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 lynnlangit/precision-medicine-mcp --skill precision-bio-testsgit clone --depth 1 https://github.com/lynnlangit/precision-medicine-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/lynnlangit/precision-medicine-mcp/precision-bio-tests)<a href="https://agentmods.dev/skills/lynnlangit/precision-medicine-mcp/precision-bio-tests"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/precision-bio-tests/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/lynnlangit/precision-medicine-mcp/precision-bio-tests"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/precision-bio-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00613 |
| Opus 5 | $0.00014 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
precision-bio-tests 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Precision Bio-Testing
This skill provides guidelines for validating the complex biological and clinical logic in this repository.
Automated Testing Strategy
1. Unit Testing (pytest)
Tests live in two locations:
- Project-root tests:
tests/unit/mcp-[server]/(e.g.,tests/unit/mcp-spatialtools/) - Server-local tests:
servers/mcp-[name]/tests/(e.g.,servers/mcp-perturbation/tests/)
Both patterns are in active use. Check both locations when looking for existing coverage.
2. The .fn Testing Pattern
FastMCP Pattern: Never call @mcp.tool() decorated functions directly. Always use the .fn attribute to bypass the MCP protocol layer:
result = await server.perturbation_predict.fn(gene="BRCA1", cell_type="T-cell")
This pattern is used across 9 test files in the project. Always follow it when writing new tests.
3. DRY_RUN Mode
Always test both modes:
DRY_RUN=True(default) — returns synthetic/simulated data, no real bio tools neededDRY_RUN=False— exercises real logic (monkeypatch external dependencies in CI)
4. Bioinformatics Fixtures
Some test suites use fixture files (e.g., tests/unit/mcp-multiomics/fixtures/ contains sample CSV files). Large datasets should be mocked or referenced from data/patient-data/.
The PatientOne Scenario
The gold standard for integration testing is the PatientOne workflow (docs/reference/testing/patient-one/):
- Phase 1: Clinical (Epic)
- Phase 2: Multi-omics
- Phase 3: Spatial
- Phase 4: Imaging
- Phase 5: Final integrated recommendation
Manual Testing (Prompts)
For browser-based or chat-based testing:
- Use the templates in
docs/reference/testing/quick-test-prompts.md - Verify the "Clinical Interpretation" matches the expected biological signal (e.g., GZMB/IFNG upregulation in immunotherapy)
Testing Checklist
- Tool discovery via MCP protocol works
-
.fnpattern used for all tool function calls in tests - Both DRY_RUN=True and DRY_RUN=False paths covered
- Memory usage remains within 4Gi during heavy bioinformatics processing
- Error messages are informative for clinicians, not just developers
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 · 71 lines · 28 tokens per session scan A 61a107323255
precision-bio-tests is a skill published in the GitHub repository lynnlangit/precision-medicine-mcp (24 stars, last pushed 16d ago), licensed Apache-2.0. It adds 28 tokens to every session and 613 once invoked, about $0.0001 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
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
nw-tlaplus-verification
TLA+ formal verification for design correctness and PBT pipeline integration.
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…