executing-plans

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

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/ttphats/project-detedxs26 --skill executing-plans-ttphats
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/ttphats/project-detedxs26/tree/main/.augment/skills/superpowers/executing-plans
Command: npx skills add https://github.com/ttphats/project-detedxs26 --skill executing-plans-ttphats

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often go stale or get executed inconsistently when an AI session improvises instead of following the documented steps. This Skill enforces disciplined execution of a pre-written plan in a separate session, with critical review upfront and verification after each task. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with the human partner before writing any code. - Task-by-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 immediately on blockers, unclear instructions, or repeated verification failures instead of guessing. - Use Case: You used a planning skill to write a detailed implementation plan for a new feature. In a fresh session, invoke this Skill to execute every task in order, 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-x.md, reviewing it critically first and stopping if anything is unclear.

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?▼

Invoke the executing-plans skill with the path to your plan file. The agent reviews the plan critically, raises concerns before starting, then executes each task in order with TodoWrite tracking and runs the verifications specified in the plan.

What should I do before running an implementation plan in a new session?▼

Ensure the plan is written with bite-sized steps and explicit verifications, and set up an isolated workspace such as a git worktree. The skill requires reviewing the plan critically and never starting implementation on main or master without explicit consent.

What happens when a plan step fails or is unclear?▼

Execution stops immediately when a blocker appears, such as a missing dependency, failing test, or unclear instruction. The agent asks the human partner for clarification rather than guessing or forcing through the blocker.

Does executing-plans work without subagent support?▼

Yes, it works in a single session, but the documentation notes that results are significantly better on platforms with subagent support. If subagents are available, the subagent-driven-development skill is recommended instead.

When should I revisit the plan instead of continuing execution?▼

Return to the review step when your partner updates the plan based on feedback or when the fundamental approach needs rethinking. Do not force execution through a plan with critical gaps.