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 agentmods add instructions/lynnlangit/precision-medicine-mcp/claude-mdgit clone --depth 1 https://github.com/lynnlangit/precision-medicine-mcpWhat 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 | $0.01744 | $0.01744 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
precision-medicine-mcp CLAUDE.md 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Project Context for Claude Code
Git Workflow
When committing and pushing changes, always complete the full git add/commit/push cycle before reporting task completion. If a usage limit is approaching, prioritize finishing the commit/push over starting new work.
Session Management
When rate limits or usage limits are hit mid-task, save progress notes in a scratch file (e.g., .claude/progress.md) listing completed steps and remaining work so the next session can resume efficiently.
What This Project Is
Precision Medicine MCP Platform — an AI-orchestrated system for precision medicine analysis across oncology and preventive health. It provides specialized MCP (Model Context Protocol) servers that expose bioinformatics and clinical risk tools via natural language through Claude or Gemini. See Server Registry for current server and tool counts.
Validated use cases (three synthetic patients, all live e2e tested):
- PAT001 (PAT001-OVC-2025) — Stage IV HGSOC; 3 investigational treatment hypotheses surfaced
- PAT002 (PAT002-BC-2026) — ER+/HER2− breast cancer; cross-cancer architecture validation
- PAT003 (PAT003-CVD-2026) — Preventive cardiovascular health, 67F post-menopausal; 3 evidence gaps identified (Lp(a), APOE, CAC score) missed by standard lipid panel and Helix Tier 1 genetic screen
Repository Structure
precision-medicine-mcp/
├── servers/ # MCP servers (Python, FastMCP) — see server-registry.md for tool counts
│ ├── mcp-fgbio/ # Genomic reference data
│ ├── mcp-multiomics/ # RNA/Protein/Phospho integration
│ ├── mcp-spatialtools/ # Spatial transcriptomics
│ ├── mcp-epic/ # Epic FHIR integration (local-only)
│ ├── mcp-mockepic/ # Synthetic EHR for demos
│ ├── mcp-perturbation/ # Perturbation prediction
│ ├── mcp-quantum-celltype-fidelity/ # Quantum cell type fidelity
│ ├── mcp-openimagedata/ # Histology image processing
│ ├── mcp-deepcell/ # Cell segmentation
│ ├── mcp-cell-classify/ # Cell phenotype classification
│ ├── mcp-mocktcga/ # Mock TCGA cohort comparison
│ ├── mcp-patient-report/ # PDF report generation
│ ├── mcp-genomic-results/ # Somatic variant/CNV parsing
│ ├── mcp-geodownload/ # GEO/SRA dataset download
│ ├── mcp-opentargets/ # Open Targets drug-target associations
│ ├── mcp-cibersortx/ # CIBERSORTx immune deconvolution
│ ├── mcp-neoantigen/ # Neoantigen prediction & HLA binding
│ ├── mcp-cardiometabolic/ # CVD risk scoring & preventive health
│ ├── mcp-deidentify/ # Stage 0: HIPAA Safe Harbor de-identification (JSON, DOCX, PDF, VCF, h5ad)
│ └── mcp-server-boilerplate/# Template for new servers
├── data/ # Patient data and reference files
│ ├── patient-data/PAT001-OVC-2025/ # Synthetic PatientOne data (HGSOC)
│ ├── pat002/ # Synthetic PAT002 data (ER+ breast cancer)
│ ├── pat003/ # Synthetic PAT003 data (preventive CVD)
│ ├── reference/ # Reference genomes
│ └── cache/ # Runtime caches
├── docs/ # Documentation (by audience)
│ ├── for-developers/ # Developer guides
│ ├── for-educators/ # Teaching materials
│ ├── for-funders/ # Stakeholder docs
│ ├── for-hospitals/ # Hospital deployment
│ ├── for-researchers/ # Researcher guides
│ ├── getting-started/ # Installation and setup
│ └── reference/ # Architecture, testing, prompts
│ └── shared/server-registry.md # Canonical server/tool counts
├── ui/ # User interfaces
│ ├── streamlit-app/ # Main Streamlit web app
│ ├── streamlit-app-students/# Simplified student version
│ ├── dashboard/ # Monitoring dashboard
│ └── jupyter-notebook/ # Jupyter integration
├── infrastructure/ # Deployment configs (GCP, Docker)
└── tests/ # Manual and integration tests
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.
- yesterday First seen · 138 lines · 1,744 tokens per session scan A ff503d7518ea
precision-medicine-mcp CLAUDE.md is an instructions file published in the GitHub repository lynnlangit/precision-medicine-mcp (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,744 tokens to every session, about $0.0087 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 instructions, from other repositories
structure-factory AGENTS.md
Instructions for BioSymphony/structure-factory, covering biosymphony structure factory agent guide, mission, how to drive a mission, compute available and orchestrators supported.
OmicsClaw AGENTS.md
Instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .
switchback-running CLAUDE.md
Instructions for rlacombe/switchback-running, covering ultrarunning training companion, constitution, athlete data, training philosophy and core principles.
asb-skill-collections copilot-instructions.md
Instructions for HolobiomicsLab/asb-skill-collections: This repository publishes the ASB Metabolomics Skill Collection (collections/metabolomics/v2/): 5,859 evidence-grounded skills over 909 software tools for computational LC-MS/MS metabolomics, each derived from a peer-reviewed method paper.
mgi-link CLAUDE.md
Claude Code instructions for berntpopp/mgi-link, covering claude.md, tl;dr, common commands and layout.
gnomad-genetics-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/gnomad-genetics-mcp-server, covering developer protocol, core rules, patterns, server config (src/config/server-config.ts) and server identity and instructions.