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 agentmods add skills/kdevos12/alkyl/torchdrugnpx skills add Kdevos12/ALKYL --skill torchdruggit clone --depth 1 https://github.com/Kdevos12/ALKYLWrote 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/kdevos12/alkyl/torchdrug)<a href="https://agentmods.dev/skills/kdevos12/alkyl/torchdrug"><img src="https://agentmods.dev/badge/skills/kdevos12/alkyl/torchdrug.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 | $0.00044 | $0.00885 |
| Opus 5 | $0.00022 | $0.00443 |
| Sonnet 5 | $0.00009 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
torchdrug 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TorchDrug
PyTorch toolkit for drug discovery — graph neural networks on molecules, proteins, and biomedical knowledge graphs. 40+ datasets, 20+ model architectures, modular task/model interface.
When to Use This Skill
- Predicting molecular properties (solubility, toxicity, BBB penetration, quantum chemistry)
- Protein function/stability/localization/interaction prediction
- Drug-target binding affinity (PDBBind, BindingDB)
- Knowledge graph completion and drug repurposing (Hetionet)
- De novo molecular generation and property optimization (GCPN, flows)
- Retrosynthesis planning (USPTO-50k, CenterIdentification + SynthonCompletion)
- Training GNNs (GCN, GAT, GIN, SchNet, GearNet, RGCN) on chemical data
- Transfer learning with pre-trained protein models (ESM, ProteinBERT)
Quick Start
from torchdrug import datasets, models, tasks
import torch
from torch.utils.data import DataLoader
# 1. Dataset
dataset = datasets.BBBP("~/datasets/")
train_set, valid_set, test_set = dataset.split()
# 2. Model
model = models.GIN(
input_dim=dataset.node_feature_dim,
hidden_dims=[256, 256, 256],
edge_input_dim=dataset.edge_feature_dim,
batch_norm=True, readout="mean"
)
# 3. Task
task = tasks.PropertyPrediction(
model, task=dataset.tasks,
criterion="bce", metric=["auroc", "auprc"]
)
# 4. Train
optimizer = torch.optim.Adam(task.parameters(), lr=1e-3)
for epoch in range(100):
for batch in DataLoader(train_set, batch_size=32, shuffle=True):
loss = task(batch)
optimizer.zero_grad(); loss.backward(); optimizer.step()
Router — What to Read
| Task | Reference |
|---|---|
| Data structures (Graph, Molecule, Protein), training loop, task/model interface | references/core-data.md |
| Molecular property prediction: datasets, tasks, model selection, training | references/molecular-property.md |
| Protein modeling: sequence & structure models, datasets, pre-training | references/protein-modeling.md |
| Knowledge graph completion, drug repurposing, Hetionet | references/knowledge-graphs.md |
| Molecular generation: GCPN, flows, property optimization | references/molecular-generation.md |
| Retrosynthesis: CenterIdentification, SynthonCompletion, USPTO-50k | references/retrosynthesis.md |
| Full model catalog: GCN, GAT, GIN, SchNet, GearNet, ESM, TransE, RotatE… | references/models-reference.md |
What ships with it
7 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.
- 4d ago First seen · 94 lines · 44 tokens per session scan A 73657d7e6ea8
torchdrug is a skill published in the GitHub repository Kdevos12/ALKYL (6 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 885 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
molecular-optimization
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).
admet-reasoning
Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.