Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4Snpx agentmods add skills/pku-yuangroup/openai4s/bio-database-access-sra-dataWrote 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-sra-data)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-database-access-sra-data"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-database-access-sra-data/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-sra-data"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-database-access-sra-data.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 | $0.00158 | $0.04732 |
| Opus 5 | $0.00079 | $0.02366 |
| Sonnet 5 | $0.00032 | $0.00946 |
| Haiku 4.5 | $0.00016 | $0.00473 |
Grade C, and why
bio-sra-data scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
# rm -rf ~/ncbi/sra/${SRR}.sra Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- CLI: `curl https://ftp.sra.ebi.ac.uk/...` (ENA mirror; direct FASTQ) This is a copy
94% identical to bio-sra-data — 16 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: sra-tools 3.0+ (fasterq-dump, prefetch, vdb-validate, vdb-config), pysradb 2.2+, ENA portal API 2.0+
Before using code patterns, verify installed versions match. If versions differ:
- CLI:
fasterq-dump --version,prefetch --version - Python:
pip show pysradb
If a flag is unrecognized or behavior changes, run <tool> --help and adapt.
SRA Data
"Download FASTQ from this SRA accession" -> Two paths exist in 2026: the SRA toolkit (NCBI's official, with prefetch + fasterq-dump) and the ENA mirror (EMBL-EBI's mirror with direct FASTQ download, often faster). For >1 TB workflows, a third path: AWS Open Data (STRIDES program) where same-region EC2 pulls SRA data with zero egress cost.
The single most impactful decision is where to pull from. SRA-direct is the default but ENA is faster more often than not, and AWS Open Data is the right answer for cloud-native analysis pipelines.
- CLI:
prefetch SRR...,fasterq-dump SRR...,vdb-validate SRR...(sra-tools) - CLI:
curl https://ftp.sra.ebi.ac.uk/...(ENA mirror; direct FASTQ) - CLI:
aws s3 cp s3://sra-pub-run-odp/sra/SRR.../SRR... ./SRR....sra ...(STRIDES; object is unsuffixed; same-region free) - Python:
pysradbfor metadata;subprocessfor download
Required Setup
# sra-tools (toolkit)
conda install -c bioconda sra-tools # 3.0+
fasterq-dump --version # confirm
# Configure cache location (default ~/ncbi/ -- often too small)
vdb-config --cfg # show current config
vdb-config --set /repository/user/main/public/root=/data/sra_cache
# Optional: pysradb for metadata
pip install pysradb
For STRIDES cloud:
# AWS CLI (no NCBI auth needed for public buckets)
aws s3 ls s3://sra-pub-run-odp/sra/SRR12345678/ --no-sign-request
Decision matrix: where to pull from
| Source | When best | Speed | Cost |
|---|---|---|---|
| ENA mirror (FTP/Aspera) | Default for most workflows | Often fastest; direct FASTQ (no SRA->FASTQ conversion needed) | Free; no rate limit observed |
| SRA toolkit + AWS STRIDES | Same-region EC2/EKS | Fastest within AWS us-east-1 | Free egress within region; small storage cost |
| SRA toolkit + GCP STRIDES | Same-region GCP Compute Engine | Fastest within GCP us-central1 | Free egress within region |
| SRA-direct (prefetch + fasterq-dump) | On-prem; small downloads; need SRA-format access | Variable; can be slow off-peak fails | Free; NCBI throttles by IP |
Aspera (ascp) |
Institutional accounts only | Faster than HTTPS on long links | NCBI public Aspera retired 2019; ENA public Aspera retired ~2023; institutional use still possible |
What ships with it
5 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 · 386 lines · 158 tokens per session scan C 19f2d1afe6ef
bio-sra-data is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (407 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 4,732 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It is 94% identical to bio-sra-data, differing in 16 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.