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 PKU-YuanGroup/OpenAI4S --skill bio-clinical-databases-variant-prioritizationgit clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4SWrote 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/pku-yuangroup/openai4s/bio-clinical-databases-variant-prioritization)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-clinical-databases-variant-prioritization"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-clinical-databases-variant-prioritization/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/pku-yuangroup/openai4s/bio-clinical-databases-variant-prioritization"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-clinical-databases-variant-prioritization.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 | $0.00167 | $0.06898 |
| Opus 5 | $0.00084 | $0.03449 |
| Sonnet 5 | $0.00033 | $0.01380 |
| Haiku 4.5 | $0.00017 | $0.00690 |
Grade A, and why
bio-clinical-databases-variant-prioritization 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 8d 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.
This is a copy
97% identical to bio-clinical-databases-variant-prioritization — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: pandas 2.2+, cyvcf2 0.30+, pyhgvs 0.12+, Exomiser 14.0+ (Smedley 2015), Phen2Gene 1.2+ (Zhao 2020), DeNovoGear 1.1.1+ (Ramu 2013), WhatsHap 2.0+ (Patterson 2015), HPO 2024+ (Human Phenotype Ontology). ACMG Secondary Findings list is v3.2 (Miller 2023): 81 genes.
Before using code patterns, verify installed versions match. If versions differ:
- Python:
pip show <package>thenhelp(module.function)to check signatures - CLI:
<tool> --version
If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. Phenotype-driven prioritization REQUIRES high-quality HPO terms; without rich phenotypic input Exomiser/AMELIE degrade significantly.
Rare-Disease Variant Prioritization Pipeline
'Prioritize candidate disease-causing variants from this trio exome' -> Filter to rare + functional + inheritance-consistent variants; rank by phenotype concordance; flag ACMG SF v3.2 incidental findings; report tiers with classification logic deferred to acmg-classification.
- Python (filtering pipeline): pandas + cyvcf2 + myvariant.info aggregation
- CLI (phenotype-driven ranking):
exomiser --analysis hiPHIVE-prioritised.yml - Python (de novo calling): DeNovoGear / Triodenovo / PossibleDeNovo
- CLI (compound het phasing):
whatshap phase --indelsfor singletons; trio-based for families - Python (HPO concordance): Phen2Gene / AMELIE / Phenolyzer
- VCEP curations:
https://cspec.genome.network/cspec/ui/svi/all
Pipeline Architecture: The Standard Rare-Disease Funnel
Typical trio exome enters as 40,000-100,000 variants per individual; reaches diagnostic candidate list of 1-10 variants through cascading filters:
| Stage | Filter | Variant count (typical trio) |
|---|---|---|
| Raw joint-called | -- | 100k-150k |
| QC filter (PASS, depth, GQ, missingness) | GATK best practices + Hail QC | 80k-120k |
| Population frequency | gnomAD grpmax_faf95 < 0.0001 (or disease-specific Whiffin max-credible-AF) | 5k-15k |
| Functional consequence | Coding / splice / regulatory | 1k-3k |
| Inheritance pattern | de novo / AR-hom / AR-compoundhet / X-linked / mosaic | 50-500 |
| Phenotype concordance | Exomiser hiPHIVE / Phen2Gene / AMELIE score | 5-50 |
| ACMG classification | Defer to acmg-classification |
1-10 |
| ACMG SF v3.2 cross-check | Miller 2023 (81 genes) | Separate output |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 408 lines · 167 tokens per session scan A 031bf338ee4a
bio-clinical-databases-variant-prioritization is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (403 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 6,898 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to bio-clinical-databases-variant-prioritization, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
histolab
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.