worktree-cleanup

worktree-cleanup is a command for Claude Code from davila7/claude-code-templates. It costs 8 tokens per session (1,033 once invoked), scanned A, original, MIT.

A command for removing completed Git worktrees and their branches. A worktree is a separate working folder connected to another branch of the same repository.

In plain words
What is it for?
Use it to list cleanup candidates, remove merged worktrees, clean their branches, or preview the changes with a dry run.
Why use it?
It clears out branches and folders left behind after work has been merged, while offering checks for merge status and a preview mode.

Command for Claude Code

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 commands/davila7/claude-code-templates/worktree-cleanup
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-code-templates

Made for: Claude Code.

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 worktree-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/commands/davila7/claude-code-templates/worktree-cleanup.svg)](https://agentmods.dev/commands/davila7/claude-code-templates/worktree-cleanup)
Your own site
<a href="https://agentmods.dev/commands/davila7/claude-code-templates/worktree-cleanup"><img src="https://agentmods.dev/badge/commands/davila7/claude-code-templates/worktree-cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,033 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 $0.00008 $0.01033
Opus 5 $0.00004 $0.00517
Sonnet 5 $0.00002 $0.00207
Haiku 4.5 $0.00001 $0.00103

Measured 4d ago against content hash 78f0ba528fcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worktree-cleanup 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 4d 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.

.claude/commands/worktree-cleanup.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worktree Cleanup

Remove worktrees and branches that have been merged: $ARGUMENTS

Instructions

You are in the main repository (not a worktree). Clean up finished worktrees.

Branch Patterns

This project uses the following branch prefixes for worktrees:

  • claude/* — Claude Code auto-created worktrees
  • claude-daniel/* — User-created worktrees
  • review/* — Component review worktrees

All three prefixes must be checked in every step below.

Step 1: Validate Environment

  1. Verify this is the main working tree (first entry in git worktree list)
  2. If inside a worktree, warn: "Run /worktree-cleanup from the main repo, not from a worktree."
  3. Fetch latest from origin: git fetch origin --prune
  4. Get the main branch name (main or master)

Step 2: Parse Arguments

Parse $ARGUMENTS for options:

  • --all — clean up ALL merged worktrees and branches
  • --branch <prefix>/<name> — clean up a specific worktree/branch
  • --dry-run — show what would be cleaned up without doing anything
  • --force-all — remove ALL worktrees regardless of merge status (asks confirmation per worktree)
  • No arguments — list worktrees and ask which to clean up

Step 3: Identify Worktrees

  1. List all worktrees: git worktree list
  2. List all matching branches:
    git branch --list 'claude/*' 'claude-daniel/*' 'review/*'
    
  3. For each matching branch, check if it's been merged into main:
    git branch --merged origin/<main-branch> | grep -E '^\s+(claude/|claude-daniel/|review/)'
    
  4. Also check remote branches:
    git branch -r --merged origin/<main-branch> | grep -E 'origin/(claude/|claude-daniel/|review/)'
    
  5. For squash-merged branches (not detected by --merged), check if the branch diff is empty against main:
    # A branch is effectively merged if its changes already exist in main
    git diff origin/main...<branch> --stat
    
    If the diff is empty or very small (only whitespace), consider it merged.

Read the full file on GitHub · 125 lines

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. 4d ago First seen · 125 lines · 8 tokens per session scan A 78f0ba528fcc

Subscribe to this mod's changes

worktree-cleanup is a command published in the GitHub repository davila7/claude-code-templates (30,508 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,033 once invoked, about $0.0000 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.