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/AAA Agentic Governance (AAA-Cockpit, canonical)
development
VerifiedTrustedCommunity
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.
SKILL.mdUpdated Jun 6, 2026
ariffazil/skill-trigger-linter
development
VerifiedTrustedCommunity
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.mdUpdated May 27, 2026
ariffazil/skill-creator
development
VerifiedTrustedCommunity
Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.
SKILL.mdUpdated May 27, 2026
ariffazil/Federation Service Health Triage
content-media
VerifiedTrustedCommunity
Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.
SKILL.mdUpdated May 27, 2026