git-clean-worktrees

git-clean-worktrees is a skill for Claude Code from ivy00johns/Skill-Madness. It costs 177 tokens per session (1,484 once invoked), scanned A, original, MIT.

A procedure for finding and removing old Git worktrees after their branches have already been merged into the main branch.

In plain words
What is it for?
Use it to inspect worktrees, determine whether their work is already merged or safely removable, and clean up secondary worktrees.
Why use it?
It prevents completed worktrees from looking like unfinished changes and reduces clutter in a repository.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the skill-madness plugin — 56 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ivy00johns/skill-madness/git-clean-worktrees
Any agent
npx skills add ivy00johns/Skill-Madness --skill git-clean-worktrees
Clone the repo
git clone --depth 1 https://github.com/ivy00johns/Skill-Madness

Made for: Claude Code.

Or install skill-madness, the plugin that ships this one along with the rest of its 56 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for git-clean-worktrees

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivy00johns/skill-madness/git-clean-worktrees.svg)](https://agentmods.dev/skills/ivy00johns/skill-madness/git-clean-worktrees)
Your own site
<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/git-clean-worktrees"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/git-clean-worktrees.svg" alt="Measured on agentmods" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.01484
Opus 5 $0.00088 $0.00742
Sonnet 5 $0.00035 $0.00297
Haiku 4.5 $0.00018 $0.00148

Measured 6d ago against content hash 2a44fd4524f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

git-clean-worktrees scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/archive/git-clean-worktrees/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Worktrees

Systematically find and remove git worktrees whose work is already on the main branch. The core problem this solves: worktrees created during feature work persist after the branch is merged, showing "modified" files that are actually already committed — creating confusion about what's merged and what isn't.

Why This Happens

Worktrees are created for isolation during feature work. When the branch gets merged (squash-merge, regular merge, or cherry-pick), the worktree doesn't disappear. It still has the branch checked out, and git status inside it shows modifications relative to the worktree's HEAD — but those changes are already on main. The worktree is stale but looks active.

Workflow

Step 1: List all worktrees

git worktree list

Identify the main worktree (the repo root) — it must never be removed. Everything else is a candidate for cleanup.

If there's only the main worktree, report "No secondary worktrees found" and stop.

Step 2: For each secondary worktree, determine if it's stale

Run these checks in order. A worktree is safe to remove if ANY of these conditions is true:

Check A: Branch is merged into main
git branch --merged main | grep -q <branch-name>

If the branch appears in --merged, all its commits are reachable from main. Safe to remove.

Check B: Squash-merged (branch not technically merged, but diff is empty)

Squash merges don't show up in --merged because git sees different commit hashes. Check if the branch's changes are already on main by comparing the trees:

git diff main...<branch-name> --stat

If this produces no output (empty diff), the branch's content is identical to main. Safe to remove.

Check C: Worktree has uncommitted changes that match main

If the worktree has uncommitted modifications, check whether those changes already exist on main:

# List uncommitted changes in the worktree
git -C <worktree-path> status --porcelain

# For each modified file, check if main already has those changes
git diff main -- <file-path>

Read the full file on GitHub · 199 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 199 lines · 177 tokens per session scan A 2a44fd4524f4

Subscribe to this mod's changes

git-clean-worktrees is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 26d ago), licensed MIT. It adds 177 tokens to every session and 1,484 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens