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 mhmdreza-rafiei/agent-tools --skill cleanupgit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/cleanup)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/cleanup"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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/mhmdreza-rafiei/agent-tools/cleanup"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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 | $0.00076 | $0.00702 |
| Opus 5.5 | $0.00030 | $0.00281 |
| Sonnet 5.5 | $0.00015 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cleanup
A focused tech-debt cleanup pass. /review checks new code for quality;
/cleanup hunts the old debt that's already in the tree — dead code, dup
helpers, stale deps, drift from the project's own conventions — and removes
it safely.
When to use
When the user says "clean up", "reduce tech debt", "dead code sweep"; on
/cleanup; before a release; after a big refactor.
Commands
/cleanup— scan the whole repo (or the touched area)./cleanup <area>— focus one area (e.g./cleanup src/auth)./cleanup --dry-run— list findings, remove nothing.
Step 1 — Scan for debt
Hunt, with grep/AST where useful:
- Dead code — unexported, uncalled functions/modules; unreachable branches.
- Duplicate helpers — same logic in 2+ places; pick the canonical one.
- Stale deps — declared but not imported; versions behind.
- Unused exports — exported but no external consumer.
- Convention drift — paths/naming that violate
files-folders-structure; code style that violates the project's own pattern.
Step 2 — For each finding, classify
- Safe — remove, no behavior change (dead code, unused export).
- Risky — remove after verifying no dynamic use (string-path imports, eval, reflection).
- Don't — keep, note why (compat shim, public API).
Step 3 — Ordered removal plan
Produce an ordered list: safe removals first (one commit), risky removals after verification (one commit each), and a "keep" list with reasons.
Output
## Cleanup plan
### Safe (one commit)
- remove <path> — <why safe>
### Risky (one commit each)
- remove <path> — verify: <what to check first>
### Keep
- <path> — <why kept, e.g. compat shim>
Constraints
- Never remove on assumption — grep for dynamic/string-path uses first.
- One commit per risky removal so a revert is one command.
- Follow
rule/global/migration: update references before removing old. - Follow
rule/global/git-workflow: ask before any destructive removal.
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.
- 1mo ago First seen · 79 lines · 76 tokens per session scan A 4b7c59de0edd
cleanup is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 15d ago), licensed MIT. It adds 76 tokens to every session and 702 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…