Cleanup Health Check (Inline Orchestration)

You ARE the orchestrator. Execute this workflow directly without spawning a separate orchestrator agent.

Workflow Overview

Beads Init → Detection → Create Issues → Remove by Priority → Close Issues → Verify → Beads Complete

Max iterations: 3 Priorities: critical → high → medium → low Beads integration: Automatic issue tracking

Phase 1: Pre-flight & Beads Init

1. Setup directories:

``bash mkdir -p .tmp/current/{plans,changes,backups} ``

1. Validate environment:

- Check package.json exists - Check type-check and build scripts exist

1. Create Beads wisp:

``bash bd mol wisp exploration --vars "question=Dead code cleanup scan" ``

IMPORTANT: Save the wisp ID (e.g., mc2-xxx) for later use.

1. Initialize TodoWrite:

``json [ {"content": "Dead code detection", "status": "in_progress", "activeForm": "Detecting dead code"}, {"content": "Create Beads issues", "status": "pending", "activeForm": "Creating issues"}, {"content": "Remove critical dead code", "status": "pending", "activeForm": "Removing critical dead code"}, {"content": "Remove high priority dead code", "status": "pending", "activeForm": "Removing high dead code"}, {"content": "Remove medium priority dead code", "status": "pending", "activeForm": "Removing medium dead code"}, {"content": "Remove low priority dead code", "status": "pending", "activeForm": "Removing low dead code"}, {"content": "Verification scan", "status": "pending", "activeForm": "Verifying cleanup"}, {"content": "Complete Beads wisp", "status": "pending", "activeForm": "Completing wisp"} ] ``

Phase 2: Detection

Invoke dead-code-hunter via Task tool:

subagent_type: "dead-code-hunter"
description: "Detect all dead code"
prompt: |
  Scan the entire codebase for dead code:
  - Unused imports and exports
  - Commented out code blocks
  - Unreachable code
  - Debug statements (console.log, debugger)
  - Unused variables and functions
  - Unused dependencies
  - Categorize by priority (critical/high/medium/low)

  Generate: dead-code-report.md

  Return summary with dead code counts per priority.

After dead-code-hunter returns:

1. Read dead-code-report.md
2. Parse dead code counts by priority
3. If zero dead code → skip to Phase 7 (Final Summary)
4. Update TodoWrite: mark detection complete

Phase 3: Create Beads Issues

For each dead code item found, create a Beads issue:

# Critical (P1)
bd create "CLEANUP: {item_title}" -t chore -p 1 -d "{description}" \
  --deps discovered-from:{wisp_id}

# High (P2)
bd create "CLEANUP: {item_title}" -t chore -p 2 -d "{description}" \
  --deps discovered-from:{wisp_id}

# Medium (P3)
bd create "CLEANUP: {item_title}" -t chore -p 3 -d "{description}" \
  --deps discovered-from:{wisp_id}

# Low (P4)
bd create "CLEANUP: {item_title}" -t chore -p 4 -d "{description}" \
  --deps discovered-from:{wisp_id}

Track issue IDs in a mapping for later closure.

Update TodoWrite: mark "Create Beads issues" complete.

Phase 4: Quality Gate (Pre-removal)

Run inline validation:

pnpm type-check
pnpm build

• If both pass → proceed to removal
• If fail → report to user, exit

Phase 5: Removal Loop

For each priority (critical → high → medium → low):

1. Check if dead code exists for this priority

- If zero → skip to next priority

1. Update TodoWrite: mark current priority in_progress

1. Claim issues in Beads:

``bash bd update {issueid} --status inprogress ``

1. Invoke dead-code-remover via Task tool:

``` subagent_type: "dead-code-remover" description: "Remove {priority} dead code" prompt: | Read dead-code-report.md and remove all {priority} priority dead code.

For each item: 1. Backup file before editing 2. Remove dead code 3. Log change to .tmp/current/changes/cleanup-changes.json

Generate/update: dead-code-cleanup-summary.md

Return: count of removed items, count of failed removals, list of removed item IDs. ```

1. Quality Gate (inline):

``bash pnpm type-check pnpm build ``

- If FAIL → report error, suggest rollback, exit - If PASS → continue

1. Close removed issues in Beads:

``bash bd close {issueid1} {issueid2} ... --reason "Removed in cleanup" ``

1. Update TodoWrite: mark priority complete

1. Repeat for next priority

Phase 6: Verification

After all priorities cleaned:

1. Update TodoWrite: mark verification in_progress

1. Invoke dead-code-hunter (verification mode):

``` subagent_type: "dead-code-hunter" description: "Verification scan" prompt: | Re-scan codebase after cleanup. Compare with previous dead-code-report.md.

Report: - Dead code removed (count) - Dead code remaining (count) - New dead code introduced (count) ```

1. Decision:

- If deadcoderemaining == 0 → Phase 7 - If iteration < 3 AND deadcoderemaining > 0 → Go to Phase 2 - If iteration >= 3 → Phase 7 with remaining items

Phase 7: Final Summary & Beads Complete

1. Complete Beads wisp:

```bash # If all cleaned bd mol squash {wisp_id}

# If nothing found bd mol burn {wisp_id} ```

1. Create issues for remaining items (if any):

``bash bd create "REMAINING: {item_title}" -t chore -p {priority} \ -d "Not removed in cleanup. See dead-code-report.md" ``

1. Generate summary for user:

## Cleanup Health Check Complete

**Wisp ID**: {wisp_id}
**Iterations**: {count}/3
**Status**: {SUCCESS/PARTIAL}

### Results
- Found: {total} dead code items
- Removed: {removed} ({percentage}%)
- Remaining: {remaining}

### By Priority
- Critical: {removed}/{total}
- High: {removed}/{total}
- Medium: {removed}/{total}
- Low: {removed}/{total}

### Beads Issues
- Created: {count}
- Closed: {count}
- Remaining: {count}

### Validation
- Type Check: {status}
- Build: {status}

### Artifacts
- Detection: `dead-code-report.md`
- Cleanup: `dead-code-cleanup-summary.md`

1. Update TodoWrite: mark wisp complete

1. SESSION CLOSE PROTOCOL:

``bash git status git add . bd sync git commit -m "chore: cleanup - {removed} dead code items removed ({wisp_id})" bd sync git push ``

Error Handling

If quality gate fails:

Rollback available: .tmp/current/changes/cleanup-changes.json

To rollback:
1. Read changes log
2. Restore files from .tmp/current/backups/
3. Re-run workflow

If worker fails:

• Report error to user
• Keep Beads wisp open for manual completion
• Suggest manual intervention
• Exit workflow

If Beads command fails:

• Log error but continue workflow
• Beads tracking is enhancement, not blocker

Quick Reference