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 admet-reasoninggit 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/admet-reasoning)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/admet-reasoning"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/admet-reasoning/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/synthetic-sciences/openscience/admet-reasoning"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/admet-reasoning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.00611 |
| Opus 5.5 | $0.00019 | $0.00244 |
| Sonnet 5.5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
admet-reasoning 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADMET Reasoning
Overview
Standard ADMET prediction tools output scores (e.g., "hERG = 0.85") without explaining why. This skill adds mechanistic reasoning — mapping each ADMET liability to its structural cause, the biological mechanism it affects, and a suggested structural fix.
Based on:
- CoTox (Park et al., 2025): Chain-of-thought toxicity reasoning with structural + biological context improved F1 from 0.37 to 0.66
- DrugR (Liu et al., 2026): Explicit liability reasoning before optimization improved scores 18×
When to Use This Skill
- After ADMET prediction: Interpret flagged liabilities with structural explanations
- Lead optimization planning: Understand which structural features to modify and why
- Toxicity reports: Generate interpretable toxicity assessments for medicinal chemistry teams
- Design review: Evaluate whether proposed modifications address the right liabilities
Do NOT use this skill for:
- Raw ADMET score computation (use
admet-predictioninstead) - Molecular optimization (use
molecular-optimizationinstead)
Related Skills
- admet-prediction: Compute ADMET properties (run this first)
- molecular-optimization: Iterative optimization using liability analysis
- rdkit: Core molecular operations
Installation
Required dependencies
pip install rdkit-pypi numpy pandas
Core Workflows
1. Full Liability Report
Generate interpretable ADMET analysis for a molecule:
python scripts/reason_admet.py --smiles "c1ccc(NC(=O)c2ccccc2Cl)cc1" --output report.json
2. Batch Liability Analysis
python scripts/reason_admet.py --input compounds.csv --output liability_report.csv
3. Targeted Toxicity Reasoning
Focus on specific endpoints:
python scripts/reason_admet.py --smiles "CCN1CCCC1" --endpoints hERG,DILI,CYP --output tox_report.json
Script Reference
| Script | Purpose | Key Outputs |
|---|---|---|
reason_admet.py |
Full ADMET reasoning with structural explanations | JSON report with liabilities, causes, mechanisms, fixes |
What ships with it
1 file 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.
- 1mo ago First seen · 76 lines · 47 tokens per session scan A be1181043ee5
admet-reasoning is a skill published in the GitHub repository synthetic-sciences/openscience (4,193 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 611 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
admet-prediction
Predict comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for drug candidate molecules using GraphMVP ensemble models. Use this skill when: (1) Predicting blood-brain barrier penetration, (2) Assessing side effect profiles, (3) Estimating Caco-2 permeability, half-life, or LD50…
admet-prediction
ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) prediction for drug candidates. Use for assessing drug-likeness, PK properties, and safety risks early in drug discovery. Keywords: ADMET, PK, toxicity, drug-likeness, DILI, hERG, bioavailability.
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.