worktree-cleanup

A cleanup command for Git worktrees, which are separate working folders for different branches of one repository.

In plain words
What is it for?
Find merged worktrees, verify branch and pull-request status, identify stale copies, and remove them after the relevant checks.
Why use it?
It helps remove stale folders after branches or pull requests have been merged while checking that cleanup is safe. It can also consolidate related settings before removal.

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/wbern/agent-instructions/worktree-cleanup
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00021 $0.03323
Opus 5 $0.00010 $0.01662
Sonnet 5 $0.00004 $0.00665
Haiku 4.5 $0.00002 $0.00332

Measured 2d ago against content hash d897ede42f48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

worktree-cleanup scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

<read_worktree_settings>{worktree_path}/.claude/settings.local.json</read_worktree_settings>
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/worktree-cleanup.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worktree Cleanup

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

Clean up merged worktrees by finding the oldest merged branch, consolidating settings, and removing stale worktrees.

User arguments:

Worktree-cleanup: $ARGUMENTS

End of user arguments

<current_state> Current branch: git branch --show-current Current worktrees: git worktree list </current_state>

<execution_steps> <step_0> Detect git hosting provider and available tools

<detect_provider> <check_remote_url>git remote get-url origin</check_remote_url> <identify_host> - github.com → GitHub - gitlab.com → GitLab - bitbucket.org → Bitbucket - Other → Ask user </identify_host> </detect_provider> <check_available_tools> <list_mcp_servers>Check which git-hosting MCP servers are available (github, gitlab, etc.)</list_mcp_servers> <check_cli>Check if gh/glab CLI is available as fallback</check_cli> </check_available_tools> <select_tool> <if_single_mcp>If only one relevant MCP available, confirm with user</if_single_mcp> <if_multiple>Let user choose which tool to use</if_multiple> <if_told_earlier>If user specified tool earlier in conversation, use that without asking again</if_told_earlier> <store_as>$GIT_HOST_TOOL (e.g., "github_mcp", "gitlab_mcp", "gh_cli")</store_as> </select_tool>

Detect git hosting provider and select appropriate tool for PR verification </step_0>

Read the full file on GitHub · 271 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. 2d ago First seen · 271 lines · 21 tokens per session scan B d897ede42f48

Subscribe to this mod's changes

worktree-cleanup is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 3,323 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.