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 Rockielab/rockie-claude --skill cleangit clone --depth 1 https://github.com/Rockielab/rockie-claudeWrote 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/rockielab/rockie-claude/clean)<a href="https://agentmods.dev/skills/rockielab/rockie-claude/clean"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/clean/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/rockielab/rockie-claude/clean"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/clean.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 | $0.00114 | $0.01216 |
| Opus 5 | $0.00057 | $0.00608 |
| Sonnet 5 | $0.00023 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00122 |
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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clean — 92% identical, 17 lines differ
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/clean — Pre-commit audit adapted for a research repo
Research repos are typically majority prose — scripts, experiment dirs,
and many .md docs read by humans AND future agents. Slop in either
kind hurts. The audit covers both.
When to run
- Before EVERY
git commit. Thepre-commit-gatehook will block if the sentinel hash doesn't match current staged state. - When the user asks to commit.
- When the hook emits a block message.
What the skill does
- Runs
${OPENCLAW_SKILLS_DIR}/clean/audit.py. Arguments:--scope staged(default) — audits files ingit diff --cached --name-only--scope dirty— audits all modified + untracked non-gitignored files
- The audit reports findings in three buckets:
- Blockers — must fix before commit (new
.mdfiles created during cleanup runs, broken internal doc links, obvious debug artifacts, syntax errors) - Warnings — should review (TODO markers pointing to resolved work,
duplicate content across docs, rules contradicting
${OPENCLAW_WORKSPACE_DIR}/memory/workflow.db) - Info — worth knowing (file size growth, complexity spikes)
- Blockers — must fix before commit (new
- If zero blockers: the audit invokes
${OPENCLAW_WORKSPACE_DIR}/scripts/clean-finalize.sh <hash>as its final action. That script writes${OPENCLAW_WORKSPACE_DIR}/.state/clean-ok-<hash>(where<hash>is computed by${OPENCLAW_WORKSPACE_DIR}/scripts/compute_clean_hash.sh) AND emits the upstream-contribute nudge to stderr. The pre-commit-gate hook recomputes the same hash and requires the sentinel to exist. - If blockers exist: the skill reports them and does NOT call
clean-finalize.sh, so no sentinel and no nudge. Agent fixes, reruns.
Hard rules for this repo specifically
- NEVER create new
.mdfiles during cleanup. Consolidate into existing ones. Exception: a user explicitly says "write a new doc for X." - NEVER auto-fix documentation. Flag it, let agent or user decide.
- NEVER audit the whole codebase. Only changed files. Existing slop elsewhere is not this commit's problem.
- Thresholds apply to NEW code only: Python funcs ≤ 80 lines, cyclomatic complexity ≤ 8. Existing violations are noise.
- Degrade gracefully: if
ruff/shellcheck/code-simplifierisn't installed, skip that check with a note. Don't block.
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.
- 10d ago First seen · 106 lines · 114 tokens per session scan A 4d447c01eaf5
clean is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,216 once invoked, about $0.0006 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 skills, from other repositories
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
spec-finish
Post-implementation completion workflow for Spec-backed Plans. Use after spec-implement completes to validate, review, create stacked commits, and open a PR via code-pull-request. Triggers only with an active Spec-backed Plan after spec-implement completes, including when the user says "finish", "done", or "complete"…