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 zamushwani/biomedical-ai-skills --skill drug-responsegit clone --depth 1 https://github.com/zamushwani/biomedical-ai-skillsWrote 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/zamushwani/biomedical-ai-skills/drug-response)<a href="https://agentmods.dev/skills/zamushwani/biomedical-ai-skills/drug-response"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-skills/drug-response/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/zamushwani/biomedical-ai-skills/drug-response"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-skills/drug-response.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 | $0.00000 | $0.03663 |
| Opus 5 | $0.00000 | $0.01832 |
| Sonnet 5 | $0.00000 | $0.00733 |
| Haiku 4.5 | $0.00000 | $0.00366 |
Grade A, and why
drug-response 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug Response
Dose-response modeling and drug sensitivity prediction in cancer cell lines. Covers IC50 and AUC estimation from viability curves, retrieval and harmonization of GDSC, CTRP, and PRISM data through PharmacoGx, DepMap dependency and drug data, sensitivity prediction with regularized regression, and pharmacogenomic biomarker discovery.
When to Use This Skill
Activate when the user requests:
- IC50, EC50, or AUC estimation from dose-response data
- Four-parameter logistic (4PL) curve fitting
- GDSC, CTRP, PRISM, or CCLE drug sensitivity retrieval
- DepMap dependency or drug screen data
- Cross-dataset harmonization of drug response
- Drug sensitivity prediction from expression or mutation
- Pharmacogenomic biomarker discovery
- Distinguishing IC50 from AUC as a response metric
Inputs
| Data Type | Format | Source |
|---|---|---|
| Dose-response | Concentration, viability per well | Screening plates, published curves |
| Curated sensitivity | PharmacoSet (.rds) |
PharmacoGx, ORCESTRA |
| Cell line molecular | Expression, mutation, CNV matrices | DepMap, CCLE |
| Drug annotation | SMILES, target, mechanism | DepMap, ChEMBL |
Environment
Versions verified 2026-08.
# Curated drug response, the practical entry point
BiocManager::install("PharmacoGx") # 3.16.0 (Bioconductor)
# NOT the CRAN PharmacoGx, which is frozen at 1.1.6 from 2016.
# install.packages("PharmacoGx") gets a decade-old package. Use Bioconductor.
# Dose-response curve fitting
install.packages("drc") # 3.0-1 (2016). Stale but standard.
install.packages("nplr") # 0.1-8 (2025). Maintained alternative.
# GDSC's own fitting pipeline
# remotes::install_github("CancerRxGene/gdscIC50") # not on CRAN
# DepMap data in R
BiocManager::install("depmap") # ExperimentHub interface to releases
Data source status, checked 2026-08:
DepMap depmap.org/portal — up. Distributes CCLE molecular data,
CRISPR dependency (Chronos), and the PRISM drug repurposing
screen. The practical download host.
cancerrxgene.org the GDSC website is currently returning HTTP 410 Gone,
on every path. Do not hardcode a download URL against it.
GDSC processed data is mirrored through DepMap and wrapped
by PharmacoGx, which is how to obtain it reliably now.
PharmacoDB pharmacodb.ca — up. Cross-dataset query interface.
ORCESTRA orcestra.ca — versioned, citable PharmacoSet objects.
Because the primary GDSC portal is unstable, prefer the curated PharmacoSet
route over scraping raw files. It also fixes the harmonization problems below.
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.
- 12d ago First seen · 329 lines · 0 tokens per session scan A 5c4fdce816fb
drug-response is a skill published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,663 tokens. 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 2026-08-31.
Other skills, from other repositories
cerna-analysis
Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory. NOT for: differential expression, single-cell analysis, enrichment analysis, or workflows without a key gene…
cibersort-immune-infiltration-analysis
Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq…
gene-protein-expression-matrix-normalization
Use when normalizing bulk gene or protein expression matrices with log2 transform, z-score standardization, or min-max scaling before downstream visualization or exploratory analysis. NOT for count-model normalization such as TPM/DESeq2 size factors, batch correction, or single-cell preprocessing.
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
torch-geometric
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.
bids
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…