AndyZ

Detects stale comments, docstring-signature mismatches, and contradicted NOTE/TODO/FIXME markers

Checks changed code against project conventions and coding style

Detects logic errors, off-by-one bugs, null handling issues, and race conditions

Detects when changes break callers, interfaces, or type contracts in other files

Detects AI-generated code issues — non-existent APIs, wrong signatures, deprecated dependencies

Uses git history to identify high-risk patterns in changed files

Confirms or downgrades CRITICAL findings post-synthesis using deployment context; requires a cited mitigation for any downgrade

Fast risk assessment of PR changes. Computes a 0-100 risk score from 6 weighted factors and recommends which review agents to dispatch.

Detects security vulnerabilities following OWASP Top 10 with data flow analysis

Detects silent error-handling failures — empty catches, swallowed Promise rejections, optional-chaining-masked nullability, assertion-free tests

Verifies acceptance criteria from REVIEW.md / .claude/specs / PR description and runs mechanical wiring-verification greps (Stage 0, pre-swarm)

Merges, deduplicates, filters, and synthesizes findings from all review agents into a coherent review

Evaluates test coverage and test quality for changed code

PR number, GitHub PR URL, or omit for local branch review