What problem does it solve? After implementing a plan, code often drifts from the original intent, introduces security or reliability risks, or breaks existing conventions. This Skill compares actual implementation work against the plan to catch drift, dangerous decisions, and pattern misuse before they compound. ## Core Features & Use Cases - Plan Drift Detection: Uses parallel sub-agents to verify each planned change matches the actual code, flagging missing, drifted, or unplanned changes. - Safety & Quality Scan: Checks changed files for security, performance, reliability, and data-safety issues, plus consistency with existing codebase patterns. - Structured Report & Interactive Triage: Produces a severity-ranked findings report with dimension verdicts (APPROVED / NEEDS ATTENTION / REJECTED), then walks each finding through an interactive fix/skip/record-as-lesson triage loop. - Use Case: After finishing phase 3 of a multi-phase feature plan, run a phase-scoped review to confirm the implementation matches the plan, automated success criteria pass, and no unplanned endpoints were added. ## Quick Start Ask the AI to review the implementation of the current change against its plan, for example by running the review on a specific phase or saved report path.
