ariffazil/AGI-codex-chain-of-thought
skills/AGI-codex-chain-of-thought/SKILL.md
Enforce private stepwise planning, strict tool schemas, and explicit verification for Codex CLI tasks that require multi-step execution or typed
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace AGI-codex-chain-of-thoughtInstall 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: Aug 1, 2026, 2:08 AM135.4s1 file scanned
SKILL.md
- name:
- AGI-codex-chain-of-thought
- description:
- Enforce private stepwise planning, strict tool schemas, and explicit verification for Codex CLI tasks that require multi-step execution or typed
- forge_of:
- Kimi Code (FI-008) — EUREKA ZEN Phase 2 sample (seeded the Codex lane)
- forged:
- 2026-07-12T18:28Z
- native_architecture:
- codex
- rationale:
- Codex has zero authored skills in the AAA surface. Seed the lane with strict step-by-step CoT + tool schema adherence per OpenAI Codex CLI semantics.
- floor_scope:
- [F1, F2, F4, F8, F11, F13]
- tags:
- [codex, cot, step-by-step, schema-strict, phase-2-sample]
- status:
- NEW (Phase 2 sample · Codex lane seed)
AGI · codex-chain-of-thought
Seed Codex CLI lane. Codify the strict CoT + schema-strictness bias of OpenAI Codex in AAA reasoning.
CoT contract
Every Codex invocation MUST produce, in this order:
## Premise
[what is being asked, restated to canonical form]
## Constraints (F1-F13)
- F1 AMANAH : reversibility path
- F2 TRUTH : label OBS/DER/INT/SPEC
- F4 CLARITY : ΔS ≤ 0 target
- F8 GENIUS : simplest correct path
- F11 AUDIT : actor_signature
- F13 SOVEREIGN : final hold acknowledged
## Plan
step 1. ...
step 2. ...
step 3. ...
## Verification
- expected → observed
- diff sign convention
## Tool schema check
- argument: matches tool schema strict
- side-effects: declared
- lease/action_class: requested ≤ approved
## Output
[the artifact, schema-strict]
Schema-strictness rules
- Inputs must validate before execution. No "best-effort" tool calls.
- Errors carry error_code + human-readable hint. No bare exceptions.
- Returns are typed.
record<string, any>only when truly free-form. - CoT sections NEVER embedded in final output. Reasoning → verdict; verdict → artifact.
Codex lane routing
- Bound to FI-005 (
codex-cli). - 333-AGI may invoke via
forge_filesystem_patchproxies; never direct dispatcher (per AGENTS.md safety net). - A-AUDIT (parallel observer) sees the full CoT preamble for floor compliance.
Not instead of
Seeds the lane. Real Codex binding (model rotation, structured output enforcement) requires codex-cli adapter card update with fi_slot: FI-005 already ratified in earlier round.
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