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 nickzren/biomed-agent --skill biomed-researchgit clone --depth 1 https://github.com/nickzren/biomed-agentWrote 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/nickzren/biomed-agent/biomed-research)<a href="https://agentmods.dev/skills/nickzren/biomed-agent/biomed-research"><img src="https://agentmods.dev/badge/skills/nickzren/biomed-agent/biomed-research/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/nickzren/biomed-agent/biomed-research"><img src="https://agentmods.dev/badge/skills/nickzren/biomed-agent/biomed-research.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 | $0.00039 | $0.00464 |
| Opus 5 | $0.00019 | $0.00232 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
biomed-research 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 12d 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.
What it actually says
Biomed Research
Use this workflow for biomedical research answers over the five local MCP servers.
Server Routing
| Need | Start With |
|---|---|
| target-disease evidence, drugs, variants, studies, trials | opentargets |
| phenotypes, HPO, rare disease, model organisms | monarch |
| gene annotation, IDs, expression, GO, orthologs | mygene |
| chemical/drug identifiers, mechanisms, structures | mychem |
| disease annotation, OMIM, Orphanet, MONDO, HPO | mydisease |
Resolve names to stable IDs first. Use the narrowest server that can answer the question. Fan out only when the question spans multiple entity types.
Evidence Rules
- Prefer curated MCP tools over raw schema queries.
- Use source-backed observations before synthesis.
- Keep result payloads small by requesting specific fields when tools support it.
- Reconcile conflicts explicitly instead of averaging them away.
- Stop after 1-2 follow-up rounds if gaps remain; report the limitation.
Output Contract
Return:
answer: concise biomedical synthesis.confidence:high,medium, orlow.citations: up to 8{observation_id, tool, note}entries.limitations: missing evidence, conflicts, source caveats, and safety notes.safety_note: included for personalized medical advice requests.
Use low confidence when no MCP evidence was used or sources conflict.
Safety Boundary
This is research and educational support, not clinical decision support. Do not diagnose, prescribe, dose, or recommend patient-specific treatment.
High-risk phrasing includes diagnose, treatment, prescribe, dose, dosage, should I take, should I stop, medical advice, my symptoms, and for me personally.
For those requests, provide only general biomedical context, decline personalized medical advice, and include the safety note in limitations.
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.
- 12d ago First seen · 49 lines · 39 tokens per session scan A 5fad90c0a759
biomed-research is a skill published in the GitHub repository nickzren/biomed-agent (15 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 464 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 2026-08-30.
Other skills, from other repositories
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
genomic-variants
Analysis of called genomic variants — filtering, annotation, GWAS, and population-genetics summaries from VCF and PLINK-format data.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.
drug-repurposing
Systematic drug repurposing via signature matching, target-based analysis, network proximity, genetic evidence scoring, and clinical evidence mining.