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.
npx skills add mostafa-drz/claude-skills --skill git-cleanupgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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.
[](https://agentmods.dev/skills/mostafa-drz/claude-skills/git-cleanup)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/git-cleanup"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/git-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.
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/git-cleanup"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/git-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.02050 |
| Opus 5 | $0.00027 | $0.01025 |
| Sonnet 5 | $0.00011 | $0.00410 |
| Haiku 4.5 | $0.00005 | $0.00205 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Cleanup
Intelligently identify and remove stale branches, orphaned remotes, and unused worktrees — with confirmation at every step.
Preferences
Before starting, use the Read tool to read ~/.claude/skills/git-cleanup/preferences.md. If the file does not exist, treat as "no preferences set".
Context
On startup, use Bash to detect: working directory, git repos in cwd (directories with .git), and current git branch. Skip any that fail.
Command routing
Check $ARGUMENTS:
help→ display help then stopconfig→ interactive setup then stopreset→ delete~/.claude/skills/git-cleanup/preferences.md, confirm, stop- anything else → parse as natural language or repo path, then run
Help
Git Cleanup — Smart cleanup of stale branches, remotes, and worktrees
Usage:
/git-cleanup Auto-detect repos, clean everything
/git-cleanup ai-assemble Clean a specific repo
/git-cleanup just local branches Natural language — local only
/git-cleanup dry run Show what would be deleted
/git-cleanup skip linear Skip Linear issue checks
/git-cleanup ai-assemble remote only Clean only remote branches
/git-cleanup config Set preferences
/git-cleanup reset Clear preferences
/git-cleanup help This help
Smart detection:
- If inside a git repo, uses that repo
- If in a parent directory, scans for git repos and lets you pick
- If one repo found, uses it automatically
Current preferences:
(shown above under Preferences)
Config
Use AskUserQuestion to collect:
- Q1: Protected branches — branches to never delete (default:
main, all-demos, develop) - Q2: Linear integration — Enable Linear issue status checks? (default: Yes)
- Q3: Ticket pattern — regex to extract ticket IDs from branch names (default:
AIS-\d+) - Q4: Auto-confirm merged — Auto-delete branches already merged into base? (default: No — always ask)
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.
- 9d ago First seen · 247 lines · 54 tokens per session scan A 65514fb3049e
git-cleanup is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 26d ago), licensed MIT. It adds 54 tokens to every session and 2,050 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 2026-08-31.
Other skills, from other repositories
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
bootstrap-project
Use when setting up a new project with the full opinionated workflow — session memory, commit hooks, copyright headers, ROADMAP, and CLAUDE.md. Invoke with "bootstrap project", "setup project", "new project setup", or /bootstrap-project.
session-end
Use when the user says "end session", "wrap up", "let's stop here", or invokes /session-end.
recall
Reconstructs the development cycle from git history, distills sequential/parallel patterns, and produces actionable insights for improving future iterations. Triggers: recall, retrospective, development analysis, what happened, dev cycle analysis.
iterate
Diverge-converge workflow: spin up N agents on isolated worktrees, each exploring a different approach to the same problem. Compare results side-by-side (with optional preview ports), pick a winner, merge it back. Use when the user says /iterate, 'try multiple approaches', 'explore different directions', or wants to…
metrics
Computes development quality and velocity metrics from git history and tracks improvement over time. Measures fix ratios, rework hotspots, test coverage, DORA metrics, and code churn.