# Executing Plans

> Use when you have a written implementation plan to execute in a separate session with review checkpoints

Source: https://skillsagentes.com/skills/obra/superpowers/executing-plans
Repository: https://github.com/obra/superpowers
Author: obra
License: MIT
Updated: el mes pasado
Context cost: 26 tok installed, 576 tok once triggered, 576 tok with every bundled file
Bundle: 1 file, 2 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add obra/superpowers --skill executing-plans --agent claude-code
```

## What it does

- Carga un plan de implementación escrito y lo revisa críticamente antes de empezar
- Crea todos para cada tarea del plan y las ejecuta marcándolas in_progress/completed
- Sigue cada paso del plan exactamente, incluyendo verificaciones
- Detiene la ejecución ante bloqueos, ambigüedades o fallos repetidos de verificación
- Al terminar, invoca finishing-a-development-branch para cerrar el trabajo

## Use it when

- Tienes un plan de implementación escrito para ejecutar en una sesión separada con puntos de revisión

## Don't bother when

- Si tienes acceso a subagentes (Claude Code, Codex CLI, Codex App, Copilot CLI, Gemini CLI), usa superpowers:subagent-driven-development en su lugar

## What triggers it

- "Ejecuta este plan de implementación que escribí"
- "Sigue los pasos del plan.md y márcalos como completados"
- "Implementa las tareas de este plan con puntos de revisión"

## Before you install

- Requiere un espacio de trabajo aislado (usar using-git-worktrees) y un plan escrito ya existente.

## Files

- SKILL.md — 2 KB

## SKILL.md

Reproduced verbatim from obra/superpowers under MIT. This section is the upstream document and is in English.

# 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:** Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

## The Process

### Step 1: Load and Review Plan
1. Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one
2. Read plan file
3. Review critically - identify any questions or concerns about the plan
4. If concerns: Raise them with your human partner before starting
5. If no concerns: Create todos for the plan items and proceed

### Step 2: Execute Tasks

For each task:
1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

### Step 3: Complete Development

After all tasks complete and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice

## 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

---

Skills Agentes — https://skillsagentes.com/skills/obra/superpowers/executing-plans