Set Up Claude Code Review to Automatically Review Pull Requests

Asking Claude to review code in the terminal is useful, but Claude Code Review is something different entirely. It's a GitHub App that automatically dispatches multiple agents on every pull request, running in parallel and cross-verifying findings before posting results as inline PR comments.

Here's how to set it up as an admin:

1. Go to claude.ai/admin-settings/claude-code in your organisation's Claude admin panel
2. Click Connect GitHub and install the Claude GitHub App
3. Select which repositories should get automatic reviews

Once enabled, every new PR triggers a review automatically. Developers don't need to change their workflow. If you want manual-only mode, switch to that in settings — reviews only run when someone comments @claude review on a PR.

The review pipeline works in three passes: agents scan for bugs in parallel, verify findings to cut false positives, then rank issues by severity. Results appear as a summary comment plus inline annotations on specific lines.

# Manual trigger in a PR comment:
@claude review

A few things to know upfront:

• Cost runs $15–25 per PR, scaled to PR size and complexity
• You can cap monthly spend under Settings → Usage Controls
• Currently in research preview for Team and Enterprise plans

This is a fundamentally different tool from piping a diff to Claude in the terminal — it's async, multi-agent, and designed to review code you didn't write.

Pair it with your existing CI pipeline and let the agents catch what human reviewers skim past.