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 learningmatter-mit/AtomisticSkills --skill drug-db-chemblgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote 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/learningmatter-mit/atomisticskills/drug-db-chembl)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/drug-db-chembl"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/drug-db-chembl.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01441 |
| Opus 5 | $0.00016 | $0.00720 |
| Sonnet 5 | $0.00007 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
drug-db-chembl scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
* **Dependencies**: Standard library only (`urllib`, `json`, `csv`, etc.). How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
db-chembl
Goal
To programmatically query the ChEMBL database web services and retrieve reproducible, model-ready datasets of targets, molecules, and bioactivities, while preserving provenance (assay/document IDs) and enabling common curation filters (e.g., pChEMBL, standardized units, handling censoring operators, assay type).
ChEMBL activity data is curated and standardized, but downstream modeling still requires careful selection/filters to avoid mixing incompatible assay formats or censored measurements.
Instructions
1. Search for candidate targets by name (broad recall)
Use this when you only have a gene/protein string and want candidate ChEMBL target IDs.
# Env: base-agent
python .agents/skills/drug-db-chembl/scripts/query_chembl.py \
--target "EGFR" \
--max_results 20 \
--output egfr_targets.json
2. Resolve target by UniProt accession (higher precision)
If you know a UniProt accession, this reduces ambiguity compared to free-text searching.
# Env: base-agent
python .agents/skills/drug-db-chembl/scripts/query_chembl.py \
--uniprot "P00533" \
--target_type "SINGLE PROTEIN" \
--max_results 10 \
--output egfr_targets_uniprot.json
3. Retrieve bioactivity data for a target (recommended "model-ready" defaults)
ChEMBL web services are paginated (limit/offset + page_meta); this script automatically iterates pages up to --max_results.
Recommended for many QSAR/ML use cases:
- use standardized fields (
standard_*) - prefer binding assays (
--assay_type B) when you want binding potency - restrict to equality relations (
--standard_relation "=") to avoid mixing censored labels - restrict to nM for consistency (
--standard_units nM) - require/compute pChEMBL (comparable negative log molar potency)
# Env: base-agent
python .agents/skills/drug-db-chembl/scripts/query_chembl.py \
--target_id "CHEMBL203" \
--activity_type "IC50" \
--assay_type "B" \
--standard_relation "=" \
--standard_units "nM" \
--require_pchembl \
--pchembl_min 5.0 \
--max_results 200 \
--output egfr_ic50_pchembl.json
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.
- 8d ago First seen · 159 lines · 33 tokens per session scan A 5a68c41240b4
drug-db-chembl is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,441 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
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…
binding-affinity
Hybrid ML + physics binding affinity prediction. Empirical scoring, MM/GBSA rescoring, multi-method consensus, and batch virtual screening for protein-ligand complexes.
drug-design
End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.
molecular-optimization
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).