Claude Code
Claude Code review: how it works and who can use it
A plain guide for engineering leads. Every fact about the product is taken from Anthropic documentation read on 8 November 2026.
Claude Code review is Anthropic's service for reviewing pull requests in GitHub repositories, available on its Team and Enterprise plans. Several agents read each change and post findings as inline comments ranked by severity. A review never approves or blocks a pull request, and Anthropic says a review with no findings does not mean the code is error-free or secure.
plain answer
What is Claude Code review?
Claude Code review is Anthropic's service for reviewing the pull requests in your GitHub repositories. Anthropic's documentation says several agents read each change alongside the surrounding code, looking for issues such as logic errors, security vulnerabilities or broken edge cases, and that a verification step checks findings against the code before they are reported. Findings arrive as inline comments on the lines concerned, ranked by severity, with a summary and a check run on the pull request. A review never approves or blocks the pull request, so the decision to merge stays with your team. Anthropic also warns that a review with no findings does not mean the code is error-free or secure. (Anthropic Claude Code docs, Code Review, read 8 November 2026.)
plain answer
Who can use Claude Code review?
Anthropic lists the Team and Enterprise plans for the Code Review service, and repositories hosted on GitHub, including GitHub Enterprise Server and GitHub Enterprise Cloud with data residency. An Owner of the Claude organization turns it on. Anthropic's page says the service is not available to organizations with Zero Data Retention enabled or with its HIPAA configuration applied, is not covered under Anthropic's Business Associate Agreement, and is not yet available with customer-managed encryption keys. Anyone on any plan can instead run the /code-review command inside a Claude Code session on their own branch. Check Anthropic's pages for the current rules before you plan a rollout. (Anthropic Claude Code docs, Code Review, read 8 November 2026.)
plain answer
How does a Claude Code review run?
Anthropic describes four stages on its own infrastructure: several agents examine the change in parallel, a verification step filters out false positives, the remaining findings are deduplicated and ranked by severity, and the results are posted to the pull request. Each repository can be set to review once when a pull request opens, after every push, or only on request, and someone with write access can comment @claude review to start one. There are three review levels, Quick, Standard (the default) and Deep, and a more thorough level costs more. Anthropic says a review works from reading the code and does not build or run it. (Anthropic Claude Code docs, Code Review, read 8 November 2026.)
plain answer
What does Claude Code review not do?
Anthropic says that by default it focuses on correctness, meaning bugs that would break production, not formatting preferences or missing test coverage. It does not approve or block a pull request, does not push commits, and has read-only access to your repository during a review. Reviews do not run in self-hosted environments. Because it can miss bugs and security problems, a human reviewer and your own tests still matter. In our view, the useful question for a team is who owns the merge decision and what a reviewer must check regardless of what the tool says. (Anthropic Claude Code docs, Code Review, read 8 November 2026; the last two sentences are Kriv's opinion.)
what kriv does
What does Kriv AI do?
Kriv AI trains engineering teams to use Claude Code in their own codebase, including review discipline, CI integration and a governance module (live page /solutions/claude-code-training, read 6 November 2026). We describe Anthropic's Code Review service here only from Anthropic's own documentation. The Claude Enterprise Training page lists the price of each tier.
Straight answers
Frequently asked questions about Claude Code review: how it works and who can use it
Is Claude Code review free?
Anthropic's page says a more thorough review level costs more and points to a separate costs page; this page states no prices. Check Anthropic's Code Review costs and usage page for current billing.
Can Claude Code review approve or block a pull request?
No. Anthropic says a review never approves or blocks the pull request, and its check run does not conclude as a failure. The merge decision stays with your team.
How do I run Claude Code review on a pull request?
After an Owner turns it on, reviews run as each repository is set, or someone with write access comments @claude review on the pull request.
Is there a way to get a review without the Team or Enterprise plan?
Anthropic says the /code-review command runs in your Claude Code session on any plan. It reviews your branch inside your own Claude Code session rather than as a pull request service.
Talk to the team that would do the work
Bring your requirements to a working session with the person who'll actually deliver.
Book a Discovery Call