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 zacharygcook/agent-skills --skill repo-cleanup-auditorgit clone --depth 1 https://github.com/zacharygcook/agent-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/zacharygcook/agent-skills/repo-cleanup-auditor)<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/repo-cleanup-auditor"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/repo-cleanup-auditor/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/zacharygcook/agent-skills/repo-cleanup-auditor"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/repo-cleanup-auditor.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 | $0.00060 | $0.01275 |
| Opus 5 | $0.00030 | $0.00638 |
| Sonnet 5 | $0.00012 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
repo-cleanup-auditor 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.
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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Cleanup Auditor
Use this skill for repo hygiene work where the first step should be a broad scan and a human approval checkpoint.
Core Rule
Do not move, delete, or rename anything during the first pass. First produce a cleanup audit. Apply changes only after the user explicitly approves specific actions.
If the user already approved a specific cleanup action, you may execute that action, but still inspect references and validate afterward.
First Pass: Repo Scan
Start at the repo root. If you are not sure which directory is the repo root, run git rev-parse --show-toplevel.
Inspect:
git status --short --untracked-files=all
rg --files
find . -maxdepth 3 -type d | sort
find . -maxdepth 4 -type f -empty | sort
Then use rg to check references before recommending a move, rename, or deletion. For large or binary-heavy repos, avoid exhaustive reads; sample names, manifests, READMEs, scripts, and tracked file lists first.
Classification
Classify findings into exactly these sections, in this order.
Potential Deletions
Possibly obsolete, generated, stale, duplicated, or confusing files where the evidence is not strong enough to delete without human judgment.
Use this table:
| ID | Path | Why suspicious | Evidence | Risk if deleted | Suggested action |
|---|
STRONG Candidates for Deletion
High-confidence clutter: empty folders, .DS_Store, stale generated outputs, duplicate rollups, outdated snapshots, abandoned scratch files, local temp artifacts, superseded outputs with a clearer canonical copy, or files with no references and obvious generated naming.
Use this table:
| ID | Path | Why strong | Evidence | Risk if deleted | Exact delete command |
|---|
Potential Moves
Files or folders that likely belong somewhere else, but where the destination needs human judgment.
Use this table:
| ID | Path | Current problem | Possible destination | Reason | Risk |
|---|
What ships with it
1 file 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.
- 12d ago First seen · 177 lines · 60 tokens per session scan A a8a9f6a21643
repo-cleanup-auditor is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,275 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
od-contribute
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship…
orbit-github
Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them…
diff-review
Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.
od-plugin-contribute-open-design
Open a pull request adding a local OpenDesign plugin to the OpenDesign community catalog using gh CLI.
od-plugin-publish-github
Publish a local OpenDesign plugin to a new public GitHub repository using gh CLI.
atlas-self-configure
Inspect and safely update Atlas user preferences through Atlas's config.toml.