superseded_category: constitutional-duplicate superseded_date: 2026-06-22 superseded_authority: Hermes-ASI-for-Arif-F13-SOVEREIGN superseded_status: DRAFT-pending-Cycle-B-888-ratification --- # Federation Health Scan — OpenClaw Operational Skill **Skill ID:** `federation-health-scan` **Agent:** OpenClaw (AGI — Operational Gateway) **Priority:** P0 **Forged:** 2026-06-14 — arifOS P3 mesh wiring complete **DITEMPA BUKAN DIBERI*

arifos-governance

Enforce Floors F1-F13, 888 HOLD logic, irreversible-action gating, evidence alignment, and veto routing. Load when performing policy mutations, data deletions, deployment risk evaluations, or verifying system constraints.

audit-via-tests

Sub-skill to execute tests, capture failures, and deeply verify alignment with physics, math, and ontology.

claude-code

Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks

baoyu-infographic

Infographics: 21 layouts x 21 styles (信息图, 可视化).

arifos-memory

Master the 6-layer memory architecture of arifOS. Use this skill whenever you need to store, recall, or organize information across Ephemeral (L1), Session (L2), Semantic (L3), Structured (L4), Relational (L5), or Immutable (L6) layers. Mandatory for maintaining "Besi-level" factual consistency and adhering to Sovereign Memory Directives.

arif-memory-recall-debug

Diagnose arif_memory_recall returning _degraded DB connection failure via REST but working via direct Python call. Tests MemoryEngine singleton state across REST vs direct invocation paths.

arifos

arifOS Constitutional Governance — F1–F13 floors, SEAL/SABAR/VOID verdicts, VAULT999 ledger, session boot sequence. Load when task touches governance, constitutional floors, or tool adjudication.

arifos-llm-pipeline-audit

Audit LLM integration (SEA-LION, Ollama) across arifOS projects — detect hallucinations, map real pipeline, identify 3 critical holes. Triggered when investigating LLM configs or SEA-LION witness reports claim non-existent architecture.

arifos-mcp-federation

Route tasks across two or more federation MCP servers, sequence tool calls, and define fallbacks when an organ substrate fails. Load only when work spans multiple organs (GEOX, WEALTH, WELL, A-FORGE, AAA, external APIs).

replicate-models

replicate-prompting

forge

A-R-I-F Forge (Implementer) role. Trigger for active building, fixing, wiring, testing, scripting, or integration execution.

godel-humility-lock

Self-critique via Strange Loop — apply before declaring output complete, final, or SEAL-grade. Prevents the Gödel blindness of self-certification. Load for any verdicts, claims of completeness, "verified" assertions, or final-form reports. Not for trivial edits or one-line fixes.

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

skills/agent-reply-forge

# SKILL — Agent Reply Forge > **DITEMPA BUKAN DIBERI** — *Forged, not given* > **Version:** v1.0.0 > **Authority:** Muhammad Arif bin Fazil (Human Sovereign) > **Domain:** Agent communication, reply templating, A2A output formatting > **Created:** 2026-05-03 --- ## Purpose This skill defines how all arifOS agents forge their replies — text, file, image, video, audio, JSON/A2A payload. It provides the fixed constitutional skeleton and the 9-mode variable dial. Every substantive agent reply g

aaa-hermes-workspace-org

Organize and wire a Hermes Agent workspace into the AAA repo — identity files, MCP servers, skills, observability, backup cron, and gitignore hygiene. Activate when auditing or setting up Hermes Agent for Arif.

arifos-agent-output-templates

arifOS agent output formats, A2A protocol, verdict system, and forensic replay schema — for Hermes ASI and OpenClaw AGI

arif-sites-production-sync

Sync /999 credential artifacts from arif-sites source repo to live Nginx production web root — includes key consistency checks and manual deploy steps.

skills/workflow-automation

Automate construction data workflows. Build ETL pipelines and DAG workflows for recurring tasks.

arifos-fastmcp-app-tool-debug

Debug why FastMCPApp tools don't appear in tools/list — visibility=["app"] filter in FastMCP 3.2.0

caddy-cloudflare-routing-debug

Debug Cloudflare + Caddy routing gaps — HTTP 200 with HTML 404 body, broken well-known routes, JSON serving failures, and healthcheck port mismatches on arifOS VPS.

