Code Review (Anthropic)
Automated PR code review using multiple specialized agents with confidence-based scoring to filter false positives.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Code Review (Anthropic), derived from its capabilities.
AIVSS 7.4 · High
View MAESTRO 7-layer threat model →Overview
This first-party plugin runs automated code review on pull requests using several specialized agents and confidence-based scoring to suppress false positives. It surfaces prioritized findings so reviewers focus on real issues. Bundled in the core Claude Code marketplace.
Key features
- Multi-agent review
- Confidence-based scoring
- False-positive filtering
- PR-focused workflow
Use cases
- Automated PR review
- Triaging review findings by confidence