Agent skill
plan-review
Use when about to implement a plan, when plan seems incomplete or has gaps, when unsure if tasks are feasible, or when validating spec before coding
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/plan-review-skill
SKILL.md
Plan Review Skill
Two-phase review: analyze/document findings (separate agent), then apply approved changes (main context).
Quick Reference
| Phase | Where | Why |
|---|---|---|
| Phase 1: Review | Forked context (Haiku) | Cost-efficient, isolated analysis |
| Phase 2: Apply | Main context | Needs user interaction |
Input: Plan path (e.g., _tasks/15-feature/02-plan.md)
Output: _plan-review.md with findings + recommendation
Baseline Problem (Why Separate Agent)
Without separation: Main agent reads plan, creates review doc, manages iterations, tracks findings → consumes significant context before user interaction even begins.
With separation: Skill runs in forked context with Haiku → returns summary only → main context preserved for Phase 2.
Benefits:
- ~80% context savings in main conversation
- ~10x cost reduction using Haiku for read-only analysis
- Clean isolation - analysis doesn't pollute implementation context
Phase 1: Review → Forked Context (This Skill)
This skill runs in an isolated forked context using Haiku model.
Tasks:
- Review the plan at
$ARGUMENTS(the plan path provided) - Create
{TARGET_DIR}/_plan-review.md - Iterate (max 4) until no NEW findings
Assess:
- Completeness: requirements covered? edge cases?
- Feasibility: achievable? hidden complexity? dependencies?
- Clarity: implementer can follow? specific paths? verification steps?
- YAGNI: unnecessary scope? duplication?
Checklist: tasks have file paths, verification steps, correct order, no scope creep.
Categorize findings: Critical/Important/Minor
Commit the review: git commit -m "review: plan review for {PLAN_NAME}"
Return: Summary only (count of findings, recommendation: Ready/Needs Revisions/Major Rework)
Phase 2: Apply → Main Context
After user approval only. User returns to main conversation to discuss findings.
- Apply user-approved fixes to source plan
- Mark findings
[x]in_plan-review.md - Commit:
git commit -m "plan: apply review feedback for {PLAN_NAME}" - Update
_plan-review.mdwith Resolution section (addressed/skipped)
Common Mistakes
| Mistake | Fix |
|---|---|
| Running Phase 1 in main context | Use this skill - it forks automatically |
| Applying fixes without user approval | STOP after Phase 1, wait for direction |
| Skipping commit after review | Commit _plan-review.md before presenting |
| Over-iterating (>4 rounds) | Quality gate: stop when no NEW findings |
Example
User: /plan-review _tasks/20-e2e-testing/02-plan.md
Claude: [Skill runs in forked Haiku context]
Skill: "2 Critical, 3 Important, 1 Minor. Needs revisions."
Claude: Plan review complete. [summary] Full details: _plan-review.md
User: Address Critical and Important. Skip Minor.
Claude: [Phase 2 in main context - applies fixes]
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?