Code review with Claude Code: commands, rules and a standing reviewer

What Claude Code does for code review

• Reviews each pull request for bugs, missing tests and risky changes, and comments inline on GitHub.
• Follows your written review rules, so comments stay off what the linter already checks.
• Reviews its own changes, and other agents', before they reach a person.
• Tracks follow-ups: a comment that needs work becomes an issue instead of getting lost.

Claude Code features for code review

How to set up Claude Code for code review

1. Connect the tools

   /code-review needs nothing extra for your own branch. To review a pull request by number and post comments with --comment, work in a checkout of the repository with the GitHub CLI signed in.

   # Sign in to GitHub once
   gh auth login
   
   # Review pull request 142 at high effort and post inline comments
   /code-review high 142 --comment

2. Write the rules in CLAUDE.md

   Claude Code reads CLAUDE.md at the start of every session, claude -p runs included. Put the job's rules there, or in a skill under .claude/skills/ if they're long. See the CLAUDE.md guide.

   ## Code Review Rules
   - Flag missing tests for new branches in billing/ and auth/.
   - Any SQL migration needs a rollback; say so if it doesn't have one.
   - Don't comment on formatting; the linter handles it.
   - Comment only: never approve, request changes or merge.

3. Run it without the interactive interface

   claude -p runs one task and exits, so cron, CI or another tool can start it. Choose what it may do without asking with --allowedTools or --permission-mode; --output-format json returns the result with its cost.

   # Review a pull request from CI or cron; /code-review follows CLAUDE.md in -p runs
   claude -p "/code-review 142 --comment"

4. Put it on a schedule

   Make it a cloud scheduled task with /schedule (Pro, Max, Ultra, Team and Enterprise), a desktop scheduled task, or /loop while a session stays open. See how to make Claude Code proactive.

Source: Claude Code documentation

Limits and safety

• It comments; it doesn't own the change. Keep approvals and merges with people.
• Reviews use your plan's usage. Review on request or when a pull request is ready, not on every push.
• It reviews the diff and the repository. It can't test against production data.
• Since Claude Code v2.1.302, claude -p starts in Manual mode: an action that needs approval is denied unless a rule allows it. Allow only the tools the job needs.

Claude Code or Codex for code review?

The rules carry over. Write them once in AGENTS.md and put @AGENTS.md in CLAUDE.md, and both agents read the same file.

Step by step for the other agent: code review with Codex.

Make code review someone's job

Commands run when someone remembers to run them. Crewmark turns your own Claude Code into an AI employee with a role, a goal in numbers, working hours and a heartbeat, so the work happens on schedule and shows up on a board.

1. Start from the role

   The AI software engineer, with these rules in its brief.

2. Put the work on its board

   Add the job as a recurring issue. The employee wakes on its heartbeat, does it and reports in a comment.

3. Related

   AI code review on every PR compares every option, and security review covers vulnerabilities.

FAQ