Anthropic has made Claude Code Review generally available to Team and Enterprise customers, promising pull-request checks in six to 10 minutes and offering eligible Enterprise organisations up to $50,000 in promotional credits.
Anthropic has made Code Review for Claude Code generally available to Team and Enterprise customers, widening access to a multi-agent system designed to inspect pull requests automatically before humans sign off on them. The launch also comes with a promotional credit offer for eligible Enterprise organisations, giving them a short window to offset review costs as they bring the tool into production workflows.
The company says the service has been refined since its research preview to reduce latency and improve the quality of findings. Anthropic claims reviews now complete about three times faster than before, typically in six to ten minutes rather than around 20, and that the system now tries to present each issue more clearly by spelling out the problem, the trigger and the likely fix. Administrators can also choose how deeply each repository is examined, with Quick, Standard and Deep review levels intended to match scrutiny to the importance of the codebase.
Under the hood, Anthropic describes a four-stage process in which several agents inspect the diff and nearby code in parallel, a verification step filters out weak or false findings, and the remaining issues are deduplicated and ranked before being posted back to the pull request. The review appears as inline comments and a check run called Claude Code Review, but it does not approve or block a merge. Anthropic says the system is aimed primarily at correctness issues rather than stylistic preferences or missing tests, although teams can steer it with REVIEW.md and CLAUDE.md guidance files.
Setup remains an administrative task rather than a developer-level one. An organisation owner enables Code Review in Claude Code settings, installs the Claude GitHub App and selects the repositories to monitor. From there, reviews can run automatically when a pull request is opened, on every push or only when requested, and anyone with write access can trigger one manually by commenting “@claude review”. Draft pull requests and forks are excluded from automatic review, and the service runs in a managed environment with read-only access to the repository.
Anthropic says the product is available only on Team and Enterprise plans and only for GitHub-hosted repositories, including GitHub Enterprise Server and GitHub Enterprise Cloud with data residency. It is not available to organisations using Zero Data Retention, the HIPAA configuration or customer-managed encryption keys, and it is not covered by the company’s Business Associate Agreement. Even organisations using Claude Code through Amazon Bedrock, Google Cloud’s Agent Platform or Microsoft Foundry still need a Claude organisation to use the review feature. The documentation also warns that the system can miss bugs and security issues, and that a clean result is not proof that code is safe.
Pricing during the preview was based on token usage, with typical reviews costing about $15 to $25 depending on pull-request size and complexity. Claude’s support documentation says administrators can monitor usage, set spend caps and tune review behaviour through the analytics dashboard and organisation settings. For eligible paid Claude Enterprise customers, Anthropic is also offering between $10,000 and $50,000 in Code Review credits, with the amount determined at the time of claim by the organisation’s active Claude Code seats. The claim window opened on October 15, 2026 and closes at 23:59 UTC on January 15, 2027.
Disclaimer: This content is intended for informational purposes only. Readers are advised to exercise their own judgement, conduct due diligence, or consult a qualified expert before acting on any information provided.
