reggiechan74/cc-plugins/plan-review

Claude Code and agent skill by reggiechan74/cc-plugins

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

This skill should be used when the user asks to "review the plan", "check the execution plan", "validate this plan", "is this plan good", or automatically after the planner agent creates an execution plan. Validates plans for completeness, clarity, measurability, and proper acceptance criteria before execution begins.

Install

npx vskill@latest install reggiechan74/cc-plugins/plan-review

SKILL.md

Plan Review: Validate Execution Plans

Purpose

Review and validate execution plans before code changes begin, ensuring plans have clear acceptance criteria, appropriate critic assignments, and realistic scope.

When to Use

  • After planner agent creates execution plan
  • When user explicitly requests plan review
  • Before high-stakes operations (configured in highStakesPatterns)

Validation Criteria

Completeness Checks

✓ Scope defined: Files, operations, and boundaries clear ✓ Success criteria present: At least 3 specific, measurable criteria ✓ Critic assignment: Each criterion mapped to responsible critic ✓ Retry budget set: Escalation path defined ✓ Cost estimate included: Token overhead calculated

Quality Gates

Acceptance criteria must be:

  • Specific (not "good code" but "all tests pass, coverage >80%")
  • Measurable (binary pass/fail, not subjective)
  • Pre-declared (before execution, not emergent)
  • Mapped to critics (clear veto authority assignment)

Domain-specific patterns:

  • Financial: Must specify precision, rounding method, audit requirements
  • Security: Must reference OWASP checklist, auth patterns
  • Performance: Must define latency SLAs, memory limits

Review Process

  1. Parse plan structure - Extract scope, criteria, critics, budget
  2. Check completeness - Verify all required sections present
  3. Validate criteria - Ensure specific and measurable
  4. Verify critic mapping - Each criterion has responsible critic
  5. Check domain patterns - Apply domain-specific requirements
  6. Estimate feasibility - Scope appropriate for retry budget
  7. Present findings - Show issues and recommendations

Example Reviews

Good Plan
EXECUTION PLAN ✓
Scope: Refactor auth to JWT ✓
Files: src/auth/*.ts ✓
SUCCESS CRITERIA: ✓
✓ All 18 existing tests pass (Code Critic validates)
✓ No OWASP Top 10 violations (Security Critic validates)
✓ Token storage uses httpOnly cookies (Security Critic validates)
✓ Token refresh handles 401 (Code Critic validates)
✓ Coverage maintains 85%+ (Code Critic validates)
Critics: code, security ✓
Budget: 6 iterations ✓
Cost: +40% tokens ($0.15) ✓
Plan Needs Improvement
EXECUTION PLAN ❌
Scope: Make the code better ❌ TOO VAGUE
Files: Not specified ❌ MISSING
SUCCESS CRITERIA: ❌
- Code should be high quality ❌ NOT MEASURABLE
- No bugs ❌ NOT SPECIFIC
- Fast performance ❌ NO THRESHOLD
Critics: None assigned ❌
Budget: Not set ❌

Required fixes:

  1. Define specific scope and files
  2. Make criteria measurable (e.g., "all tests pass", "latency <200ms")
  3. Assign critics to each criterion
  4. Set retry budget

Configuration

Plans automatically reviewed when autoVerify: true in settings.

For manual review, invoke explicitly after planning phase.

Additional Resources

  • `references/acceptance-criteria-patterns.md` - Domain-specific criteria templates
  • `references/plan-examples.md` - Good and bad plan examples

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/reggiechan74/cc-plugins/plan-review/badge)](https://verified-skill.com/skills/reggiechan74/cc-plugins/plan-review)

Something wrong with this skill or its page? Tell us.