Claude Code’s /code-review now has effort levels
The code-review command runs at several levels, rebuilding the review from scratch at each one:
• Low: beats other review tools on number of findings while using a fraction of their tokens • High: noticeably better finding coverage when you need to dig deeper • Ultra: spins up a set of reviewer agents and independently reproduces every finding
Ultra matches high on coverage of serious issues but with far fewer false positives. Anthropic runs it on every PR. It’s live in all sessions once you update Claude Code.
Up next
Claude Managed Agents can now hand tasks off to each other, Video
Claude Managed Agents added a multi-agent mode where Claude coordinates work and hands tasks between agents. Each agent can run its own model, prompt, and tools while sharing sandboxes or vault credentials. Anthropic recapped it in a YouTube talk.
Related stories
- Claude Code v2.1.218: /code-review moves to a background subagent
- Claude reviewing Codex: 71.6% to 89.7%. Codex reviewing Claude: 91.4% down to 82.8%.
- Cloud sessions in Claude Code now set up your repo
- Claude Code desktop gives each parallel task its own session
- Claude Code Projects admits its whole Pro and Max waitlist
- In Claude Code, a “block” hook could let commands through
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.