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-uigit 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-ui)<a href="https://agentmods.dev/skills/lynnlangit/precision-medicine-mcp/precision-bio-ui"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/precision-bio-ui/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-ui"><img src="https://agentmods.dev/badge/skills/lynnlangit/precision-medicine-mcp/precision-bio-ui.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 | $0.00031 | $0.00400 |
| Opus 5 | $0.00015 | $0.00200 |
| Sonnet 5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
precision-bio-ui 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.
What it actually says
Precision Bio-UI Development
This skill guides the development of the frontend and LLM orchestration layer of the platform.
🖼️ Dashboard Architecture
The UI is built with Streamlit and follows a modular provider-based architecture:
ui/streamlit-app/app.py: Main entry point.ui/streamlit-app/providers/: Abstracted LLM orchestration (Claude, Gemini).ui/streamlit-app/utils/: Visualization, GCS handling, and trace logic.
🤖 Provider Development
When adding or modifying LLM providers:
- Base Class: Extend
providers/base.py. - Streaming: Implement
generate_response_streamfor a better user experience. - Trace Extraction: Use
trace_utils.pyto ensure tool calls are correctly recorded for the orchestration trace.
📊 Visualization & Traces
- Orchestration Trace: Supports Log, Card, Timeline, and Sequence Diagram (Mermaid) views.
- Bio-Data Rendering: Use Streamlit's
st.dataframefor large genomic tables andst.imagefor GCS-hosted UMAPs/PCA plots. - Complexity: Keep the sidebar clean—use
st.expanderfor advanced settings.
⚙️ Configuration
- Ensure all new features are togglable via
.envor the sidebar (e.g.,USE_MOCK_MCP). - Example prompts are maintained in
utils/mcp_config.py.
Use this skill when:
- Adding a new LLM provider (e.g., DeepSeek, Llama).
- Modifying the orchestration trace visualization.
- Adding new file upload handlers or GCS widgets.
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 · 43 lines · 31 tokens per session scan A dfb43770fa87
precision-bio-ui is a skill published in the GitHub repository lynnlangit/precision-medicine-mcp (24 stars, last pushed 16d ago), licensed Apache-2.0. It adds 31 tokens to every session and 400 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
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…
multimodal-single-cell
Multi-modal single-cell analysis for CITE-seq, Multiome, TEA-seq, and DOGMA-seq including joint embedding, per-modality QC, and cross-modal integration.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
umap-learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.