Claude Code Review
claude.com
- Windows
- macOS
- Linux
- Web
6.9 Club score Visit claude.com
Plans
Every plan and priceCode Review usage
—
Claude Code Review
—
What the maker publishes
- Average duration
- Reviews take 20 minutes on average, according to the setup article. source
- Company
- Anthropic describes itself as an AI safety and research company that builds reliable, interpretable, and steerable AI systems. source
- Configuration
- Claude can discover REVIEW.md at the repository root, and organizations can configure what the review flags or skips. source
- Findings
- Findings are deduplicated, ranked by severity, and posted as inline comments; reviews do not approve or block pull requests. source
- Free plan
- No source
- Headquarters and founding
- Anthropic is headquartered in San Francisco and was founded at the beginning of 2021. source
- Limits
- Code Review is in research preview, available on Team and Enterprise plans, and unavailable to organizations with zero data retention enabled. source
- Marketplace plugin
- The Anthropic verified Claude Code plugin runs with `/code-review` and can post actionable feedback directly to GitHub. source
- Plugin filtering
- The marketplace plugin skips closed, draft, automated, or already-reviewed pull requests, and its default confidence threshold for comments is 80 out of 100. source
- Purpose
- Claude Code Review analyzes GitHub pull requests and posts findings as inline comments on affected lines. source
- Review focus
- By default, Code Review focuses on correctness issues that could break production rather than formatting preferences or missing test coverage. source
- Review triggers
- Organizations can trigger reviews when a pull request opens, after every push, or only when someone requests one manually. source
- Security focus
- The marketplace plugin lets users customize review focus areas such as security, performance, and accessibility. source
- Specialized agents
- Multiple agents examine code changes in the context of the full codebase for logic errors, security vulnerabilities, broken edge cases, and regressions. source
- Usage cost
- Review costs vary with pull request size, codebase complexity, and the number of issues requiring verification. source
Checked against the maker's pages on 11 Oct 2026.