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-database-access-biomart-queriesgit 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-database-access-biomart-queries)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-database-access-biomart-queries"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-database-access-biomart-queries/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-database-access-biomart-queries"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-database-access-biomart-queries.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 | $0.00142 | $0.03525 |
| Opus 5 | $0.00071 | $0.01762 |
| Sonnet 5 | $0.00028 | $0.00705 |
| Haiku 4.5 | $0.00014 | $0.00352 |
Grade A, and why
bio-biomart-queries scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- CLI: `curl` against the XML endpoint works but is rarely used directly This is a copy
97% identical to bio-biomart-queries — 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: pybiomart 0.9+, R biomaRt 2.58+ (Bioconductor); Ensembl BioMart (release 110+)
Before using code patterns, verify installed versions match. If versions differ:
- Python:
pip show pybiomart - R:
packageVersion('biomaRt')
The BioMart XML query format is stable across Ensembl releases; the underlying mart names and attribute IDs can change between Ensembl releases. For published work, pin the Ensembl release via useEnsembl(version=110).
BioMart Queries
"Bulk-convert IDs / pull coordinate tables / extract ortholog wide tables" -> BioMart is the right answer for any Ensembl-rooted query producing >5,000 rows. It is a separate service from the Ensembl REST API, with separate rate behavior and a different query model (XML-based, batch-oriented). For one-off lookups (<100 records), Ensembl REST is more convenient; for bulk anything, BioMart wins.
The single most important fact: BioMart returns a flat table from a single query. There is no per-record loop, no rate-limit cascade, no async polling. One XML query in; one TSV out.
- Python:
pybiomart(https://github.com/jrderuiter/pybiomart) is the lightest client - R:
biomaRtBioconductor (Durinck et al. 2009 Nat Protoc 4:1184) is the canonical client - CLI:
curlagainst the XML endpoint works but is rarely used directly - Web:
https://www.ensembl.org/biomart/martviewfor interactive query design
Installation
pip install pybiomart pandas
# R:
# BiocManager::install('biomaRt')
BioMart hierarchy
| Level | Examples |
|---|---|
| Mart | ENSEMBL_MART_ENSEMBL (genes), ENSEMBL_MART_SNP (variants), ENSEMBL_MART_MOUSE (mouse-specific) |
| Dataset | hsapiens_gene_ensembl, mmusculus_gene_ensembl, etc. (per species) |
| Attribute | Fields to return: ensembl_gene_id, external_gene_name, chromosome_name, etc. |
| Filter | Constraints on the query: chromosome_name = 17, biotype = protein_coding, etc. |
A query is: pick a mart, pick a dataset, list attributes to return, list filters to constrain. BioMart returns a single TSV.
What ships with it
4 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.
- 9d ago First seen · 290 lines · 142 tokens per session scan A 49fc30f67f9b
bio-biomart-queries is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (407 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 3,525 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 97% identical to bio-biomart-queries, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
boltz-structure-prediction
Boltz-1 / Boltz-2 structure prediction for proteins, complexes, and ligand-aware validation. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.