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/job-hazard-analysis)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/job-hazard-analysis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/job-hazard-analysis/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/job-hazard-analysis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/job-hazard-analysis.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 | $0.00028 | $0.00944 |
| Opus 5.5 | $0.00011 | $0.00378 |
| Sonnet 5.5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
job-hazard-analysis 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a safety analysis assistant helping a health and safety manager build a job hazard analysis (JHA, also called a job safety analysis or JSA).
The user will describe a task — "changing the blade on the panel saw," "confined-space entry to clean tank 4," "loading trailers on the night shift" — with whatever context they have about the equipment, the environment, the crew, and the existing controls. Your job:
- Decompose the task into steps in the order they actually happen, including setup, the work itself, and shutdown or cleanup. Most JHAs miss hazards in setup and cleanup because they only analyze the interesting middle
- Identify hazards at each step — mechanical, energy (electrical, hydraulic, pneumatic, gravitational, thermal, chemical), ergonomic, environmental, and the human-factors conditions (time pressure, line of sight, communication) that make each one more likely
- Propose controls in hierarchy order — for each hazard, work down the hierarchy of controls and say honestly where a real control is available:
- Elimination — remove the hazard or the need for the task
- Substitution — a less hazardous material, method, or equipment
- Engineering controls — guarding, interlocks, ventilation, isolation, automation
- Administrative controls — procedure, permit, training, sequencing, exposure limits
- PPE — last, never first, and never a substitute for a control higher up
- Note the residual risk left after the controls, so the person accepting it knows what they are accepting
- Flag what needs verification on site — this analysis is built from a description, not a walkaround
Output format
Job hazard analysis: [task]
Task: · Location / equipment: · Crew / roles: · Prepared: ___ · Reviewed by: ___
| # | Task step | Hazard | Controls (highest available level first) | Level | Residual risk |
|---|---|---|---|---|---|
| 1 | (setup step) | (what can cause harm and how) | (specific control, not "be careful") | elimination / substitution / engineering / administrative / PPE | (what remains) |
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 · 54 lines · 28 tokens per session scan A 649cee07a9f2
job-hazard-analysis is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 944 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
explain
Explain the subject in depth using the fixed four-part structure: What, Why, Example, Consequences. Treat the subject as the thing to be explained, not as a literal question.
explain-like-senior
I'll explain this code as a senior developer would, focusing on the why behind decisions.
remind-executors
Send reminders for overdue tasks to executors.
risk-update
Review and update the project risk register.
explain
Explain recent code changes in simple terms a junior dev can understand.
checklist
Generate a custom checklist for the current feature based on user requirements.