codex-eval
Skill1 starsChanged 17 days agoNo licenceView on GitHub
Use when running, interpreting, or reasoning about a Codex external eval — the independent second-model evaluation layer. Covers run-external-skill-eval.js, run-external-agent-eval.js, run-native-audit.js, their dry-run/--live modes, the native audit mode, the Claude-Code-vs-Codex disagreement matrix, and the ownership boundary. Trigger on "codex eval", "external eval", "second-model eval", "native audit", "CODEX-EVAL-SUMMARY", or before adding --live to anything.
In this repository31 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-adaptSkill
- agent-auditSkill
- agent-evalSkill
- agent-refineSkill
- agent-scoutSkill
- brain-captureSkill
- brain-compileSkill
- brain-context-packSkill
- brain-kernelSkill
- brain-promoteSkill
- brain-searchSkill
- brain-weekly-reviewSkill
- capture-learningSkill
- gstack-pattern-auditSkill
- project-auditSkill
- project-brain-bootstrapSkill
- project-ideaSkill
- project-setupSkill
- reference-repo-addSkill
- reference-repo-auditSkill
- reference-repo-pattern-extractSkill
- repo-auditSkill
- second-brain-setupSkill
- skill-adaptSkill
- skill-auditSkill
- skill-discoverySkill
- skill-evalSkill
- skill-refineSkill
- skill-scoutSkill
- team-evalSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.