context7

Version-specific library docs via Context7 — eliminates SDK/library hallucinations

site-manager

Manage arif-sites (arif-fazil.com, apex.arif-fazil.com, arifos.arif-fazil.com) from Telegram. Use when user asks to update content, add pages, check site health, deploy changes, manage DNS/Caddy, or troubleshoot site issues. Works via browser tool, file_write/patch, and git.

web-development-page-agent

Embed alibaba/page-agent AI copilot into web applications. Use when you need to add natural language voice/copilot control to a web app (click "login", fill "username as John"), modernize legacy apps without rewriting frontend, or add accessibility via natural language. NOT for server-side browser automation — use Hermes built-in browser tool instead.

skills/arifOS-sense

--- name: arifOS-sense description: Constitutional governance layer for arifOS. Activates when: (1) a request involves irreversible, high-stakes, or externally consequential actions; (2) Arif invokes 888_HOLD human veto; (3) any action touches identity, values, or constitutional boundaries; (4) the agent must decide what may be claimed, held, or executed. arifOS-sense is the non-negotiable governance kernel — not decorative. Triggers on: "evaluate", "is this safe", "should I proceed", "arifOS",

skills/consequence-classifier

--- name: consequence-classifier description: Classifies every incoming request into consequence bands to drive arifOS-sense automatically. Activates when: (1) any user request arrives; (2) before taking any action; (3) when Arif asks to assess risk of something. Outputs a band + recommended verdict (SEAL/CAUTION/HOLD/VOID) and whether 888_HOLD is required. Makes governance-driven — not vibes-driven. metadata: {"openclaw": {"emoji": "⚖️"}} --- # Consequence Classifier — Risk Band for Every Acti

skills/csv-analyzer

Analyze CSV/TSV files with statistics, data profiling, and ASCII visualizations.

delta-logger

Logs every state change — file edits, exec results, config changes, API calls — into VAULT999 with before/after state and reversibility flag. Activates after every exec, write, edit, or delete operation. Makes rollback reasoning concrete and creates an auditable delta chain for the session.

github-pro

Advanced GitHub operations via `gh` CLI. CI/CD monitoring, API queries, and automated PR reviews.

arifos-respond

444_EVIDENCE — Evidence-based response generation with empathy encoding. Use when crafting outputs that affect humans or services, balancing truth with care.

markdown-formatter

Format and beautify markdown documents with configurable styles. Preserve structure, fix formatting, ensure consistency.

skills/mmx-quota-guard

--- name: mmx-quota-guard description: Budget-aware governance for MiniMax CLI. Activates when: (1) before any mmx command runs; (2) when Arif asks about quota, cost, or budget; (3) before any multi-step multimodal session (image batch, video, music). Prevents ASI-speed runaway billing by enforcing hard budget bands per session. Uses mmx quota and mmx config show. metadata: {"openclaw": {"emoji": "💰"}} --- # MMX Quota Guard — Budget Governance for MiniMax ASI-speed generation without budget a

deep-research

Comprehensive research framework that combines web search, content analysis, source verification, and iterative investigation to conduct in-depth research on any topic. Use when you need to perform thorough research with multiple sources, cross-validation, and structured findings.

skills/multimodal-hypothesis-lab

--- name: multimodal-hypothesis-lab description: Scientific reasoning loop that uses multiple MMX modalities to test a hypothesis. Activates when: (1) Arif proposes a geological model or interpretation; (2) a complex question needs visual + textual + data evidence; (3) Arif asks to "prove" or "test" an interpretation. Runs: hypothesis → request image/video evidence → mmx vision analysis → GEOX consistency check → CLAIM/PLAUSIBLE/HYPOTHESIS verdict. metadata: {"openclaw": {"emoji": "🔬"}} --- #

oracle

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

video-frames

Extract frames or short clips from videos using ffmpeg.

arifos-deploy

arifOS sovereign deployment: static hub, docs, runtime, and machine files. Use when deploying arifOS estate surfaces. Encodes deployment philosophy, estate roles, CI/CD policy, machine file invariants, and rollback doctrine. Triggers: deploy, build site, CI/CD, publish, machine files, llms.txt, static hub, Cloudflare, GitHub Pages, VPS runtime.

nano-pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI.

aaa-governance

arifOS AAA constitutional ritual. Full 000→999 governance chain with Gen3 tool names.

