pr-review-toolkit
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and simplification.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for pr-review-toolkit, 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 PR review toolkit. It bundles a set of specialized review subagents, each focused on one axis: comment quality, test coverage, error handling, type design, general code quality, and code simplification. Surface is the bundled subagents plus commands that invoke them against a diff.
Key features and capabilities
- Dedicated subagent per review axis
- Covers comments, tests, error handling, type design
- Code-quality and simplification agents
- Composable review commands
Use cases
- Deep multi-axis review of a pull request
- Targeting a specific review concern like test coverage