peer-reviewlisted

# Peer Review > 📦 This skill is also part of a larger collection: **[claude-code-skills](https://github.com/jkm-4314/claude-code-skills)** — project bootstrap, persistent session memory, and peer review. Clone the repo if you want all of them. Orchestrate iterative review of specs or code by Codex (GPT-5.5) until both Claude and Codex agree the work is production-ready. ## Installation 1. **Prerequisites:** - [Claude Code](https://docs.claude.com/claude-code) installed and configured - [Codex CLI](https://github.com/openai/codex) v0.125.0 or later in PATH, authenticated against an OpenAI account that can call `gpt-5.5` - Run `codex --version` to verify 2. **Install the skill:** - Save this `SKILL.md` to `~/.claude/skills/peer-review/SKILL.md` (Linux/macOS) or `%USERPROFILE%\.claude\skills\peer-review\SKILL.md` (Windows) - Restart Claude Code, or start a new session, so the skill is discovered 3. **Optional — slash command:** - Invoke explicitly with `/peer-review spec` or `/peer-review code` - Otherwise the skill triggers automatically after spec writing or code completion (unless the user opts out) 4. **Verify:** Ask Claude "run the peer-review skill on this spec" and confirm Codex is invoked. ## Modes - **spec** — Review a specification document - **code** — Review code changes (git diff) Determine mode from context or from the argument passed (e.g., `/peer-review spec`). ## Bypass Do NOT run this skill ONLY if: - User explicitly said one o