gitclean

gitclean is a skill for Claude Code, Codex from TweekFawkes/prompts. It costs 118 tokens per session (1,255 once invoked), scanned A, original, Unlicense.

A procedure for finishing a Git worktree, which is a separate working directory linked to a branch. It verifies the work, merges the branch into the main branch, and retires the finished worktree.

In plain words
What is it for?
Use it after an agent finishes a feature branch and you need to check its status, run the required tests, merge it, and move its worktree aside.
Why use it?
It reduces confusion and leftover directories after branch-based work is complete while keeping a visible record of the retired worktree.

Skill for Claude CodeCodex

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/tweekfawkes/prompts/gitclean
Any agent
npx skills add TweekFawkes/prompts --skill gitclean
Clone the repo
git clone --depth 1 https://github.com/TweekFawkes/prompts

Made for: Claude Code, Codex.

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 gitclean

README.md
[![agentmods](https://agentmods.dev/badge/skills/tweekfawkes/prompts/gitclean.svg)](https://agentmods.dev/skills/tweekfawkes/prompts/gitclean)
Your own site
<a href="https://agentmods.dev/skills/tweekfawkes/prompts/gitclean"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/gitclean.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,255 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 $0.00118 $0.01255
Opus 5 $0.00059 $0.00628
Sonnet 5 $0.00024 $0.00251
Haiku 4.5 $0.00012 $0.00126

Measured 5d ago against content hash 20e96a2ed9f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gitclean 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gitclean.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/gitclean/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gitclean

Use this skill only for a finished task branch that should be merged into the repository's main branch and then retired. The goal is to leave main current, preserve a visible retired worktree under delete_me, and reduce confusion for other local agents. For worktrees created by gitready, the default retirement path is a sibling delete_me/ directory next to the worktree.

Required Checks

  1. Read the repo's CLAUDE.md (or AGENTS.md) and follow its Git, verification, and cleanup rules.

  2. Identify the current worktree, current branch, main branch, and all local worktrees:

    git rev-parse --show-toplevel
    git branch --show-current
    git worktree list --porcelain
    git status --short
    
  3. Stop if the current branch is main, master, or detached. This skill retires feature worktrees only.

  4. Stop if this worktree or the main worktree is dirty. Review, stage, and commit intentional task changes first; never sweep unrelated files into a cleanup commit.

  5. Run the repo's required verification before merging — for example:

    bash scripts/smoke.sh   # or the repo's test suite / lint / build
    

    If that is impossible, run the strongest relevant test/lint/build checks and state exactly what could not run.

Preferred Automation

Use the bundled helper after the required checks pass:

bash .claude/skills/gitclean/scripts/gitclean.sh \
  --repo "$(pwd)" \
  --verified "bash scripts/smoke.sh"

Useful options:

  • --dry-run: print the planned merge and retirement steps without changing files.
  • --main <branch>: use a non-default main branch.
  • --no-push: merge locally but do not push main.
  • --verified <text>: record the verification command(s) that passed before cleanup.
  • --keep-branch: keep the local task branch after detaching the retired worktree.
  • --delete-remote-branch: delete the remote task branch after main is pushed. Use only when the user asked for remote branch cleanup or the repo clearly expects it.
  • --target-parent <path>: place the retired worktree under a specific delete_me parent.

Read the full file on GitHub · 130 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. 5d ago First seen · 130 lines · 118 tokens per session scan A 20e96a2ed9f2

Subscribe to this mod's changes

gitclean is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 118 tokens to every session and 1,255 once invoked, about $0.0006 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 2026-08-31.

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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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