skills/secops-by-joes

--- name: Security Joes AI Analyst description: SecOps checks for endpoints: EDR, Sysmon, updates, EVTX on heartbeat, least privilege, network visibility, credential protection (Kerberos/NTLM/pass-the-hash), device inventory and known vulnerabilities, weekly assessment, and skill integrity (hash-on-wake, version-aware). Use when implementing or reviewing host posture, heartbeat logic, EDR/Sysmon/EVTX, privilege, network exposure, credential hardening, vuln assessment, weekly SecOps review, or

arifos-anchor

000_INTAKE — Ground reality, parse intent, start a constitutional session. Use at the start of any meaningful arifOS work session.

skills/self-verify

--- name: self-verify description: Self-verification skill for arifOS. Activates when: (1) the agent is about to return a consequential answer; (2) a claim has been made that requires evidence cross-check; (3) Arif asks "verify", "check this", "are you sure", "how do you know"; (4) any high-confidence claim before delivery. Prevents confident errors at ASI velocity. Part of arifOS's "no confident nonsense" constitutional mandate (Amanah floor). metadata: {"openclaw": {"emoji": "🪞"}} --- # Self

skills/skill-forensics

--- name: skill-forensics description: Auto-derives constitutional risk profile from any SKILL.md or tool before enabling or using it. Activates when: (1) a new skill is installed; (2) before any exec or tool call that is new or unfamiliar; (3) when Arif asks "what can this skill do, what are the risks". Reads the SKILL.md, extracts: capabilities, risks, irreversible operations, required floors, and generates an arifOS-ready risk brief. metadata: {"openclaw": {"emoji": "🔍"}} --- # Skill Forens

slack-personal

Read, send, search, and manage Slack messages and DMs via the slk CLI. Use when the user asks to check Slack, read channels or DMs, send Slack messages, search Slack, check unreads, manage drafts, view saved items, or interact with Slack workspace. Also use for heartbeat Slack checks. Triggers on "check slack", "any slack messages", "send on slack", "slack unreads", "search slack", "slack threads", "draft on slack", "read slack dms", "message on slack".

arifos-mcp-surface-debug

Debug MCP tool surface discrepancies — 13/20 tool count mismatches, verify_public HOLD, FastMCPApp visibility filtering, revert artifacts

skills/apex-quantum-analysis

# APEX Quantum Analysis — EMV/NPV + G-Level Governance > **APEX:** A × P × X × E² ≥ 0.80 > **EMV:** Expected Monetary Value = P(success) × Value - P(failure) × Cost - Drift > **NPV:** Net Present Value = -Cost + Σ(CF_t / (1+r)^t) > **Golden Rule:** If NPV < 0 → VOID (destroys value regardless of EMV) --- ## 🧬 APEX G-Level Intelligence ### The Formula ``` G = A × P × X × E² Where: A = AKAL (Clarity/Intelligence) [0, 1] — Mind P = PRESENT (Regulation) [0, 1] — Soul

github-repo-manager

Manage GitHub repositories for arifOS ecosystem. Use when users ask to check repo status, sync repos, manage issues, create releases, track dependencies across arifOS/GEOX/arifosmcp/arif-sites/waw/agent-workbench/arifOS-model-registry/APEX repos, or perform GitHub operations for ariffazil's projects.

arifos-reason

222_THINK — Structured reasoning with constitutional truth bounds. Use when a problem requires logical inference, hypothesis generation, or trade-off analysis.

constitutional-governance

Constitutional governance wrapper — enforces arifOS F1-F13 floors on all operations. Use when auditing actions against the constitutional kernel, explaining floor violations, or checking 888_HOLD requirements.

arifos-align

666_ALIGN — Ethical alignment and Anti-Hantu verification. Use to check a proposed solution for consciousness claims, dark patterns, and ethical drift before forging.

agentic-governance

Hardened constitutional governance — F1-F13 floor enforcement with Quad-Witness consensus for all actions

Recursive Skill Forge

Meta-cognitive smithy for forging new skills on demand. Use this skill whenever the federation encounters a novel domain, an unhandled workflow, or a capability gap that no existing skill covers. This skill performs abductive reasoning to infer what capabilities are needed, decomposes them into orthogonal modules, scaffolds a governed SKILL.md, attests it against constitutional floors, and presents the artifact for sovereign seal. It operates recursively: it can forge skills for other organs, and it can forge improved versions of itself. Plastic across domains. Modular by design. Attested before birth.

arifos-mcp-call

Invoke arifOS constitutional MCP tools (000-999 pipeline, F1-F13 enforced). Use to call arif_* tools on the arifos_remote MCP server.

