Source: Ported from obra/superpowers -- skills/executing-plans

Executing Plans

Overview

Load plan, review critically, execute all tasks, report when complete.

Announce at start: "I'm using the executing-plans skill to implement this plan."

Note: This skill works best on platforms with subagent support (such as Claude Code or Codex). When subagents are available, prefer dispatching a fresh subagent per task for higher quality results.

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 Tasks

For each task:

Mark as in_progress
Follow each step exactly (plan has bite-sized steps)
Run verifications as specified
Mark as completed

Step 3: Complete Development

After all tasks complete and verified:

Verify all tests pass
Present summary of what was built
Offer options: merge to main, create PR, or clean up branch (squash commits, update docs)

When to Stop and Ask for Help

STOP executing immediately when:

Hit a blocker (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
Stop when blocked, don't guess
Never start implementation on main/master branch without explicit user consent

Integration

Related skills and practices:

ai-tooling:writing-plans - Creates the plan this skill executes
Use a git worktree or dedicated branch to isolate work before starting
After completion: verify tests pass, then merge, create PR, or clean up branch