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 alexei-led/cc-thingz --skill cleanup-gitgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/cleanup-git)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/cleanup-git"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/cleanup-git/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/alexei-led/cc-thingz/cleanup-git"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/cleanup-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01013 |
| Opus 5.5 | $0.00028 | $0.00405 |
| Sonnet 5.5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
cleanup-git 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 15d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup Git
Use the target repo's own scripts/cleanup-git.sh if it ships one, otherwise this skill's script. Inspect a repo-provided script before relying on its safety policy. Use direct deletion only for a specifically approved exception described below; never pipe a branch list into force-delete.
scripts/cleanup-git.sh # preview (default)
scripts/cleanup-git.sh --apply # execute the requested safe cleanup
scripts/cleanup-git.sh --apply --force --branch <name> # approved ahead-commit loss
scripts/cleanup-git.sh --base <ref> # override base detection
The script fetches and prunes remotes. It prefers the fetched remote default branch, then remote main, master, trunk, develop, or dev, then local fallbacks. --base overrides this choice.
What the script decides
A branch or its worktree is a candidate when one of these holds:
PR merged: GitHub confirms the PR in the target repository and base, and its merge commit is reachable from the base. This catches squash, conflict-resolved squash, and rebase merges; ahead commits count only past the PR head.merged: the branch is an ancestor of the base.squash merged: the complete branch patch is equivalent to a commit in the base. This works offline withoutgh; conflict resolution can prevent equivalence.upstream gone: only a candidate signal, not merge proof. Unique commits still keep the branch.
It skips the current worktree, current branch, base, and main/master/trunk/develop/dev. It keeps locked worktrees and worktrees with tracked, untracked, or ignored files, or unknown status. It keeps candidates with ahead commits or unknown ahead counts unless --force --branch <name> is passed for one approved target. No proof prints skip ... (active); do not treat that as proof of unmerged work.
Workflow
- Run the preview and show the safe removals and kept objects.
- An explicit cleanup request authorizes
--applyfor verified safe candidates. Run it without another confirmation; kept objects do not block safe removals. For a preview-only request, do not apply. - Report what was removed and what remains. Do not ask about every kept object unless the user wants it removed. For a risky exception, show the exact branch/path, full tip OID, unique commits, and uncommitted files (including ignored files), then ask once for permission to discard them. A reply such as “I allow it” authorizes only that described scope; execute it yourself rather than telling the user to run it.
What ships with it
2 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.
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.
- 15d ago Changed · +21 lines df38a5563edf
- 22d ago Changed · -44 lines d0e01b4f81e2
- 1mo ago First seen · 94 lines · 70 tokens per session scan A 703b8e34acc5
cleanup-git is a skill published in the GitHub repository alexei-led/cc-thingz (38 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 1,013 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.