agentmods.dev

cleanup-worktrees

cleanup-worktrees is a skill for Claude Code from paulbaranowski/wild-horses. It costs 104 tokens per session (2,454 once invoked), scanned A, original, MIT.

A command-line tool for finding stale Git worktrees, which are extra working copies of a repository, and removing the ones judged safe. It skips worktrees with uncommitted, locked, or unpushed changes.

In plain words
What is it for?
Use it to configure scanned repositories, list worktrees and their status, set the stale threshold, and remove selected worktrees after validation.
Why use it?
It helps reclaim disk space while protecting active or unfinished work. Its JSON output also makes results easier for other tools to process reliably.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/you/grafts/carrot/CAT-39996-....

Part of the cleanup-worktrees plugin — 1 skill, 1 hook shipped together

not rated 12repo +1 22d ago A scan 104 tokens original MIT

Good fit Use it to configure scanned repositories, list worktrees and their status, set the stale threshold, and remove selected worktrees after validation.

Compare 6 skills from other repositories ↓
View source ↗ paulbaranowski/wild-horses
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add paulbaranowski/wild-horses
Claude Code
/plugin install cleanup-worktrees

Made for: Claude Code.

Or install cleanup-worktrees, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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 cleanup-worktrees

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/cleanup-worktrees/github.svg)](https://agentmods.dev/skills/paulbaranowski/wild-horses/cleanup-worktrees)
Your own site
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/cleanup-worktrees"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/cleanup-worktrees/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cleanup-worktrees

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/cleanup-worktrees"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/cleanup-worktrees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00104 $0.02454
Opus 5 $0.00052 $0.01227
Sonnet 5 $0.00021 $0.00491
Haiku 4.5 $0.00010 $0.00245

Measured 10d ago against content hash 0c12aa9474a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cleanup-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 10d 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.

plugins/cleanup-worktrees/skills/cleanup-worktrees/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cleanup-worktrees

Reclaim disk space from git worktrees that are safe to delete. The bundled CLI discovers worktrees under configured roots, classifies each, and removes the ones you select - re-validating before every removal, never --force, and never touching a worktree with uncommitted, locked, or unpushed work.

Quick reference

  • Config: ~/.config/wild-horses/cleanup-worktrees/config.json - {"repos": [{"path": "..."}], "parents": [{"path": "...", "depth": 1}], "stale_days": 30, "last_confirmed_at": "..."}. repos are direct repo paths; parents are dirs whose subdirs are auto-scanned (depth = levels to descend, default 1).
  • CLI: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cleanup_worktrees_cli.py" <subcommand>
  • Subcommands: scan, remove --paths P1 [P2 ...], config list, config add-repo PATH, config add-parent PATH [--depth N], config remove PATH, config set-stale-days N, config confirm
  • Every subcommand prints JSON on stdout. Parse it; do not screen-scrape.
  • Exit codes: 0 means the command itself succeeded (per-worktree outcomes live inside the JSON); non-zero means a CLI-level error (bad path, corrupt config, a path outside $HOME).
  • Cleanable reasons: pr-merged, pr-closed, upstream-gone, merged-to-default, stale. Skip reasons: dirty, locked, unpushed (never removed).

Procedure

1. First-run confirm

Run:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cleanup_worktrees_cli.py" config list
  • Empty config (no repos and no parents): there is nothing to scan yet. Tell the user and ask which roots to track. Add direct repos with config add-repo PATH and parent dirs with config add-parent PATH [--depth N] (use --depth 3 for nested layouts like emdash/worktrees/<repo>/<harness>/<branch>). Then run config confirm and continue to step 2.
  • last_confirmed_at is null, or the resolved roots changed since you last confirmed: print the repos and parents paths and ask the user to confirm them with a single yes/no. On yes, run config confirm. On no, adjust with config add-* / config remove, then config confirm.
  • Already confirmed and roots unchanged: skip straight to step 2.

Read the full file on GitHub · 108 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. 10d ago First seen · 108 lines · 0 tokens per session scan A 0c12aa9474a2

Subscribe to this mod's changes

cleanup-worktrees is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 22d ago), licensed MIT. It adds 104 tokens to every session and 2,454 once invoked, about $0.0005 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.

Git and workflow
Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens