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 littleblakew/msds-chain-mcp --skill msds-safety-checkgit clone --depth 1 https://github.com/littleblakew/msds-chain-mcpWrote 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/littleblakew/msds-chain-mcp/msds-safety-check)<a href="https://agentmods.dev/skills/littleblakew/msds-chain-mcp/msds-safety-check"><img src="https://agentmods.dev/badge/skills/littleblakew/msds-chain-mcp/msds-safety-check/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/littleblakew/msds-chain-mcp/msds-safety-check"><img src="https://agentmods.dev/badge/skills/littleblakew/msds-chain-mcp/msds-safety-check.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 | $0.00034 | $0.00763 |
| Opus 5 | $0.00017 | $0.00381 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
msds-safety-check 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MSDS Safety Check
Chemical safety intelligence powered by MSDS Chain. Provides compatibility checks, PPE recommendations, storage guidance, regulatory compliance, and signed audit reports for lab workflows.
When to Use
Automatically triggered when the user's message contains:
- Chemical names (e.g., Acetone, HCl, Sulfuric acid, 硫酸, アセトン)
- CAS numbers (e.g., 67-64-1, 7647-01-0)
- Lab protocol keywords (protocol, experiment, reagent, mixture, dilution, 配制, 混合, 稀释)
- EHS keywords (compliance, SDS, MSDS, hazard, PPE, safety data sheet)
Manually triggered via /msds-safety-check for full guided audit.
How It Works
This skill orchestrates MSDS Chain's 23 MCP tools. It requires the msds-chain MCP server to be configured. If not configured, it will guide the user through setup (see rules/setup-guide.md).
Two Modes
-
Auto-detect mode — When chemicals are detected in context, prompt the user: "Detected chemicals in your content. Run a safety check?" If confirmed, run a quick scan and output a concise safety brief. Details in rules/auto-detect.md.
-
Full audit mode (
/msds-safety-check) — Guide the user through chemical input, check type selection, and produce a detailed report. Two workflows:- Lab Protocol Audit (for researchers): rules/lab-protocol-audit.md
- EHS Compliance Review (for compliance officers): rules/compliance-review.md
Output Formats
Output adapts to context — concise for auto-detect, detailed for manual audit. See rules/output-formats.md.
Tool Call Principles
- Minimum calls first: Use
batch_safety_checkfor one-shot pairwise results (compatibility + per-chemical risk warnings). It does NOT cover PPE or storage grouping — callget_ppe_recommendation/get_storage_guidancewhen the user needs those. - Progressive disclosure: Only call
get_emergency_response,check_mixing_order, orget_chemical_alternativeswhen the user asks follow-up questions. - Freemium upgrade: Audit tools (
create_audit_session,get_audit_report,upload_msds_pdf) require an API key. Prompt for registration only when the user requests audit functionality, not during basic queries.
What ships with it
5 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.
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.
- 11d ago First seen · 51 lines · 34 tokens per session scan A 456a5b9183a8
msds-safety-check is a skill published in the GitHub repository littleblakew/msds-chain-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 763 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
radiology-ethics
Write compliant, non-overstated Ethics, Informed-Consent, and privacy/governance text for imaging and imaging+omics studies — study-type framing (retrospective, prospective, registered, multi-center), IRB/ethics-committee approval and numbers, consent vs documented waiver, re-identification risk (DICOM metadata…
radiology-data
Prepare and audit Data/Code Availability statements, DICOM de-identification plans, repository selection, dataset citations, and FAIR/sharing checks for Radiology (RSNA) and Nature-portfolio imaging+omics submissions. Use when the user needs a data availability statement, must de-identify DICOM imaging, choose a…
clinical-trial-logistics
When the user wants to optimize clinical trial supply chain, manage investigational products, implement IRT systems, or ensure GCP compliance. Also use when the user mentions "clinical trial supply," "IMP logistics," "IVRS/IWRS," "drug accountability," "randomization and supply," "comparator sourcing," "depot…
fea-workflow
FEA post-processing workflow skill. Guides AI agents through finite element analysis visualization: stress distribution, deformation, mode shapes, and yield detection. Maps FEA domain vocabulary to viznoir MCP tool calls. Triggers: FEA, structural, stress, deformation, displacement, von Mises, yield, mode shape, 응력…
contract-review-workflow
Trigger a deployed Mistral Workflow for contract review, poll execution status, detect human-in-the-loop checkpoints via workflowinteract(query), collect approval or changes, and resume the workflow via workflowinteract(signal). Use when the user wants to run a contract through a Mistral Workflow with oversight…
math-paper
A role guide for writing and checking mathematical modelling papers, including evidence gathering, source verification, and final review. It is designed for teams that coordinate work through separate repository folders.