commit
01Skill Claude CodeCodex
Smart commit — run tests, update docs and memory, then commit to ensure knowledge is not lost.
not rated 0 2d ago A 21 tokens
original MIT
0Stars on the repository
15Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
coplan
02Skill Claude CodeCodex
Write the plan under discussion to docs/current-plan.md so an external reviewer can check it against the real code. User-invoked; stacks after /think.
not rated 0
changed today A 35 tokens
original MIT
evaluate
03Skill Claude CodeCodex
Objectively evaluate external review/advice against your actual codebase knowledge. Use when pasting suggestions from reviewers, consultants, or AI who lack project context.
not rated 0 2d ago A 33 tokens
original MIT
investigate
04Skill Claude CodeCodex
Multi-agent cross-investigation. Two modes — research (explore from scratch) and review (challenge existing proposal). Spawns parallel agents per dimension, synthesizes with dialectical cross-check.
not rated 0 2d ago A 41 tokens
original MIT
self-check
05Skill Claude CodeCodex
Periodic self-check — reflect on alignment, progress, and quality. Use with /loop for continuous monitoring.
not rated 0 2d ago B 24 tokens
original MIT
summary
06Skill Claude CodeCodex
Summarize current session context for high-quality /compact. Run before compacting to preserve what matters.
not rated 0 2d ago A 23 tokens
original MIT
think
07Skill Claude CodeCodex
Stop and think before coding. Read context, ask questions, propose approaches, self-review, wait for user choice. Use when starting any non-trivial task.
not rated 0 2d ago A 34 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: