executing-plans

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

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/fred-meng/harness --skill executing-plans-fred-meng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/fred-meng/harness/tree/main/.github/skills/executing-plans
Command: npx skills add https://github.com/fred-meng/harness --skill executing-plans-fred-meng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a written implementation plan into working code often drifts off track: steps get skipped, verifications are ignored, and blockers are guessed around. 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 raises questions or concerns with your human partner before writing any code. - Task-by-Task Execution: Works through each bite-sized task, marking progress, following steps exactly, and running the specified verifications. - Stop-and-Ask Discipline: Halts immediately on blockers, unclear instructions, or repeated verification failures instead of guessing. - Use Case: You have a multi-task implementation plan written in a previous session. Hand it to this Skill in a fresh session and it will execute every task, run verifications, and finish the development branch. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/my-feature-plan.md.

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?

Provide the written plan file and invoke the executing-plans skill. It reviews the plan critically, raises concerns before starting, then executes each task in order while running the verifications specified in the plan.

What should an implementation plan contain before execution?

The plan should contain bite-sized tasks with explicit steps and verification commands. The executing-plans skill reviews the plan critically first and raises questions if anything is unclear or has critical gaps before starting work.

What happens when a task verification fails during plan execution?

The skill stops executing immediately when verification fails repeatedly, a dependency is missing, or an instruction is unclear. It asks for clarification rather than guessing or forcing through blockers.

Can I start implementation directly on the main branch?

No. The skill never starts implementation on main or master without explicit user consent, and it recommends setting up an isolated workspace using the superpowers:using-git-worktrees skill before beginning.

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

If your platform supports subagents, such as Claude Code or Codex, the skill recommends using superpowers:subagent-driven-development instead, since work quality is significantly higher with subagent support.