Claude Code Launches /ultrareview for Multi-Agent Cloud Code Review

According to monitoring by Beating, Anthropic has introduced /ultrareview (research preview) in Claude Code, a cloud-based multi-agent code review feature. Users can input /ultrareview in the CLI, and the system will launch a set of review agents in a remote sandbox to concurrently check the diff between the current branch and the default branch (including uncommitted changes). Users can also directly review GitHub PRs by providing the PR number. The entire process does not consume local resources and takes about 5 to 10 minutes, with results returned to the session in the form of notifications. The core difference from the local /review is the validation mechanism: each finding is confirmed by independent agents, focusing on real bugs rather than code style suggestions. The official documentation positions the two as tools for different stages: /review is for quick feedback during the coding process, while /ultrareview is for in-depth review of critical changes (such as authentication and data migration) before merging. In terms of billing, /ultrareview is charged as extra usage and does not consume planned usage. Pro and Max users have three free uses each before May 5 (one-time, non-refreshable), after which each use costs approximately $5 to $20, depending on the scale of changes. Team and Enterprise users do not have free usage. This feature requires a Claude.ai account for authentication and cannot be used with Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry, or organizations that have enabled zero data retention.