Claude Launches 'Ultrareview' AI Code Review Tool That Deploys Remote Agents to Catch Real Bugs Before Merging
Summary
Claude launches 'Ultrareview,' a premium AI-powered code review tool that deploys remote agents to independently detect and verify real bugs in pull requests before merging, available to Pro and Max subscribers with 3 free runs before costing $5–$20 per review.
Key Points
- Ultrareview (/code-review ultra) is a premium cloud-based code review tool that deploys a fleet of remote AI agents to independently find and verify real bugs in a branch or pull request before merging, offering higher signal and broader coverage than local reviews.
- The feature runs entirely in a remote sandbox, requires Claude.ai authentication, and is unavailable on Amazon Bedrock, Google Cloud, Microsoft Foundry, or for organizations with Zero Data Retention enabled; Pro and Max subscribers receive 3 free runs, after which reviews cost $5–$20 in usage credits.
- Users can run ultrareview interactively via /code-review ultra, track progress with /tasks, or execute it non-interactively in CI pipelines using the claude ultrareview subcommand, which blocks until completion and outputs findings to stdout.