jamesclaw0/codex-loop
/SKILL.md
# Codex-Loop: The Ultimate AI Quality Gate ## 🛡️ Core Definition **Codex-Loop** is a "Ping-Pong" enforcement tool designed for AI coding agents. It ensures that no agent can finish a task until their code passes a rigorous, cross-model review. - **Capabilities**: - Automatically filters for code changes (Python, JS, TS, etc.). - Isolates staged changes from dirty workspaces using Git Stash. - Truncates and retries reviews until 🟢 `[SUCCESS]`. - **3-Strike Mechanism**: If an
tools
Updated Apr 6, 2026
$ install --global
skillsauthnpx skillsauth add jamesclaw0/codex-loop codex-loopInstall 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: Apr 6, 2026, 2:16 AM6.8s26 files scanned
SKILL.md
Codex-Loop: The Ultimate AI Quality Gate
🛡️ Core Definition
Codex-Loop is a "Ping-Pong" enforcement tool designed for AI coding agents. It ensures that no agent can finish a task until their code passes a rigorous, cross-model review.
- Capabilities:
- Automatically filters for code changes (Python, JS, TS, etc.).
- Isolates staged changes from dirty workspaces using Git Stash.
- Truncates and retries reviews until 🟢
[SUCCESS]. - 3-Strike Mechanism: If an agent fails 3 times, it triggers a "Final Instruction Mode" to force-output the correct solution, preventing endless "advice" loops.
- Repetition Guard: Detects if the AI is giving the same suggestions and breaks the loop.
- Trigger: Run
codex-loopbefore any code commit or task completion.
📂 Structure
scripts/codex-loop.sh: The main bash controller.scripts/quality_stamper.py: Injects "Codex-Verified" stamps into passed files.
⚙️ Installation
- Copy
scripts/to your local bin. - Ensure
codexCLI is installed and configured. - Run
codex-loopto start the cycle.
🤖 Multi-Agent Dispatcher Protocol
When orchestrating parallel tasks (e.g. via *parallel-fix), you must act as the Orchestrator and route subtasks based on complexity:
-
Routing Logic:
- Codex Agent (High Complexity): Algorithms, core architecture refactoring, complex state migrations.
- Gemini Agent (Medium/Low Complexity): UI/CSS adjustments, basic CRUD, documentation, config files, lightweight scripts.
-
Headless Execution Commands:
- Dispatch to Codex:
nohup codex exec --full-auto -m <model> -C <Worktree_Path> "Please read .fix_log and fix this project accordingly." >/dev/null 2>&1 & - Dispatch to Gemini:
nohup gemini --workspace <Worktree_Path> -y "Please read .fix_log and fix this project accordingly, exit immediately when done." >/dev/null 2>&1 &(Both agents must be run in the background allowing true parallelism.)
- Dispatch to Codex:
%% Built for the Muse-Core level 15 ecosystem %%
Related Skills
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026
steipete/xurl
tools
VerifiedTrustedCommunity
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
356,423SKILL.mdUpdated Apr 13, 2026