
Code Review
Run a final, exhaustive pull-request review by fanning out every code-review-* skill in the repo via subagents before merge or release.
Install
npx skills add https://github.com/openai/codex --skill code-reviewWhat is this skill?
- Orchestrator invokes one subagent per code-review-* skill (excluding itself) with full skill path
- Requires xhigh reasoning and mandates returning every issue from every subagent with no cap on findings
- Findings use raw Markdown, numbering, and mandatory file path plus line number per item
- Optional GitHub `code-reviewed` label when the review user owns the PR
- Does not post GitHub comments unless explicitly requested
Adoption & trust: 1 installs on skills.sh; 89.7k GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
Recommended Skills
Journey fit
Canonical shelf is Ship because the skill is explicitly a final PR code review orchestrator with optional GitHub labeling—not ideation or growth analytics. Review subphase fits the orchestrated multi-skill audit that returns numbered findings with paths and line numbers on a pull request.
Common Questions / FAQ
Is Code Review safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Code Review
Use subagents to review code using all code-review-* skills in this repository other than this orchestrator. One subagent per skill. Pass full skill path to subagents. Use xhigh reasoning. You must return every single issue from every subagent. You can return an unlimited number of findings. Use raw Markdown to report findings. Number findings for ease of reference. Each finding must include a specific file path and line number. If the GitHub user running the review is the owner of the pull request add a `code-reviewed` label. Do not leave GitHub comments unless explicitly asked.