ehs-knowledge-retrieve

ehs-knowledge-retrieve is a skill for Claude Code, Codex from microsoft/cat-agent-skills. It costs 96 tokens per session (619 once invoked), scanned A, original, MIT.

A safety-information lookup step that attaches relevant OSHA criteria, ISO 45001 requirements, job hazard analyses, internal policy and similar past incidents to a reported event. OSHA is the US workplace-safety regulator, and ISO 45001 is an occupational-safety management standard.

In plain words
What is it for?
It is for checking recordability requirements, reviewing hazards for the task or area, and finding repeated incident patterns.
Why use it?
It brings the rules, task guidance and prior cases together so the incident can be assessed against documented sources.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit It is for checking recordability requirements, reviewing hazards for the task or area, and finding repeated incident patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve
About the project

microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.

microsoft/cat-agent-skills · 93 stars · on GitHub

Install

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.

Any agent
npx skills add microsoft/cat-agent-skills --skill ehs-knowledge-retrieve
Clone the repo
git clone --depth 1 https://github.com/microsoft/cat-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ehs-knowledge-retrieve

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve/github.svg)](https://agentmods.dev/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve)
Your own site
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve/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.

agentmods 80×15 button for ehs-knowledge-retrieve

Your own site · 80×15
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/ehs-knowledge-retrieve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.00619
Opus 5.5 $0.00038 $0.00248
Sonnet 5.5 $0.00019 $0.00124
Haiku 4.5 $0.00010 $0.00062

Measured today against content hash 619dd6837e1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ehs-knowledge-retrieve 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 today.

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.

submissions/safety-incident/skills/ehs-knowledge-retrieve/SKILL.md · 54 lines

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.

EHS Knowledge Retrieve

Purpose

Enrich the incident payload with grounded knowledge: the applicable OSHA 300/300A recordability criteria, the relevant ISO 45001 clauses, the JHA/HIRA for the task/area, internal EHS policy, and the area's prior similar incidents (to reveal a repeat pattern).

When to use

  • After incident-intake, in every run.
  • "Pull the OSHA criteria and the JHA" / "have we had this incident on this machine before?".

Inputs

  • incident-intake.json (contract inputs from incident-intake).
  • OSHA recordability excerpt, JHA/HIRA excerpt, EHS policy excerpt (PDF/Markdown).
  • Prior-incident log (CSV): incident_id, date, area, asset_or_area, type, body_part, outcome, recordable.

Steps

  1. Filter the prior-incident log to this asset_or_area (and body_part/type where relevant); extract each into history.prior_incidents[] with its outcome and recordable flag.
  2. Set history.window_days to the span covered and compute history.repeat_count. Set history.repeat_pattern = true when the same area/asset shows recurring similar incidents (a systemic signal, ehs-policy-excerpts.md #4).
  3. Attach retrieved OSHA criteria, ISO 45001 clauses, JHA/HIRA and policy excerpts into retrieved{}, each with a citation.
  4. Write the enriched payload back onto the contract.

Output

The contract payload with populated history{} and retrieved{} — the input to severity-recordability.

Grounding requirements

Every prior incident cites its log record ID; every criteria/clause/JHA reference cites its section or file.

Constraints

  • Retrieval only — do not classify severity or recordability here (engine/LLM split).
  • Do not infer a prior incident's recordability if the log does not state it.
  • Do not drop a prior incident that reveals a repeat pattern; surfacing it is the point.

Escalation / uncertainty

  • If the prior-incident log or JHA is unavailable, proceed on the report and OSHA criteria alone and note it in escalations[]; do not block the run.

Read the full file on GitHub · 54 lines

Files

What ships with it

6 files 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.

Changes

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.

  1. today First seen · 54 lines · 96 tokens per session scan A 619dd6837e1b

Subscribe to this mod's changes

ehs-knowledge-retrieve is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 619 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 2026-10-28.

Related

Other skills, from other repositories

fto-triage

Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…

anthropics/claude-for-legal · 81 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

terms-of-service

Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.

genspark-ai/genoffice · 32 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

ai-risk-management

Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…

briiirussell/cybersecurity-skills · 180 tokens