code-review
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, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official code-review plugin. It runs multiple specialized subagents over a pull request diff and combines their findings with confidence-based scoring to suppress false positives. Surface is a slash command that dispatches review subagents; the agents read the diff and produce ranked findings.
Key features and capabilities
- Multiple specialized review subagents
- Confidence-based scoring to filter false positives
- Runs over pull request diffs
- Slash-command driven
Use cases
- Automated first-pass review of a PR before human review
- Filtering noisy static-analysis-style findings