CL
Claude Code reads a single module, writes characterization tests, then changes structure only where those tests pass.
Claude Code · Unverified · code.claude.com · 15 Oct 2026
Loading the catalog…
Claude Code handles this as a draft: After an admin turns on Code Review for a repository, a new pull request gets an automatic review. A person still merges. The product is for Team and Enterprise plans.
The announcement says Team and Enterprise admins turn it on in Claude Code settings, install the GitHub App, and choose repositories. Pick Quick, Standard, or Deep per repository. Standard is the default.
The announcement says reviews then run on new pull requests without a developer setting. Check each finding against the diff.
You merge. The review does not replace that decision.
These are editorial labels so you can compare playbooks. They are not measurements.
No. Status is unverified. The announcement was checked on 17 Oct 2026. The prompt is an adaptation.
Merging. An admin also chooses which repositories are reviewed and how deep the pass is.
Anthropic announcement, dated 15 Oct 2026 on the page. It returned HTTP 200 on 17 Oct 2026. Code Review left research preview for Team and Enterprise. Admins enable it, install the GitHub App, and pick Quick, Standard, or Deep. Reviews then run on new pull requests. Prompt and stop rules are an AI Playbook Gems adaptation, not a vendor quote; unverified.
Machine-readable copy: JSON
Claude Code reads a single module, writes characterization tests, then changes structure only where those tests pass.
Claude Code · Unverified · code.claude.com · 15 Oct 2026
Claude Code handles this as a draft: Which commands are missing a script entry. Do not rewrite the README until I agree.
Claude Code · Unverified · code.claude.com · 14 Oct 2026
Claude Code handles this as a draft: Which ones are not on the allow list I wrote. Do not add packages.
Claude Code · Unverified · code.claude.com · 12 Sep 2026