git-stale-branch-cleanup

git-stale-branch-cleanup is a skill for Claude Code from jamesyang124/agent-skills. It costs 79 tokens per session (1,149 once invoked), scanned A, original, MIT.

A tool that finds old branches on a remote Git repository, where Git is used to track code changes. It reports branches that are behind a base branch and have exceeded a chosen age, then can optionally delete selected remote branches and local copies.

In plain words
What is it for?
Use it to review stale branches, detect possible related Jira tickets, remove obsolete remote branches, and prune their local counterparts.
Why use it?
It makes branch cleanup safer by showing a report first and using a dry-run mode by default. The live mode requires selection and confirmation before deletion.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review stale branches, detect possible related Jira tickets, remove obsolete remote branches, and prune their local counterparts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamesyang124/agent-skills/git-stale-branch-cleanup
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.

Any agent
npx skills add jamesyang124/agent-skills --skill git-stale-branch-cleanup
Clone the repo
git clone --depth 1 https://github.com/jamesyang124/agent-skills

Made for: Claude Code.

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 git-stale-branch-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesyang124/agent-skills/git-stale-branch-cleanup/github.svg)](https://agentmods.dev/skills/jamesyang124/agent-skills/git-stale-branch-cleanup)
Your own site
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/git-stale-branch-cleanup"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/git-stale-branch-cleanup/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 git-stale-branch-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/git-stale-branch-cleanup"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/git-stale-branch-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,149 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 $0.00079 $0.01149
Opus 5 $0.00039 $0.00575
Sonnet 5 $0.00016 $0.00230
Haiku 4.5 $0.00008 $0.00115

Measured 12d ago against content hash 029ad4898e14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

git-stale-branch-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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (references/delete-branch.sh, references/scan-pass-a.sh, references/scan-pass-b.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.

.agent-settings/skills/playground/git-stale-branch-cleanup/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Stale Branch Cleanup

Two modes — both always generate a full scan report before any action:

  • Dry-run (default): scan → report only, nothing deleted.
  • Live: scan → report → multi-select → confirm → delete remote → prune local.

Usage

/git-stale-branch-cleanup             # prompts for mode
/git-stale-branch-cleanup --dry-run
/git-stale-branch-cleanup --live

Arguments

All optional.

Token / flag Meaning
--dry-run scan and report only, nothing deleted (default)
--live scan, report, then multi-select and delete
a bare integer staleness threshold in days (Phase 2)
any other bare token base branch, e.g. origin/main (Phase 1)

Anything not passed is asked for in its phase prompt.


Reference Scripts

Run directly — do not regenerate these commands inline. Agent instructions are embedded in each script header; read them after running.

Script Run as
references/scan-pass-a.sh bash references/scan-pass-a.sh "$BASE_BRANCH" "$THRESHOLD_DAYS" "$SCAN_LIMIT"
references/scan-pass-b.sh bash references/scan-pass-b.sh "<branch>" "$BASE_BRANCH"
references/delete-branch.sh bash references/delete-branch.sh "<branch>"

⚠ BLOCKING: Load mode file before proceeding

If Live mode / --live: → read_file: .agent-settings/skills/git-stale-branch-cleanup/references/mode-live.md

If Dry-run / --dry-run / default: → No extra file needed — dry-run exits after Phase 4.


Phase 0 — Mode Selection

  [D] Dry-run  (default) — scan and report only, nothing deleted
  [L] Live               — scan, report, then select branches to delete

Select mode [D/L]:

Default (Enter) → Dry-run. Load mode file immediately per BLOCKING rule above.


Phase 1 — Base Branch

  [1] origin/main    (default)
  [2] origin/master
  [3] origin/develop
  [4] Other — type the branch name

Select [1-4]:

Auto-detect default via git remote show origin | grep 'HEAD branch'. Store as BASE_BRANCH. Then: git fetch --prune origin

Read the full file on GitHub · 157 lines

Files

What ships with it

4 files 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. 12d ago First seen · 157 lines · 79 tokens per session scan A 029ad4898e14

Subscribe to this mod's changes

git-stale-branch-cleanup is a skill published in the GitHub repository jamesyang124/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,149 once invoked, about $0.0004 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

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

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 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