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 K-Dense-AI/drug-discovery-agent-skills --skill molfeatgit clone --depth 1 https://github.com/K-Dense-AI/drug-discovery-agent-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/k-dense-ai/drug-discovery-agent-skills/molfeat)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/molfeat"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/molfeat/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/k-dense-ai/drug-discovery-agent-skills/molfeat"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/molfeat.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 | $0.00165 | $0.05068 |
| Opus 5 | $0.00082 | $0.02534 |
| Sonnet 5 | $0.00033 | $0.01014 |
| Haiku 4.5 | $0.00016 | $0.00507 |
Grade A, and why
molfeat 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Molfeat - Molecular Featurization Hub
Overview
Molfeat turns molecules (SMILES strings or RDKit/datamol Mol objects) into numerical
representations for machine learning: fingerprints, descriptors, pharmacophores, shape
descriptors, and pretrained neural embeddings, all behind one scikit-learn-compatible
transformer interface with state serialization and caching.
Current baseline (verified 2026-08-16): molfeat 0.11.0 (May 2025) is still the latest
PyPI and GitHub release; the repository has had no commits since. All examples in this skill
were executed against 0.11.0 on Python 3.10 with datamol 0.12.5, RDKit 2026.03.5, numpy
2.2.6 and torch 2.13.0. Python 3.11+ is not installable (requires-python = ">=3.9,<3.11").
The Python cap isolates this skill from the rest of the bundle. Nothing else here needs an
interpreter below 3.11, so molfeat requires its own environment and cannot share one with
admet-prediction (3.11+), pytdc, or deepchem. That is manageable for a featurisation step
that writes a matrix to disk, and painful for anything interactive. For new work where the
featuriser is not itself the point, RDKit or datamol fingerprints plus a Chemprop or scikit-learn
model reach the same place without the constraint; use molfeat when you specifically want its
breadth of featurisers behind one interface.
0.11.0 loads pretrained models in memory, sets base models to eval mode, and moved the model
store to a Cloudflare HTTP bucket (PR #115) — that last change broke store downloads for the
HuggingFace models (see Pretrained models).
When to Use This Skill
- Converting SMILES into ML-ready feature matrices (QSAR/QSPR, ADMET, activity prediction)
- Virtual screening: featurize a library, score it with a trained model
- Similarity searching and chemical-space analysis (clustering, UMAP/t-SNE)
- Benchmarking several representations against each other on the same task
- Building reproducible featurization pipelines that can be serialized and reloaded
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.
- 12d ago First seen · 384 lines · 165 tokens per session scan A 04b9fa8ad938
molfeat is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (28 stars, last pushed 5d ago), licensed MIT. It adds 165 tokens to every session and 5,068 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
patsnap-biological-modality
Biological sequence and modality intelligence via Patsnap MCP.
patsnap-chemical-molecular
Patsnap Chemical Molecular MCP for AI agents. Search 160M+ chemical structures, synthetic routes, and bioactivity data via specialized chemistry tools.
patsnap-scientific-translational-evidence
Patsnap Scientific & Translational Evidence MCP for AI agents. Retrieval platform focusing on scientific literature and translational outcomes, covering academic publication queries and translational medicine record tracking.
patsnap-target-disease
Patsnap Target & Disease MCP for AI agents. Target and disease profiling tool, covering target characterization, disease profiling, and epidemiology evidence retrieval.
patsnap-solution-engine
Patsnap TRIZ Concept Solution Engine MCP for AI agents. Generates innovation or product cost-reduction concepts through asynchronous TRIZ and TRIZ/DFMA workflows. Use for engineering problem solving, concept alternatives, cost-reduction analysis, task-progress retrieval, and selected-solution details.
patsnap-clinical-trials
Patsnap Clinical Trials MCP for AI agents. Intelligent clinical trial retrieval system, covering registered trial tracking, trial details and results analysis, and supporting clinical semantic search.