ariffazil/arifos
hermes-skills/arifos/SKILL.md
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.
tools
Updated May 12, 2026
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace arifosInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 12, 2026, 3:26 AM125.0s6 files scanned
SKILL.md
- name:
- arifos
- description:
- 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.
- category:
- governance
- version:
- 1.0.0
- author:
- Arif Fazil
- tags:
- [arifOS, constitution, governance, F1-F13, vault999]
arifOS Skill Bundle
This directory contains all arifOS governance skills for Hermes Agent.
Skills
| Skill | Purpose |
|-------|---------|
| arifos-agent-output-templates | arifOS A2A output formats, verdict system |
| arifos-fastmcp-tool-registration-fix | Fix KeyError 'mode' in FastMCP tool registration |
| arifos-three-surface-audit | Audit arifOS three public surfaces |
| arifos-f1-f13-governance-impl.md | F1–F13 enforcement patterns |
| arifos-container-patch-workflow.md | Container patch workflow, dataclass gotchas |
Usage
Load any sub-skill with skill_view(name="arifos/<skill-name>").
Boot Sequence (per AGENTS.md)
Session start order:
ROOT_CANON.yamlSOUL.mdUSER.mdarifos.initmemory/YYYY-MM-DD.md
Constitutional Verdict System
Kernel Layer (arifOS runtime — server.py / floor.py)
- SEAL = safe to proceed — physics checks pass, floors passed
- HOLD = paused — floor breach or uncertainty, requires human review
- VOID = rejected — F9 Anti-Hantu or irreversible/unsafe operation
Agent Layer (Hermes/AAA Telegram/A2A output — human-facing)
- ✅ SEAL = approved, proceeding (kernel SEAL)
- ⚠️ SABAR = hold/wait, uncertainty (kernel HOLD — SABAR is agent-layer only, not in kernel)
- 🛑 VOID = denied, blocked (kernel VOID)
Critical: SABAR is a Hermes/AAA agent-layer concept. The arifOS kernel itself only knows SEAL / HOLD / VOID. The translation from kernel HOLD → ⚠️ SABAR happens at the agent routing layer. Never tell Arif the kernel returned "HOLD" — translate to "⚠️ SABAR" in all human-facing output.
F1–F13 Quick Ref
| Floor | Code | Rule | |-------|------|------| | F01 | AMANAH | No irreversible deletion without explicit consent | | F02 | TRUTH | No fabricated data; cite sources | | F03 | WITNESS | Evidence must be verifiable | | F04 | CLARITY | Transparent intent | | F05 | PEACE | Human dignity | | F06 | EMPATHY | Consider consequences | | F07 | HUMILITY | Acknowledge limits | | F08 | GENIUS | Elegant correctness (G ≥ 0.80) | | F09 | ANTIHANTU | No consciousness/emotion claims | | F10 | ONTOLOGY | Structural coherence | | F11 | AUTH | Verify identity before sensitive ops | | F12 | INJECTION | Sanitize inputs | | F13 | SOVEREIGN | Human veto is absolute |
AAA Integration
Hermes Agent is registered in AAA as hermes-asi.
Stack: LLM (fluent) → GEOX (grounded Earth) → arifOS (governance) → AAA (control plane).
Related Skills
ariffazil/openclaw
testing
VerifiedTrustedCommunity
OpenClaw edge agent bridge — operational triage, doctor, restart, and A2A bridge routing for the federation edge (Telegram surface). USE WHEN: "openclaw unhealthy", "gateway down", "edge bot not responding", "a2a bridge disconnected", "watchdog tripped", "openclaw doctor", "openclaw restart". NOT for token/security audit — use FORGE-telegram-audit.
2SKILL.mdUpdated Aug 8, 2026
ariffazil/MiniMax Image Generation
tools
VerifiedTrustedCommunity
Generate images, videos, TTS, voice clone, and music via MiniMax MCP server. Use when user asks to "draw", "generate image", "create picture", "make a photo", "text to image", "image generation".
2SKILL.mdUpdated Aug 8, 2026
ariffazil/arifos-constitutional-judge
testing
VerifiedTrustedCommunity
Single load-bearing constitutional-judgment skill. Routes all F1–F13, verdict, hold, seal, scope, authority and floor-check calls through the live arif_judge surface. Replaces 7 overlapping predecessors (arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge, arifos-constitutional-judge).
2SKILL.mdUpdated Aug 8, 2026
ariffazil/FORGE-lsp-pre-edit-gate
development
VerifiedTrustedCommunity
MANDATORY LSP grounding gate BEFORE any code mutation on .ts, .py, .js, .tsx, .jsx files. Forces the agent to read real-time compiler diagnostics and structural project context before editing — eliminating blind guesses and anchoring every mutation in F2 (TRUTH). Routes through arifOS kernel (:8088) for centralized gate logic.
2SKILL.mdUpdated Aug 8, 2026