🧪 Executing Plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
npx playbooks add skill obra/superpowers --skill executing-plans
About Executing Plans
Load plan, review critically, execute tasks in batches, report for review between batches.
Its 356-word system prompt specializes your agent in testing & qa with structured methodology and proven output formats. Install with one command to activate immediately.
Key Capabilities
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."
- Apply changes if needed
- Execute next batch
What This Skill Covers
- Overview
- The Process
- When to Stop and Ask for Help
- When to Revisit Earlier Steps
- Remember
- Integration
How It Works
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
- Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
Use Cases
- Writing unit, integration, and end-to-end tests
- Setting up test coverage and CI pipelines
- Refactoring legacy code with confidence using tests
- Creating test plans and QA checklists
Example Prompts
System Prompt (356 words)
Executing Plans
Overview
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
The Process
Step 1: Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Batch
Default: First 3 tasksFor each task:
- Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
- Run verifications as specified
- Mark as completed
Step 3: Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."
Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete
Step 5: Complete Development
After all tasks complete and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice
When to Stop and Ask for Help
STOP executing immediately when:
- Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly
Ask for clarification rather than guessing.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- Partner updates the plan based on your feedback
- Fundamental approach needs rethinking
Don't force through blockers - stop and ask.
Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Between batches: just report and wait
- Stop when blocked, don't guess
- Never start implementation on main/master branch without explicit user consent
Integration
Required workflow skills:
- superpowers:using-git-worktrees - REQUIRED: Set up isolated workspace before starting
- superpowers:writing-plans - Creates the plan this skill executes
- superpowers:finishing-a-development-branch - Complete development after all tasks
Frequently Asked Questions
What is Executing Plans?
Executing Plans is a free testing & qa skill for AI coding agents. Use when you have a written implementation plan to execute in a separate session with review checkpoints. It provides a specialized system prompt that configures your agent with testing & qa expertise.
How do I use Executing Plans with Claude Code?
Run npx playbooks add skill obra/superpowers --skill executing-plans in your terminal to install Executing Plans into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Executing Plans?
Executing Plans is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Executing Plans free to use?
Yes, Executing Plans is completely free and open source. The full source is available on GitHub at https://github.com/obra/superpowers/tree/main/skills/executing-plans. You only need a subscription to the AI agent you use it with.
