ariffazil/self-audit
forge_work/self-audit/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace self-auditInstall 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: Jul 10, 2026, 4:02 AM135.3s1 file scanned
SKILL.md
- name:
- self-audit
- description:
- 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.
- version:
- 0.1.0
- created:
- 2026-06-06
- author:
- OPENCLAW
- doctrine:
- DITEMPA BUKAN DIBERI
Self-Audit Skill
Mission: Produce a structured, citable, constitutionally-aware audit document. Output: Markdown file in
forge_work/, with: executive verdict, deep-research section, current state, gap table, improvement plan, floor compliance check, sealing.
When to Use
- User asks to "audit," "review," or "show me the state of"
- A new organ is added to the federation
- A version drift is detected (build ≠ live, version behind)
- Weekly/monthly self-audit cron fires
- After a major change (skill add, config patch, container rebuild)
The Audit Skeleton
# <SUBJECT> Audit — <DATE>
> Date: ISO timestamp
> Sealed by: OPENCLAW (or whoever)
> Sovereign directive: <quote if any>
## 0. Executive Verdict
| Axis | State | Note |
|------|-------|------|
| one row per axis | 🟢/🟡/🔴 | one line |
## 1. What <SUBJECT> Is (Plain)
2-3 paragraphs, no jargon
## 2. Deep Research (Upstream)
Latest version, what's new, what's drift
## 3. Current State
3.1 Version, 3.2 Model, 3.3 Skills, 3.4 Memory,
3.5 Channels, 3.6 Crons, 3.7 Constitutional posture
## 4. Real Gaps
Table of question → answer
## 5. Recursive Improvement Plan
5.1 Immediate, 5.2 Next 24h, 5.3 Next 7d, 5.4 30d
## 6. Constitutional Audit (Self-Applied)
Table: Floor | Triggered? | Note
For F1-F13
## 7. Sealing
Path, timestamp, hash, verdict, reviewer, sovereign waiver
Required Sources
Every audit MUST cite at least:
- Live health endpoint (curl + status code)
- Latest version from official source (web_fetch with URL)
- Workspace state (ls, cat)
- Constitutional floors (FLOORS.md or 000_CONSTITUTION.md)
Falsifiability Rules
A self-audit is INVALID if any of these are missing:
- No live verification of state (only "I think it's...")
- No source URL for "latest version"
- No execution path mentioned (file path, command, or output)
- No floor compliance table
- No seal/verdict
Anti-Patterns
- ❌ Auditing without touching the system
- ❌ Repeating last audit's structure without re-verifying
- ❌ Skipping the floor table because "obviously passes"
- ❌ "I think the version is..." instead of
cat package.json | head -1 - ❌ Auditing the audit (meta-loop without progress)
Cron Hooks
- Weekly: Sunday 03:00 KL (after morning briefing, before Asia open)
- Monthly: 1st of month, full deep-research pass
- On-demand: via
agentic-loopskill
Output Path
/root/.openclaw/workspace/forge_work/<SUBJECT>-AUDIT-<DATE>.md
Seal Format
TASK: <audit subject>
STATUS: SEAL | SEAL-with-CAVEATS | HOLD | VOID
EVIDENCE: <path to audit doc>
FLOORS: F01 F02 F04 F07 (those triggered)
NEXT: <next action>
Forged 2026-06-06 under sovereign directive. DITEMPA BUKAN DIBERI.
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