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 wenhaochai/claude-plugins --skill clean-upgit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote 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/wenhaochai/claude-plugins/clean-up)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/clean-up"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/clean-up/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/wenhaochai/claude-plugins/clean-up"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/clean-up.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 | $0.00098 | $0.00906 |
| Opus 5.5 | $0.00039 | $0.00362 |
| Sonnet 5.5 | $0.00020 | $0.00181 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
clean-up 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 14d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliver the branch
The campaign branch is a record, not something to merge.
- Tag it, then cherry-pick the survivors onto the base it ran on.
git tag <campaign>-full-history HEAD. Never rewrite the campaign branch:records/candidates.jsonlreferences its shas, and every check below compares against it. - Cherry-pick, do not rebase and drop. A rejected candidate and its revert cancel out in the net diff, but a replay still applies each one.
- Ship only what changed the workload, plus the checkpoint calls, which step 6 removes again. Runners and capture harnesses stay behind, and their commands go into the reproduce block instead. Anything in the shipped source that imports a file outside the checkout is a harness, whatever it is called.
- Delete the A/B flags before you measure, not on both sides of the
deletion, and as one commit of its own. Watch for an
elsethat is another caller's entry point, and theimport osonly the flag needed. - Run the recorder comparison here, on the head with the flags hardcoded
and the checkpoint calls still in, against the setup tolerance. This is the
code that ships plus the calls that record it, so name it:
git branch <delivery>-verify HEAD. A maintainer who wants to reproduce the correctness table checks that branch out. - Strip the checkpoint calls in one last commit. Pure deletion, nothing else in it: the recorder's import, its calls and any file that exists only for them. Maintainers review the speed-up, not the instrumentation, so the delivery branch carries none. If the repo's own recorder was used, there is nothing to strip and no verify branch; say so in the handover.
- Time what ships. An interleaved timed pair on this head, with
git checkout <base> -- <src dirs>for the before arm. If something goes wrong, fix it, and redo step 5 if the fix touched the model's math.
Rename the branch to what you want merged and leave it checked out.
Move stray files out of the workspace root and update any affected paths or commands.
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.
- 14d ago Changed · +32 tokens per session ee8eb55dc948
- 17d ago First seen · 72 lines · 66 tokens per session scan A a23cb395a83f
clean-up is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 906 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.