Anthropic Launches /ultrareview for Claude Code: Multi-Agent Cloud-Based Code Review

Gate News message, April 23 — Anthropic has introduced /ultrareview (research preview), a cloud-based multi-agent code review feature for Claude Code. Users can type /ultrareview in the CLI to launch a group of review agents in a remote sandbox that work in parallel to examine diffs between the current branch and the default branch (including uncommitted changes), or directly review GitHub PRs by providing a PR number. The entire process requires no local resources and typically takes 5 to 10 minutes, with results returned to the session as notifications.

The key distinction from the local /review tool lies in its verification mechanism: each finding is independently reproduced and confirmed by a separate agent, focusing on actual bugs rather than code style suggestions. Anthropic positions the two tools for different stages of development—/review for quick feedback during coding, and /ultrareview for deep review of critical changes (such as authentication or data migration) before merging.

Regarding pricing, /ultrareview uses extra usage billing and does not consume plan-included usage. Pro and Max users each have 3 free uses before May 5 (one-time, non-renewable), after which each review costs approximately $5 to $20 depending on the scale of changes. Team and Enterprise users have no free allowance. The feature requires Claude.ai account authentication and is unavailable for Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry, or organizations with zero data retention enabled.