executing-plans

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

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/Pega88/agy-superpowers --skill executing-plans-pega88
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/Pega88/agy-superpowers/tree/main/.agents/plugins/superpowers/skills/executing-plans
Command: npx skills add https://github.com/Pega88/agy-superpowers --skill executing-plans-pega88

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often get executed inconsistently: steps get skipped, verifications are ignored, and blockers are worked around with guesses. This Skill enforces a disciplined process for loading a plan, reviewing it critically, executing every task in order, and stopping to ask for help instead of improvising. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file, identifies questions or concerns, and raises them with the human partner before any code is written. - Task Artifact Tracking: Converts plan items into a Markdown task list, marking each task in_progress and completed as work proceeds. - Verification Enforcement: Runs the verifications specified in each plan step and stops immediately when a check fails repeatedly or a blocker appears. - Use Case: You have a multi-task implementation plan written in a previous session. Use this Skill in a fresh session to execute every task exactly as specified, then hand off to the finishing-a-development-branch workflow to verify tests and complete the branch. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-auth.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 agent?

Load the plan file, review it critically for gaps or concerns, then execute each task in order while marking progress in a task artifact. Run the verifications specified per step and stop to ask for clarification when blocked rather than guessing.

What should I do before starting plan execution?

Ensure an isolated workspace such as a git worktree, read the full plan, and raise any concerns with your human partner before writing code. Never start implementation on the main or master branch without explicit user consent.

When should I use subagent-driven-development instead of executing-plans?

Use subagent-driven-development when your platform supports background subagents, such as Google Antigravity CLI, Codex CLI, Copilot CLI, or Gemini CLI. The executing-plans skill is the fallback for sessions without subagent access.

What happens when a plan step fails verification?

Stop executing immediately when a verification fails repeatedly, a dependency is missing, or an instruction is unclear. Ask your human partner for clarification instead of forcing through the blocker or guessing at a fix.

Does executing-plans work with git worktrees?

Yes, the first step requires an isolated workspace, either by creating a git worktree with the using-git-worktrees skill or verifying an existing one. This keeps plan execution separate from the main working tree.