Babysitter executing-plans

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

install

source · Clone the upstream repo

git clone https://github.com/a5c-ai/babysitter

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/superpowers/skills/executing-plans" ~/.claude/skills/a5c-ai-babysitter-executing-plans && rm -rf "$T"

manifest: library/methodologies/superpowers/skills/executing-plans/SKILL.md

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

Load persisted tasks (resume support)
Verify/setup worktree
Execute tasks in batches (default 3)
Report after each batch, wait for feedback
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