Claude Code Review
claude.com
Spec sheet
- Purpose
- Claude Code Review analyzes GitHub pull requests and posts findings as inline comments on affected lines.Read 11 Oct 2026 · support.claude.com
- Free plan
- NoRead 22 Sep 2026 · claude.com
- Company
- Anthropic describes itself as an AI safety and research company that builds reliable, interpretable, and steerable AI systems.Read 11 Oct 2026 · anthropic.com
- Average duration
- Reviews take 20 minutes on average, according to the setup article.Read 11 Oct 2026 · support.claude.com
- Configuration
- Claude can discover REVIEW.md at the repository root, and organizations can configure what the review flags or skips.Read 11 Oct 2026 · support.claude.com
- Findings
- Findings are deduplicated, ranked by severity, and posted as inline comments; reviews do not approve or block pull requests.Read 11 Oct 2026 · support.claude.com
- Headquarters and founding
- Anthropic is headquartered in San Francisco and was founded at the beginning of 2021.Read 11 Oct 2026 · anthropic.com
- Limits
- Code Review is in research preview, available on Team and Enterprise plans, and unavailable to organizations with zero data retention enabled.Read 11 Oct 2026 · support.claude.com
- Marketplace plugin
- The Anthropic verified Claude Code plugin runs with `/code-review` and can post actionable feedback directly to GitHub.Read 11 Oct 2026 · claude.com
- 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.Read 11 Oct 2026 · claude.com
- Review focus
- By default, Code Review focuses on correctness issues that could break production rather than formatting preferences or missing test coverage.Read 11 Oct 2026 · support.claude.com
- Review triggers
- Organizations can trigger reviews when a pull request opens, after every push, or only when someone requests one manually.Read 11 Oct 2026 · support.claude.com
- Security focus
- The marketplace plugin lets users customize review focus areas such as security, performance, and accessibility.Read 11 Oct 2026 · claude.com
- Specialized agents
- Multiple agents examine code changes in the context of the full codebase for logic errors, security vulnerabilities, broken edge cases, and regressions.Read 11 Oct 2026 · support.claude.com
- Usage cost
- Review costs vary with pull request size, codebase complexity, and the number of issues requiring verification.Read 11 Oct 2026 · support.claude.com
Plans and prices
Code Review usage Price not published Available for Team and Enterprise plans · Billed separately through usage credits · Average review cost is stated as $15–25 Read 22 Sep 2026 · support.claude.com
Claude Code Review Price not published Billed based on token usage; each review averages $15–25. Available on Team and Enterprise plans · Usage billed separately through usage credits Read 11 Oct 2026 · support.claude.com
Where Specifiction places it
- Pull Request Automation Tools#15 of 297.7
- Code review software#35 of 517.8
- Emerging AI Software#18 of 227.8
- AI Code Generators#46 of 547.7
- AI Coding Assistants#96 of 1027.0