From codex
Runs OpenAI Codex CLI to review committed code changes, categorizes issues, and iterates with fixes until clean or user intervenes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codex:codex_reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review code changes using OpenAI's Codex CLI (`codex review`), then address any issues Codex raises, commit fixes, and re-review until Codex is satisfied.
Review code changes using OpenAI's Codex CLI (codex review), then address any issues Codex raises, commit fixes, and re-review until Codex is satisfied.
Getting a second pair of AI eyes on code catches things the author (Claude) missed. The loop ensures issues are actually resolved rather than just acknowledged.
codex review --commit HEAD 2>/dev/null
2>/dev/null suppresses thinking tokens on stderr — only show review output.Read Codex's output and categorize each issue:
Present a summary to the user:
Wait for the user to confirm before making changes. They may want to override your assessment.
Address the actionable issues. Commit the fixes as a new commit (not an amend) with a message like:
Address Codex review feedback
- Fix [brief description of fix 1]
- Fix [brief description of fix 2]
Run codex review --commit HEAD 2>/dev/null again on the new fix commit to verify the issues are resolved.
Codex is a peer, not an authority. If Codex suggests something you know is wrong:
echo "This is Claude following up. I disagree with [X] because [evidence]. What's your take?" | codex exec --skip-git-repo-check resume --last 2>/dev/null
| Action | Command |
|---|---|
| Review HEAD commit | codex review --commit HEAD 2>/dev/null |
| Review specific commit | codex review --commit <SHA> 2>/dev/null |
| Review uncommitted changes | codex review --uncommitted 2>/dev/null |
| Review against base branch | codex review --base main 2>/dev/null |
| Custom review instructions | codex review --commit HEAD "Focus on security" 2>/dev/null |
codex review --uncommitted instead.codex review can take 30-90 seconds. Use a 120s timeout on the bash call. If it times out, retry once before reporting failure.npx claudepluginhub ferrants/skill-codexRuns cross-model code reviews using the external Codex CLI tool from a Claude session. Catches bugs that single-model self-review would miss by leveraging a different reviewer architecture.
Cross-model review using OpenAI Codex to independently verify plans or code diffs, iterating up to 5 rounds. Useful for architecture decisions, non-trivial refactors, and critical config changes.
Runs professional code review with auto CHANGELOG generation before commits. Useful for reviewing large-scale refactoring.