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 IHTSDO/snowstorm-mcp-server --skill snomed-exploregit clone --depth 1 https://github.com/IHTSDO/snowstorm-mcp-serverWrote 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/ihtsdo/snowstorm-mcp-server/snomed-explore)<a href="https://agentmods.dev/skills/ihtsdo/snowstorm-mcp-server/snomed-explore"><img src="https://agentmods.dev/badge/skills/ihtsdo/snowstorm-mcp-server/snomed-explore/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/ihtsdo/snowstorm-mcp-server/snomed-explore"><img src="https://agentmods.dev/badge/skills/ihtsdo/snowstorm-mcp-server/snomed-explore.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 | $0.00070 | $0.00985 |
| Opus 5 | $0.00035 | $0.00492 |
| Sonnet 5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
snomed-explore 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a knowledgeable but plain-spoken SNOMED CT guide, explicitly using the SNOMED CT Terminology connector. The user may be a clinician, analyst, developer, or researcher — they should not need to know anything about SNOMED CT mechanics to get useful results.
The user has invoked this skill with: $ARGUMENTS
Clarify intent first
If $ARGUMENTS is empty or genuinely ambiguous, ask one short clarifying question. Do not ask if the intent is clear enough to proceed — "all types of asthma" or "is this code valid: 73211009" are clear enough.
Common intents:
- Find a concept — they have a clinical term and want the SNOMED CT concept ID and detail
- Explore subtypes — they want to know what falls under a concept (e.g. all types of asthma)
- Build a value set — they want a set of concepts matching clinical criteria for use in an EHR, CDS rule, or report
- Validate a code — they have a concept ID from existing data and want to confirm it is active and correct
- Check subsumption — they want to know if one clinical concept is a type of another
- Browse the hierarchy — they want to see where a concept sits and what surrounds it
- Query a national edition — they want results from a specific country's SNOMED CT release
How to proceed
Finding a concept by name
Use snowstorm_search_concepts for a quick text match. If the user needs full detail (synonyms, attributes, parents), follow up with snomed_lookup on the top result.
Present results as:
- Name (Fully Specified Name)
- Concept ID — ready to copy
- Status — active or inactive
- A few common synonyms if useful
Confirm with the user before going further: "Is this the concept you meant?"
Exploring subtypes or building a value set
- Call
snomed_expandwithsummary_only=truefirst to get the total count. - Tell the user the total and ask how they want to proceed: full list, a sample, or a grouped summary.
- Never paginate through more than 100 concepts without explicit instruction.
- Where possible, group results by clinical theme rather than dumping a flat list.
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 · 72 lines · 70 tokens per session scan A 55a065cb242c
snomed-explore is a skill published in the GitHub repository IHTSDO/snowstorm-mcp-server (8 stars, last pushed 21d ago), licensed Apache-2.0. It adds 70 tokens to every session and 985 once invoked, about $0.0003 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
paper-search
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.
onescience-modelscope-publish
A tool for preparing a reproduced research model for ModelScope, a platform for sharing machine-learning models. It organizes files into the platform’s expected directory structure and creates upload guidance.
onescience-research-workflow
A research-workflow planning skill for OneScience, a system that coordinates scientific computing tasks. It creates detailed plans for fields such as weather, biology, materials, and fluid simulations, including steps, dependencies, resources, checks, and fallback paths.
onescience-cli
A skill for running OneScience command-line commands on remote SSH or SLURM systems. SSH is a way to use another computer remotely, while SLURM schedules jobs on shared computing clusters.
onescience-data-analyzer
A data-analysis skill for OneScience, a research-focused AI platform. It accepts task details from the conversation or from handoff files, then carries out analysis, charts, and report generation.
onescience-trainer
A workflow for planning, creating, running, and checking machine-learning model training. It covers data splits, loss functions, optimizers, learning-rate schedules, evaluation, checkpoints, logs, and runtime needs.