Assumption health report — validate whether deep-work's enforcement rules are still justified by session evidence

Phase 0: Brainstorm — explore why before how (skip-able with --skip-brainstorm)

Clean up stale deep-work worktrees — scan and delete old worktrees

Systematic debugging sub-mode — root cause investigation before fixes

Finish a deep work session — merge, PR, keep, or discard the branch

View deep work session history — cross-session trends, model usage, TDD compliance

Phase 3: Implement the approved plan using slice-based TDD execution

코드 메트릭, 복잡도, 의존성 분석 기반 인사이트 리포트. 독립 실행 또는 deep-work Insight Quality Gate로 사용.

Phase 2: Deep planning - create a detailed implementation plan

Receipt management — view, dashboard, export receipts

Generate or view the deep work session report

Phase 1: Deep research - exhaustively analyze the codebase

Resume an active deep work session — restores context and continues from where you left off

Manually trigger structural review and/or cross-model adversarial review on current phase document

Slice management — view status, activate, deactivate slices

Check the current deep work session status and progress

Phase 4: Run comprehensive tests and verify implementation

Start a deep work session with Evidence-Driven Protocol (Brainstorm → Research → Plan → Implement → Test)

Plan alignment verification — detects unimplemented items, out-of-scope changes, and design drift. Standalone or deep-work Required Gate.

SOLID design principles code review — evaluates SRP, OCP, LSP, ISP, DIP compliance. Standalone or deep-work Advisory Quality Gate.

Evidence-driven development protocol with auto-flow orchestration. Use when: "deep work", "plan before code", "TDD", "evidence-driven", "분석 후 구현", "structured workflow", or complex multi-file tasks that benefit from structured planning before implementation.

4 hooks across 4 events