Skill Claude CodeCodex
Selected during the capability phase — adds new tools, exposes new parameters, fixes tool implementations, or removes infrastructure limitations to expand what the agent can do.
150 7d ago A 34 tokens
original MIT
150Stars on the repository
8Mods indexed here, across every type
7d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
diagnose
02Skill Claude CodeCodex
Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns.
150 7d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Use to systematically analyze the full evolution history without output truncation — produces a structured summary of what matters for the current iteration.
150 7d ago A 27 tokens
original MIT
Skill Claude CodeCodex
Use after applying any patch to thoroughly verify the agent codebase has no bugs — checks syntax, imports, runtime behavior, docstrings, templates, hooks, and logical correctness.
150 7d ago A 38 tokens
original MIT
Skill Claude CodeCodex
Selected during the steering phase — refines agent behavior by modifying prompts, tool descriptions, or hook reminders without changing executable code.
150 7d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use before proposing a mutation to diagnose measured failures from evaluator outcomes, traces, history, and the controlling candidate surfaces.
150 7d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use after applying a candidate change to verify its diff, scope, syntax, integration behavior, and consistency before returning it.
150 7d ago A 28 tokens
original MIT