Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
Use when you need to understand what a system was truly designed to become, where its real moat lies, or to produce a comprehensive analysis report combining all prior findings.
Use when predicting how a system behaves under different conditions, testing "what if" scenarios for gate combinations, or comparing behavioral fingerprints across configurations.
Use when you have a specific suspicion about a codebase and want targeted analysis to confirm or deny it with evidence, rather than exploratory analysis.
Use when repo origin is unclear, dealing with leaks/sourcemaps/decompiled code, or needing to distinguish source of truth from derived, generated, or reconstructed layers.
Use when tracking how data enters, transforms, persists, and exits a system, or when investigating trust boundaries, validation gaps, and potential data exfiltration paths.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.