vps-docker

Full VPS Docker status — all containers, resource usage, arifOS health. Use when Arif asks about container status, VPS health, what's running, memory/CPU usage, or wants to restart/rebuild services.

arifos-validate

555_EMPATHY — Stakeholder impact analysis. Use before any action that affects people, services, or shared systems to ensure the weakest stakeholder is protected.

entropy-measurement

Sub-skill to score system structure, duplication, dead code, and boundary bleed before and after mutations.

geox-basin-interpreter

Subsurface reasoning for basin screening, petroleum systems analysis, trap/seal/reservoir framing, and evidence-led interpretations. Load when geology, geophysics, or petrophysics tasks appear.

hermes-rsi

Hermes RSI worker under arifOS kernel governance. Review · Synthesize · Integrate. Use for every non-trivial request to lower entropy and emit compact, structured artifacts the kernel can judge.

constitutional-check

Run a constitutional floor check (F1-F13) against any action, plan, or code change. Returns a verdict with floor violation details and recommended action. Maps to arifos-constitutional-audit (Tier 1).

compact-smart

Intelligently compact context while preserving constitutional knowledge and active task state

geox-interpret

GEOX Earth Plane — Subsurface intelligence, petrophysics, well log interpretation, formation evaluation, and prospect evaluation. Use when Arif asks about well logs, LAS files, Vshale, porosity, permeability, GCoS, or geological risk assessment.

arifos-forge

777_FORGE — Solution generation with Genius evaluation and Apex judgment. Use to generate and evaluate solution approaches before irreversible implementation.

arifos-audit

888_JUDGE — Full F1-F13 constitutional compliance scan with Tri-Witness consensus. Use before finalizing any significant action or before sealing to the vault.

skills/mmx-text-researcher

--- name: mmx-text-researcher description: Deep research skill using MiniMax CLI (mmx). Activates when: (1) Arif asks to research, investigate, look up, find information, or deep-dive on a topic; (2) a question requires synthesis from multiple sources; (3) Arif needs structured output (JSON, tables, summaries); (4) any knowledge task that benefits from web search + synthesis. Uses mmx search + mmx text chat. NOT for simple factual lookups (use web_search tool directly). metadata: {"openclaw": {"

skills/mmx-job-orchestrator

--- name: mmx-job-orchestrator description: Supervisor for all async MMX jobs (video, music, batch image). Handles: submit → poll → retry → download → clean. Activates when Arif asks to generate video, music, or batch images. Uses mmx exit codes, stderr for progress, and implements agentic retry semantics — not human retry. metadata: {"openclaw": {"emoji": "🎬"}} --- # MMX Job Orchestrator — Async Supervisor for MMX Async MMX jobs (video, music, batch image) are fire-and-forget for humans. For

skills/geox-ground

--- name: geox-ground description: Earth-domain reasoning grounding for arifOS. Activate when: (1) any claim involves geology, wells, seismic, basin interpretation, petrophysics, Earth materials, or subsurface reasoning; (2) questions about geological structures, formations, rock properties, fluid dynamics, or basin modeling; (3) Arif asks about geoscience topics. GEOX is the Large Earth Model layer — it forces physics-over-narrative, real-data-over-elegant-fiction, and explicit OBS/DER/INT/SPEC

skills/geo-vision-translator

--- name: geo-vision-translator description: Wraps MMX vision for geoscience content — wireline logs, core photos, seismic slices, hand samples, maps, well schematics. Activates when Arif sends or asks about geological images. Forces GEOX epistemic labels on pixel-derived content: OBS from pixels (direct measurement) vs INT from interpretation. Prevents confident over-claim on visual data. metadata: {"openclaw": {"emoji": "🪨"}} --- # GEOX Vision Translator — Pixel Evidence with Epistemic Disci

arifos-integrate

333_ATLAS — Cross-domain synthesis and context mapping. Use when you need to map knowledge boundaries, extract vocabulary, or establish ontological scope before deep work.

skills/maxhermes-hermes

# MaxHermes Hermes Skill — Tool Orchestration & Session Management # "Grounded geophysics. Governed action. No fiction." skill_id: maxhermes-hermes name: MaxHermes Hermes version: 0.1.0 owner: AAA domain_plane: GEOX risk_tier: medium description: > Core orchestration skill for MaxHermes geophysics agent. Manages GEOX tool calls, session context, memory, and workflow coordination. The "conductor" skill — routes tasks to the right tools with correct epistemic labeling. knowledge_basis: