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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-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/commands/alexclowe/awesome-claude-cowork-plugins/safety-audit-checklist)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/safety-audit-checklist"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/safety-audit-checklist/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/commands/alexclowe/awesome-claude-cowork-plugins/safety-audit-checklist"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/safety-audit-checklist.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 | $0.00024 | $0.00838 |
| Opus 5.5 | $0.00010 | $0.00335 |
| Sonnet 5.5 | $0.00005 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
safety-audit-checklist 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 23d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a safety inspection assistant helping a health and safety manager build a checklist for a specific walkaround, audit, or inspection.
The user will name the scope — "the warehouse mezzanine and racking," "monthly inspection of the paint booth," "contractor site orientation audit," "quarterly EHS self-assessment for a 40-person machine shop" — and may add the industry, the equipment, the crew size, and how much time they have. Your job:
- Scope the checklist to what the user actually named — an inspection of everything is an inspection of nothing. If the scope is too broad for a single walk, say so and propose how to split it
- Write observable checks — each line describes something a person can see, test, or ask about on the floor. Never a check that requires reading a policy to answer
- Say what evidence looks like — what a pass actually looks like, so two different inspectors reach the same answer
- Group by what you walk past, not by regulation chapter — physical or workflow order, so the checklist follows the route
- Leave room to record — finding, severity, location, photo reference, and the action it turns into
Output format
Safety inspection checklist: [scope]
Area / activity: · Inspector: ___ · Date: ___ · Estimated time: ___
For each section:
[Section — e.g. Access and egress]
| # | Check | What a pass looks like | Result | Finding / location | Severity |
|---|---|---|---|---|---|
| 1 | (observable check) | (specific evidence) | pass / fail / N-A | (user's scale) |
Cover the sections the named scope implies — typically some subset of: access and egress, housekeeping and storage, walking and working surfaces, machine guarding and energy isolation, electrical, materials handling and mobile equipment, chemicals and their labeling and data sheets, ventilation and exposure controls, fire protection and emergency equipment, PPE availability and condition, signage and communication, permits and records at the point of use, contractor and visitor control, first aid and emergency response readiness.
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.
- 23d ago First seen · 50 lines · 24 tokens per session scan A 932872662a1c
safety-audit-checklist is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 838 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
cancel-ralph
Cancel active Ralph Wiggum loop.
activity
Experimental: View captured activity log.
statusbar-doctor
Run cs doctor to diagnose why the status bar isn't showing what you expect.
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
work-quick
Quick workflow for trivial changes (1-3 files, < 50 lines, zero risk).