executing-plans

Executes written implementation plans task-by-task with verification checkpoints and review gates.

1|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/ibytechaos/claude --skill executing-plans-ibytechaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/ibytechaos/claude/tree/main/plugins/superpowers/skills/executing-plans
Command: npx skills add https://github.com/ibytechaos/claude --skill executing-plans-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often get executed inconsistently—steps get skipped, verifications are ignored, and blockers are guessed around instead of raised. This Skill enforces a disciplined process for executing a plan in a separate session with review checkpoints. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and reviews it critically before starting, raising concerns with the human partner instead of proceeding blindly. - Structured Task Execution: Tracks each task with TodoWrite, follows bite-sized steps exactly, and runs the verifications specified in the plan. - Stop-and-Ask Discipline: Halts execution on blockers, unclear instructions, or repeated verification failures rather than guessing. - Use Case: You have a multi-task implementation plan written in a prior session. Hand it to this Skill in a fresh session, and it reviews the plan, executes every task with verifications, and hands off to the finishing-a-development-branch workflow when complete. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/my-feature-plan.md, reviewing it critically first and stopping if you hit any blockers.

Frequently Asked Questions about executing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an implementation plan with an AI coding assistant?

Load the plan file, review it critically for gaps or concerns, then execute each task in order while running the verifications the plan specifies. Track progress with a todo list and mark tasks completed only after verification passes.

What should I do before starting to execute a written plan?

Read the entire plan and review it critically, raising any questions or concerns with your human partner before writing code. Only proceed once concerns are resolved, and set up an isolated workspace such as a git worktree first.

When should I stop executing a plan and ask for help?

Stop immediately when you hit a blocker such as a missing dependency, a failing test, an unclear instruction, or a critical gap in the plan. Ask for clarification rather than guessing, and never force through repeated verification failures.

Does this skill work without subagent support?

Yes, it is designed for sessions without subagents, but the documentation notes that platforms with subagent support such as Claude Code or Codex produce higher-quality results. In those environments, subagent-driven-development is recommended instead.

What happens after all plan tasks are completed?

After all tasks complete and pass verification, the workflow hands off to the finishing-a-development-branch skill. That step verifies tests, presents merge or cleanup options, and executes the chosen completion path.