Cleanup logo

Cleanup

CommunityPopular
davepoon
cleanup

Reclaim disk space and prune branches left behind by AI coding agents - merged or abandoned git worktrees, merged branches, stale build artifacts (node_modules, .venv, target), old archives and backups, package caches, and old agent session logs. Use when the user runs /cleanup, says the disk is full, or asks to clean up worktrees, branches, or storage.

Overview

Publisherdavepoon
Repositorybuildwithclaude
Skill namecleanup
Stars
3.7K
Forks
669
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by davepoon on GitHub. Read the source before you install it.

Installation

Install the Cleanup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/cleanup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davepoon/buildwithclaude.git /tmp/buildwithclaude
mkdir -p .claude/skills
cp -r /tmp/buildwithclaude/plugins/all-skills/skills/cleanup .claude/skills/cleanup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cleanup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cleanup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cleanup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cleanup

Free disk space and prune branches with one scan, one confirmation, and one apply. Every deletion goes through scripts/agent_cleanup.py in this skill's directory. Right before acting, it re-checks each git item, artifact folder, archive and the trash, and skips anything that changed since the scan.

1. Scope

Choose what to scan:

  • This repo (default): run from inside it with no --root. The scan covers this repo, the agent worktree folders (Codex, Cursor, Conductor, Vibe Kanban), package caches, agent logs and the trash.
  • Whole machine: the user says disk full, all projects, or everything. Add --root <dir> for each folder that holds their projects. Look for the usual ones (~/code, ~/dev, ~/src, ~/projects, ~/repos, ~/Developer, ~/Documents/*). If none of them exist, ask the user.

Narrow with --only git,artifacts,archives,caches,agents,trash when the user asks for one kind, e.g. "just branches" → --only git. Add --remote only when the user wants merged branches deleted on origin too.

Done when the scan command is chosen.

2. Scan

python3 <skill-dir>/scripts/agent_cleanup.py scan --fetch [--root DIR ...] [--only ...] [--remote]

The scan is read-only, apart from --fetch updating remote-tracking refs. It prints numbered items in four classes and saves the plan:

  • REMOVE: merged into the base branch, regenerable, or a worktree whose directory is already gone (unregistering it keeps its branch).
  • NEEDS-DECISION: holds something unique (uncommitted or ignored files, unmerged or unpushed commits, build output, archives, old logs).
  • KEEP-ACTIVE and SKIP: open PRs, recent work, long-lived branches, the main checkout, locked or rebasing worktrees, anything a running process is inside, unmounted drives. Never act on these.

--help lists the thresholds (--stale-days, --keep-days, --min-size).

Done when the plan is printed with its reclaimable total.

3. One confirmation

Ask once, using your multi-select question tool if you have one, otherwise a single message, then wait for the answer:

  • REMOVE, pre-selected, one line per item: id, size, path and note. When there are many, group lines by kind (worktrees, branches, artifacts, caches) and keep each id visible. Say that caches re-download on demand and artifacts come back on the next install or build.
  • Each NEEDS-DECISION item on its own line, unselected: path, size, and what is unique in it (the note). Agent logs and archives cannot be recovered once deleted.
  • Remote branches, if --remote was used, as a separate question: deleting them affects everyone using the repo.

KEEP-ACTIVE and SKIP get one summary line so the user knows they were seen.

Done when the user has answered.

4. Apply

Pass exactly the ids the user picked:

python3 <skill-dir>/scripts/agent_cleanup.py apply 1 2 5 9-14

Add --remote only when the picked ids include remote branches the user approved in their own question. apply --recommended takes every REMOVE item; use it only when the user approved all of them and nothing else.

apply prints one line per item: done, skipped (changed since the scan, gone, or now in use), refused, or failed with git's reason. Report each one as printed. Leave skipped and refused items in place; the next scan classifies them again. If the plan is more than 24 hours old, apply refuses it: scan again and confirm again.

git worktree remove refuses a worktree with uncommitted changes. Add --force only for ids where the user explicitly accepted losing those changes. A detached worktree's unique commits are saved under refs/agent-cleanup/ before removal.

Done when every picked id has a result line.

5. Report

Tell the user:

  • how much space was freed;
  • what was removed;
  • what was left and why;
  • for each agent-data item, the agent's built-in retention setting named in its note, so the logs stop piling up.

Every action is logged to ~/.local/state/agent-cleanup/history.jsonl.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cleanup AI skill do?

Reclaim disk space and prune branches left behind by AI coding agents - merged or abandoned git worktrees, merged branches, stale build artifacts (node_modules, .venv, target), old archives and backups, package caches, and old agent session logs. Use when the user runs /cleanup, says the disk is full, or asks to clean up worktrees, branches, or storage.

Why use Cleanup on TypingMind?

Because you install it once and use it with any model. Cleanup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cleanup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/cleanup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cleanup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cleanup?

As many as you like. As long as a model supports skills, you can use Cleanup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cleanup AI skill free?

Yes. It is published on GitHub by davepoon under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