feat: integrate cleanup phase into implementation workflow

- Add handoff from implement.md to cleanup command
- Add cleanup phase (N+1) to tasks-template.md
- Update phase dependencies to include cleanup as final gate
- Update incremental delivery strategy to include cleanup step
- Suggest running cleanup after implementation completes

Author: dsrednicki

templates/commands/implement.md

@@ -3,6 +3,10 @@ description: Execute the implementation plan by processing and executing all tas
 scripts:
   sh: scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
   ps: scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
+handoffs:
+  - label: Run cleanup phase
+    agent: speckit.cleanup
+    prompt: Review implementation changes, fix small issues, and identify tech debt
 ---
 
 ## User Input
@@ -134,5 +138,6 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Validate that tests pass and coverage meets requirements
    - Confirm the implementation follows the technical plan
    - Report final status with summary of completed work
+   - **Suggest next step**: Recommend running `/speckit.cleanup` to review changes and identify tech debt
 
 Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running `/speckit.tasks` first to regenerate the task list.

templates/tasks-template.md

@@ -159,6 +159,30 @@ Examples of foundational tasks (adjust based on your project):
 
 ---
 
+## Phase N+1: Cleanup & Tech Debt Review
+
+**Purpose**: Final quality gate - review all changes, identify tech debt, and ensure code hygiene
+
+**Executed by**: `/speckit.cleanup` command (run after `/speckit.implement` completes)
+
+The cleanup phase handles issues by severity:
+
+| Severity | Examples | Action |
+|----------|----------|--------|
+| **Small** | Debug statements, unused imports, dead code | Fix immediately (Scout Rule) |
+| **Medium** | Missing error handling, code duplication (2-3x) | Create follow-up tasks in tasks.md |
+| **Large** | Architectural issues, security vulnerabilities | Generate tech-debt-report.md with options |
+
+### Output Artifacts
+
+All outputs stay within the spec workflow (`/specs/[###-feature-name]/`):
+
+- **Direct fixes**: Small issues fixed and committed
+- **Tech Debt Tasks**: Appended to tasks.md for medium issues
+- **tech-debt-report.md**: Analysis with options for large issues
+
+---
+
 ## Dependencies & Execution Order
 
 ### Phase Dependencies
@@ -168,7 +192,8 @@ Examples of foundational tasks (adjust based on your project):
 - **User Stories (Phase 3+)**: All depend on Foundational phase completion
   - User stories can then proceed in parallel (if staffed)
   - Or sequentially in priority order (P1 → P2 → P3)
-- **Polish (Final Phase)**: Depends on all desired user stories being complete
+- **Polish (Phase N)**: Depends on all desired user stories being complete
+- **Cleanup (Phase N+1)**: Depends on Polish completion - FINAL quality gate before delivery
 
 ### User Story Dependencies
 
@@ -225,7 +250,9 @@ Task: "Create [Entity2] model in src/models/[entity2].py"
 2. Add User Story 1 → Test independently → Deploy/Demo (MVP!)
 3. Add User Story 2 → Test independently → Deploy/Demo
 4. Add User Story 3 → Test independently → Deploy/Demo
-5. Each story adds value without breaking previous stories
+5. Complete Polish → Cross-cutting improvements applied
+6. Complete Cleanup → Tech debt reviewed, small fixes applied, follow-ups created
+7. Each story adds value without breaking previous stories
 
 ### Parallel Team Strategy