Phase 4: Design → PLAN.md written → user approved
  → [THIS SKILL] Dispatch plan reviewer subagent
  → For plans with >15 tasks: review per-chunk
  → Issues found? Fix PLAN.md → re-dispatch reviewer
  → Approved? → Phase 5: Implement

Agent(
  subagent_type="workflows:dev-plan-checker",
  allowed_tools=["Read", "Glob", "Grep", "Bash(read-only)"],
  description="Review plan document",
  prompt="""
You are a plan document reviewer. Verify this plan is complete, matches the spec, and is ready for implementation.

**Tool Restrictions:** You are READ-ONLY. You MUST NOT use Write or Edit tools. You read `.planning/PLAN.md` and `.planning/SPEC.md`, evaluate against the checklist, and return a verdict. If you find issues, you report them — the main chat fixes them.

**Plan to review:** .planning/PLAN.md [— Chunk N only, if chunked]
**Spec for reference:** .planning/SPEC.md

Read BOTH files, then evaluate the plan against ALL categories below.

## What to Check

| Category | What to Look For |
|----------|------------------|
| Completeness | TODOs, placeholders, incomplete tasks, missing steps |
| Spec Alignment | Plan covers ALL spec requirements, no scope creep, no requirements silently dropped |
| Task Decomposition | Tasks atomic enough for a single subagent, clear boundaries, steps actionable |
| Task Ordering | Dependencies correct, no circular dependencies, independent tasks marked |
| File Structure | Files have clear single responsibilities, split by responsibility not layer |
| File Size | Would any new or modified file likely grow too large to reason about? |
| Task Syntax | Checkbox syntax on steps for tracking |
| Testing Strategy | Testing section filled (framework, command, first test, location, skill) |

## CRITICAL — Look Especially Hard For:

- Any TODO markers or placeholder text
- Steps that say "similar to X" without actual content
- Incomplete task definitions (missing verify command or expected output)
- Missing verification steps or expected outputs
- Files planned to hold multiple responsibilities or likely to grow unwieldy
- Spec requirements not covered by ANY task (silently dropped)
- Tasks too large for a single subagent (>100 lines of change)

## Output Format

## Plan Review

**Status:** APPROVED | ISSUES_FOUND

**Issues (if any):**
- [Task X, Step Y]: [specific issue] - [why it matters for implementation]

**Spec Coverage Check:**
- [Requirement 1]: Covered by Task N ✅ | NOT COVERED ❌
- [Requirement 2]: Covered by Task N ✅ | NOT COVERED ❌

**Recommendations (advisory — don't block approval):**
- [suggestions for improvement that aren't blocking]
""")

"Plan reviewer has flagged issues 5 times. Remaining issues:
[list issues]
Should I: (A) Fix these, (B) Proceed with known gaps, (C) Rethink the plan?"

1. IDENTIFY: `.planning/PLAN.md` exists and user approved
2. DISPATCH: Send to reviewer subagent (per-chunk if >15 tasks)
3. READ: Reviewer returns APPROVED or ISSUES_FOUND
4. VERIFY: If ISSUES_FOUND, fix and re-dispatch (max 5)
5. CLAIM: Only proceed to implement when ALL chunks APPROVED