executing-plans

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

509 stars

Best use case

executing-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using executing-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/executing-plans/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/superpowers/skills/executing-plans/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/executing-plans/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How executing-plans Compares

Feature / Agentexecuting-plansStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Executing Plans

## Overview

Load plan, review critically, execute tasks in batches, report for human review between batches. Supports resume via `.tasks.json` persistence.

**Core principle:** Batch execution with checkpoints for architect review.

## When to Use

- You have a written implementation plan on disk
- Executing in a separate/parallel session
- Want human checkpoints between task batches

## Process

1. Load persisted tasks (resume support)
2. Verify/setup worktree
3. Execute tasks in batches (default 3)
4. Report after each batch, wait for feedback
5. Finish branch after all tasks complete

## Agents Used

- Process agents defined in `executing-plans.js`
- References `using-git-worktrees` for workspace isolation
- References `finishing-a-development-branch` for completion

## Tool Use

Invoke via babysitter process: `methodologies/superpowers/executing-plans`