Test Plan Clean — Testing skill for Claude Code
Create implementation plan ONLY - does NOT implement code.
How to install Test Plan Clean
Installs to ~/.claude/commands/codingthefuturewithai-mcp-cookie-cutter-test-plan-clean.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/codingthefuturewithai/mcp-cookie-cutter/HEAD/.claude/commands/test-plan-clean.md -o ~/.claude/commands/codingthefuturewithai-mcp-cookie-cutter-test-plan-clean.md Restart Claude Code, or start a new session, for it to be picked up.
What Test Plan Clean does
description: Create implementation plan ONLY - does NOT implement code argument-hint: "[--tdd]" allowed-tools: ["mcp__context7__resolve-library-id", "mcp__context7__get-library-docs", "Read", "Grep", "Glob", "Bash", "Write"]
Plan Work - TEST-123
⚠️ **CRITICAL COMMAND BOUNDARY** ⚠️
- This command MUST ONLY create plans
- This command MUST NOT implement any code
- This command MUST NOT use Edit or MultiEdit tools
- Even if the user says "approved" or "looks good", DO NOT IMPLEMENT
I'
Alternatives in Testing
- AI Contribution Skills (Engram) — branch-pr: clean branch and PR workflow 2.5k ★
- Spec Driven Development — Drive Kandev feature work through spec, plan, independent tasks, implementation, QA, and verification 697 ★
- Green — Execute TDD Green Phase - write minimal implementation to pass the failing test 168 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Rpi Implement
RPI Step 4 — Execute phased implementation with validation gates. Reads PLAN.md and eng.md, implements phase-b
Execute Tasks
Execute the task DAG for a work item — implement, verify against the testing plan, self-check, self/critic-rev
Yarstack
Engineering workflows and standards for Codex and Claude Code: plan, implement, test, review, and deliver repo
Ab Test Setup
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation
Skeleton First Code Skill
AI coding agent workflow skill: long-context memory, anti-amnesia pipeline (Plan→Implement→Test), module tree
Flawz
Hostile-but-honest flaw hunt on a plan, spec, design, or reasoning (not code diffs — that's /flow:deep-review)
Related Agents
Qrspi Code Quality Reviewer
Verifies the implementation is clean, well-structured, and maintainable. Used in both Implement phase (per-tas
Cook
Feature implementation orchestrator — handles 70% of requests. Full TDD cycle: understand → plan → test → impl
Omg Implementer
Executes a single approved plan step in an OMG repo — grep-first edit, TDD when a test file exists, OMG layer
