What problem does it solve? Deep codebase reviews often produce shallow, hallucinated, or unverifiable findings. This Skill enforces an evidence-gated review workflow where every claim must cite exact file paths, line numbers, and verbatim quotes, and no report is written until full coverage closure is reached. ## Core Features & Use Cases - Phase 0 Inventory: Maps directories, manifests, dependencies, public surfaces, trust boundaries, tests, UI, and AI/MCP surfaces before any review begins. - Selectable Review Tracks: Run focused or combined audits for functionality, security and supply chain, testing, UI/accessibility, performance/observability, AI slop, or enhancement opportunities, with depth that never dilutes across tracks. - Multi-Stage Validation: Explorer candidates are filtered by reviewer validation, inline critics for CRITICAL/HIGH findings, and a mandatory final whole-report critic before the report is written. - Use Case: Ask for a security and supply-chain audit of a repository; the skill inventories the codebase, checks dependencies against OWASP ASVS 5.0.0 and SLSA v1.2, validates each finding with quoted evidence, and writes a verified report under .swarm/review-v8 without modifying source files. ## Quick Start Ask the agent to run $codebase-review-swarm at the repository root to perform a comprehensive codebase review, then choose your review tracks when prompted after the Phase 0 inventory.
