synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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 synthetic-sciences/openscience --skill drugbank-databasegit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/drugbank-database)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/drugbank-database"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/drugbank-database.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.01957 |
| Opus 5 | $0.00042 | $0.00979 |
| Sonnet 5 | $0.00017 | $0.00391 |
| Haiku 4.5 | $0.00008 | $0.00196 |
Grade A, and why
drugbank-database 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 today.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- drugbank-database — 100% identical, 5 lines differ
- drugbank-database — 100% identical, 3 lines differ
- drugbank-database — 100% identical, 3 lines differ
- drugbank-database — 95% identical, 6 lines differ
- drugbank-database — 95% identical, 6 lines differ
- drugbank-database — 95% identical, 6 lines differ
- alterlab-drugbank — 94% identical, 14 lines differ
- drugbank-database-hardened — 94% identical, 15 lines differ
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DrugBank Database
Overview
DrugBank contains drug and drug-target information. The bundled helper reads a licensed local XML export; it does not include the dataset or download it automatically. Available records depend on the supplied export and its version.
Core Capabilities
1. Data Access and Authentication
Access a DrugBank export that the user is licensed to use. The skill provides guidance on:
- Supplying an explicit local XML path or a pre-loaded XML root
- Keeping licensed data out of repositories and shared artifacts
- Recording the supplied database version
- Opening and parsing XML data efficiently
- Working with cached data to optimize performance
When to use: Setting up local DrugBank analysis or diagnosing a missing export.
Reference: See references/data-access.md for detailed authentication, download procedures, API access, caching strategies, and troubleshooting.
2. Drug Information Queries
Extract comprehensive drug information from the database including identifiers, chemical properties, pharmacology, clinical data, and cross-references to external databases.
Query capabilities:
- Search by DrugBank ID, name, CAS number, or keywords
- Extract basic drug information (name, type, description, indication)
- Retrieve chemical properties (SMILES, InChI, molecular formula)
- Get pharmacology data (mechanism of action, pharmacodynamics, ADME)
- Access external identifiers (PubChem, ChEMBL, UniProt, KEGG)
- Build searchable drug datasets and export to DataFrames
- Filter drugs by type (small molecule, biotech, nutraceutical)
When to use: Retrieving specific drug information, building drug databases, pharmacology research, literature review, drug profiling.
Reference: See references/drug-queries.md for XML navigation, query functions, data extraction methods, and performance optimization.
3. Drug-Drug Interactions Analysis
Analyze drug-drug interactions (DDIs) including mechanism, clinical significance, and interaction networks for pharmacovigilance and clinical decision support.
What ships with it
6 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.
- today Changed · +5 lines 62a13191f390
- 3d ago First seen · 190 lines · 84 tokens per session scan A ed8d1a5df8c7
drugbank-database is a skill published in the GitHub repository synthetic-sciences/openscience (3,493 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,957 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
arxiv
Search arXiv papers by keyword, author, category, or ID.
research-paper-writing
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
paper-plot-stub
Plot a results CSV (x, ybaseline, yours) as a two-line matplotlib chart and write a PDF. Demo-only.
google-workspace-setup
One-time setup for gws: install, OAuth, scopes, auto-approve.