worktree-cleanup

worktree-cleanup is a skill for Claude Code, Codex from Synaptic-Labs-AI/PACT-Plugin. It costs 57 tokens per session (1,343 once invoked), scanned A, original, MIT.

A Git cleanup helper for removing a worktree—a separate working folder connected to a branch—and that branch after the work is finished.

In plain words
What is it for?
Use it after a pull request is merged, work is consolidated, or an abandoned branch and its worktree need manual cleanup.
Why use it?
It prevents completed or abandoned worktrees from accumulating, while checking for project documents that would otherwise be lost during removal.

Skill for Claude CodeCodex

Part of the PACT plugin — 21 skills, 13 commands, 13 agents, 11 hooks 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/synaptic-labs-ai/pact-plugin/worktree-cleanup
Any agent
npx skills add Synaptic-Labs-AI/PACT-Plugin --skill worktree-cleanup
Clone the repo
git clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-Plugin

Made for: Claude Code, Codex.

Or install PACT, the plugin that ships this one along with the rest of its 21 skills, 13 commands, 13 agents, 11 hooks.

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/skills/synaptic-labs-ai/pact-plugin/worktree-cleanup.svg)](https://agentmods.dev/skills/synaptic-labs-ai/pact-plugin/worktree-cleanup)
Your own site
<a href="https://agentmods.dev/skills/synaptic-labs-ai/pact-plugin/worktree-cleanup"><img src="https://agentmods.dev/badge/skills/synaptic-labs-ai/pact-plugin/worktree-cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,343 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 $0.00057 $0.01343
Opus 5 $0.00028 $0.00672
Sonnet 5 $0.00011 $0.00269
Haiku 4.5 $0.00006 $0.00134

Measured 5d ago against content hash 2600ae7e576f, 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 5d 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.

pact-plugin/skills/worktree-cleanup/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worktree Cleanup

Remove a git worktree and its associated branch after work is complete. Typically invoked after a PR is merged, after CONSOLIDATE merges sub-scope branches, or manually by the user.

When to Use

  • After peer-review merges a PR (automatic cleanup)
  • After CONSOLIDATE merges sub-scope branches
  • Manual cleanup of stale worktrees (/PACT:worktree-cleanup)
  • User aborts a workflow and wants to clean up

Process

Follow these steps in order. Surface all git errors clearly — the user resolves them.

Step 1: Identify Target

Determine which worktree to remove.

If a worktree path or branch name was provided: Use that directly.

If no target was specified: List all worktrees and ask the user which to clean up.

git worktree list

Present the list and ask: "Which worktree should I remove?"

Step 1.5: Harvest docs/ Artifacts Before Teardown

git worktree remove deletes the worktree's docs/ directory irrecoverably — that directory is gitignored and worktree-ephemeral, so the phase artifacts it holds (docs/preparation/, docs/architecture/, docs/plans/, docs/review/, docs/decision-logs/) are gone the instant the worktree is removed. Those artifacts are the fuller substance behind each phase's distilled HANDOFF. This step is the single chokepoint that protects them for all teardown callers — peer-review auto-cleanup, CONSOLIDATE sub-scope early-teardown, and manual /PACT:worktree-cleanup alike — so harvest MUST precede remove.

Glob the target worktree's docs/ for artifacts, then apply this conditional guard:

  • Artifacts exist AND a secretary/team is reachable (the normal workflow-driven teardown): trigger a secretary harvest of the worktree's docs/ artifacts and confirm it completes before proceeding to Step 2. The secretary reads + distills each artifact into pact-memory (its pact-handoff-harvest Step 3.5 resolves artifact_paths events and reads the disk artifacts while the worktree is still live — this guard is what guarantees that liveness). Do NOT remove the worktree until the harvest is confirmed done.
  • Artifacts exist but no secretary/team is reachable (e.g. a manual cleanup in a fresh session with no active team): do NOT silently delete. Surface a loud warning that the worktree's docs/ artifacts have NOT been harvested and will be irrecoverably deleted by removal, and let the user decide whether to proceed, harvest manually first, or abort.
  • No docs/ artifacts in the worktree: nothing to protect — proceed directly to Step 2.

Read the full file on GitHub · 121 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. 5d ago First seen · 121 lines · 57 tokens per session scan A 2600ae7e576f

Subscribe to this mod's changes

worktree-cleanup is a skill published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,343 once invoked, about $0.0003 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens