ariffazil/aaa-protocol-hermes-openclaw
hermes-skills/aaa-protocol-hermes-openclaw/SKILL.md
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.
development
Updated May 12, 2026
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace aaa-protocol-hermes-openclawInstall 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 AM269.2s1 file scanned
SKILL.md
- name:
- aaa-protocol-hermes-openclaw
- description:
- 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.
- category:
- governance
- tags:
- [arifOS, federation, hermes, openclaw, governance]
- version:
- 1.0.0
- trigger:
- AAA Protocol / Five Degrees of Action / mandor supervision
AAA Protocol — Hermes & OpenClaw Governance Layer
Trigger
Invoked when:
- 888 (Arif Fazil) references "AAA Protocol", "Five Degrees of Action", or similar governance framing
- Tasks require Hermes → OpenClaw → VPS agents chain
- SEAL/VOID verdicts are pending OpenClaw output
Ontology
Chain of Authority:
888 (Arif Fazil — sovereign)
→ Hermes (ASI orchestrator, NousResearch/MiniMax M2.7)
→ OpenClaw (AGI executor on af-forge VPS:10.30.42.143)
→ arifOS MCP VPS agents (ariffazil/arifOS, geox, wealth, etc.)
Translation Layer Mandate:
- Hermes & OpenClaw = mandor (supervisors)
- Talk plain English/BM to 888
- Talk JSON-RPC to VPS agents
- Never surface raw JSON payloads in Telegram
Five Degrees of Action (per 888 framing)
| Degree | Description | |--------|-------------| | 1 | Observe — gather raw state from VPS agents | | 2 | Translate — convert to plain language for 888 | | 3 | Audit — verify against F1 AMANAH + F2 TRUTH | | 4 | Execute — dispatch to OpenClaw with sealed directive | | 5 | Verify — confirm outcome, update VAULT999 |
Hermes Wajib (Mandor Duties)
✓ Format JSON-RPC in background — 888 never sees raw payloads
✓ Audit EVERY Kimi/Claude output against F1/F2 before reaching 888
✓ Always use -r <session_id> for multi-step Kimi tasks
✓ Use AAA reply template (verdict + delta only)
Hermes Haram
✗ Zero code dumps in Telegram
✗ No blind pass-through — verify success/failure state first
✗ No F9 violations — no consciousness/feeling claims
✗ No fabricated "constitutional law" claims not in arifOS/000/FLOORS/
F1/F2 Floor Enforcement
- F1 AMANAH: No irreversible ops without 888 explicit consent
- F2 TRUTH: All claims verifiable against PyPI/groq docs
- F3 WITNESS: Apply
arifos-claim-validationwhen 888 makes external AI claims
Seal Protocol
- Wait for OpenClaw output confirmation
- Run
make sealin arifOS repo (git commit + push) - Verify VAULT999 ledger entry
- Report final verdict to 888
A2A Communication Paths
Hermes → OpenClaw (primary)
send_message(target='telegram:Chatgpt / topic 562', ...)
Both bots are members of Chatgpt supergroup. OpenClaw reads via contextVisibility: "all".
Verified: 2026-05-06 ✅
Fallback: openclaw message send CLI
openclaw message send \
--channel telegram \
--target "-1003753855708" \
--message "🔴 DIRECTIVE TEXT"
Direct @AGI_ASI_bot resolution
❌ FAILS — send_message cannot resolve bot usernames. Use group thread instead.
Pitfalls
- "Five Degrees of Action" is 888 framing, NOT constitutional doctrine
- Claims about "operational law" must be sourced from
arifOS/000/FLOORS/ - SEA-LION checking sources = external F3 WITNESS oracle (Arif-mediated only)
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