git-cleanup

A cleanup workflow for local Git worktrees and branches linked to closed pull requests or branches that have not changed for a chosen period. Git worktrees are extra working folders connected to one repository.

In plain words
What is it for?
Use it to inspect worktrees and branches, check pull-request status, identify stale branches, and remove them after confirmation.
Why use it?
It helps remove old local copies and branches that clutter a repository after work is merged or abandoned.

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/wrannaman/agentic-engineering/git-cleanup
Any agent
npx skills add wrannaman/agentic-engineering --skill git-cleanup
Clone the repo
git clone --depth 1 https://github.com/wrannaman/agentic-engineering

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 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 $0.00018 $0.01825
Opus 5 $0.00009 $0.00912
Sonnet 5 $0.00004 $0.00365
Haiku 4.5 $0.00002 $0.00183

Measured 2d ago against content hash 44a10235dcf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-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 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.

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/git/git-cleanup/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Cleanup

Clean up local git worktrees and branches that are no longer needed. Identifies branches with closed PRs and stale branches, then removes them after user confirmation.

When to Use

  • When your repo has accumulated many old branches
  • After merging/closing multiple PRs
  • Periodic maintenance to keep your local repo clean

Arguments

Argument Default Description
--stale-weeks N 4 Branches with no commits in more than N weeks (N*7 days) are considered stale. Default 4 = 28 days. Set to 0 to disable stale detection.

Process

Step 1: Gather Information

Run these commands to understand the current state:

# List all worktrees
git worktree list

# List all local branches with last commit date
git for-each-ref --sort=-committerdate refs/heads/ --format='%(refname:short)|%(committerdate:iso8601)|%(committerdate:relative)'

# Get the default branch
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'

# Get current branch
git branch --show-current

For each local branch (except protected ones), check its PR status:

# Check if branch has any PRs (open, closed, or merged)
gh pr list --head <branch-name> --state all --json number,state,headRefName --limit 1

Step 2: Categorize Branches

Create four categories:

  1. Protected branches (NEVER delete):

    • main
    • master
    • develop
    • production
    • The default branch (from Step 1)
    • The current branch
  2. Closed PR branches (mark for deletion):

    • Branches where the most recent PR is CLOSED or MERGED
  3. Stale branches (mark for deletion):

    • Branches with NO PR (empty result from gh pr list) AND last commit older than threshold
    • Threshold calculation: stale_weeks * 7 days. Default is 4 weeks = 28 days.
    • A branch is stale ONLY if: (today - last_commit_date) > (stale_weeks * 7 days)
    • Example: With default 4 weeks, a branch with last commit 7 days ago is NOT stale (7 < 28)
    • Example: With default 4 weeks, a branch with last commit 30 days ago IS stale (30 > 28)

Read the full file on GitHub · 244 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 · 244 lines · 18 tokens per session scan A 44a10235dcf3

Subscribe to this mod's changes

git-cleanup is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,825 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens