claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.
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 agentmods add commands/alirezarezvani/claude-skills/cleangit clone --depth 1 https://github.com/alirezarezvani/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/commands/alirezarezvani/claude-skills/clean)<a href="https://agentmods.dev/commands/alirezarezvani/claude-skills/clean"><img src="https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/clean.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00390 |
| Opus 5 | $0.00010 | $0.00195 |
| Sonnet 5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
clean scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Clean up stale branches that have been merged or are no longer needed.
Steps
- List local branches to delete (excluding
main,dev,gh-pages):
git branch | grep -v -E '^\*|main$|dev$|gh-pages$'
Report what will be deleted. If no branches found, say "No local branches to clean" and skip to step 3.
- Delete local branches that are fully merged:
git branch -d <branch-name>
If a branch is not fully merged, report it to the user and ask whether to force-delete. Do NOT force-delete without confirmation.
- List remote branches to delete (excluding
main,dev,gh-pages,HEAD):
git branch -r | grep -v -E 'origin/main$|origin/dev$|origin/gh-pages$|origin/HEAD'
Report what will be deleted. If no branches found, say "No remote branches to clean" and skip to step 5.
- Confirm with the user before deleting remote branches. Show the full list and wait for approval. Then delete:
git push origin --delete <branch-names>
- Prune stale remote refs:
git remote prune origin
- Report final state:
git branch # local
git branch -r # remote
Present a summary:
| Item | Count |
|---|---|
| Local branches deleted | N |
| Remote branches deleted | N |
| Remaining local | main, dev |
| Remaining remote | origin/main, origin/dev, origin/gh-pages |
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.
- 6d ago First seen · 60 lines · 19 tokens per session scan A 03ed9e5e4f25
clean is a command published in the GitHub repository alirezarezvani/claude-skills (25,582 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 390 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 2026-08-30.
Other commands, from other repositories
story-continue
Resume an interrupted story from where you left off.
post
Post the current OCR review to a GitHub PR.
history
List past OCR review sessions.
help
Display the following help text to the user.
growth-landing
Create or optimize an effective landing page.
growth-retention
Analyzes and improves user retention with data-driven strategies.