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/learningmatter-mit/atomisticskills/drug-db-pdbnpx skills add learningmatter-mit/AtomisticSkills --skill drug-db-pdbgit 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-pdb)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/drug-db-pdb"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/drug-db-pdb.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 | $0.00041 | $0.01116 |
| Opus 5 | $0.00020 | $0.00558 |
| Sonnet 5 | $0.00008 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
drug-db-pdb 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 5d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
db-pdb
Goal
To programmatically discover and retrieve protein (and protein-ligand complex) structures from the RCSB Protein Data Bank (PDB) by combining the RCSB Search API (to find matching PDB IDs) with the RCSB Data API (to retrieve rich metadata and ligand information), and optionally downloading coordinate files (PDB/mmCIF) and wwPDB validation reports for downstream modeling.
Instructions
1. (Recommended) Create a dedicated output directory
Keep downloaded coordinates/JSON in a reproducible folder.
# Env: base-agent
mkdir -p research/db-pdb/ace2_example
2. Search by keyword (full-text)
Uses the RCSB Search API to return the top scoring PDB IDs for a query.
# Env: base-agent
python .agents/skills/drug-db-pdb/scripts/query_pdb.py \
--search "kinase inhibitor" \
--max_results 10 \
--output research/db-pdb/kinase_results.json
3. Search with structure-quality filters (recommended for drug discovery)
For ligand modeling, you often want:
- An experimental method like X-RAY DIFFRACTION (or high-resolution cryo-EM).
- A resolution cutoff (e.g., <= 2.5 A for X-ray, context dependent).
# Env: base-agent
python .agents/skills/drug-db-pdb/scripts/query_pdb.py \
--search "ACE2" \
--organism "Homo sapiens" \
--method "X-RAY DIFFRACTION" \
--resolution 2.5 \
--max_results 25 \
--output research/db-pdb/ace2_xray_le2p5.json
4. Retrieve a specific PDB entry by ID
This pulls metadata via the Data API and (by default) also collects bound ligands by enumerating non-polymer entities.
# Env: base-agent
python .agents/skills/drug-db-pdb/scripts/query_pdb.py \
--pdb_id 1HSG \
--output research/db-pdb/1hsg_info.json
5. Download coordinate files (mmCIF recommended)
The PDB ecosystem's canonical archival format is PDBx/mmCIF (legacy PDB format can be unavailable or insufficient for very large structures).
# Env: base-agent
python .agents/skills/drug-db-pdb/scripts/query_pdb.py \
--pdb_id 1HSG \
--download mmcif \
--download_dir research/db-pdb/structures \
--output research/db-pdb/1hsg_with_file.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.
- 5d ago First seen · 117 lines · 41 tokens per session scan A 2c2b7ef837c7
drug-db-pdb is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,116 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 2026-08-30.
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…
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).
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).