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-pose-validationnpx skills add learningmatter-mit/AtomisticSkills --skill drug-pose-validationgit 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-pose-validation)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/drug-pose-validation"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/drug-pose-validation.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 | $0.00033 | $0.01310 |
| Opus 5 | $0.00016 | $0.00655 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
drug-pose-validation 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drug-pose-validation
Goal
To filter docked or generated ligand poses through physical plausibility checks (bond lengths, angles, planarity, internal clashes, protein-ligand clashes, stereochemistry) using PoseBusters, producing a validated subset of poses plus a machine-readable report.
This skill sits between docking (drug-docking-vina) and downstream refinement (drug-complex-system-builder, drug-protein-ligand-md), ensuring that only physically reasonable poses enter expensive simulation stages.
Instructions
1. Prepare inputs
You need:
- Docked poses: an SDF file containing one or more ligand poses (e.g., output from Vina converted to SDF, or from any pose-generation tool).
- Receptor structure (optional but recommended): PDB file of the protein. When provided, PoseBusters also checks for protein-ligand steric clashes.
If your docked poses are in PDBQT format, convert them to SDF first:
# Env: drugdisc-agent
obabel docking/results/ligand_docked.pdbqt -O docking/results/ligand_docked.sdf -m
2. Run pose validation
# Env: drugdisc-agent
python .agents/skills/drug-pose-validation/scripts/validate_poses.py \
--poses docking/results/ligand_docked.sdf \
--receptor docking/inputs/protein_prepared.pdb \
--output_dir docking/validation/
This produces:
docking/validation/validation_report.json: per-pose pass/fail results for each checkdocking/validation/valid_poses.sdf: SDF containing only poses that pass all checksdocking/validation/summary.txt: human-readable summary
3. Run without receptor (ligand-only checks)
When no receptor is available, run ligand-only validation (checks bond geometry, planarity, stereochemistry, internal clashes):
# Env: drugdisc-agent
python .agents/skills/drug-pose-validation/scripts/validate_poses.py \
--poses generated/conformers.sdf \
--output_dir generated/validation/
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.
- examples/hiv1-protease/mixed_poses.sdf 6.2 KB
- examples/hiv1-protease/mixed_validation/summary.txt 263 B
- examples/hiv1-protease/mixed_validation/valid_poses.sdf 4.6 KB
- examples/hiv1-protease/mixed_validation/validation_report.json 5.7 KB
- examples/hiv1-protease/README.md 1.5 KB
- examples/hiv1-protease/test_poses.sdf 4.6 KB
- scripts/validate_poses.py 6.3 KB runs code
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 · 129 lines · 33 tokens per session scan A 054d444bd937
drug-pose-validation is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,310 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…
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).
text-based-molecule-editing
Modify molecules based on natural language descriptions using MolT5/BioT5 models. Use this skill when: (1) User wants to modify a molecule to improve specific properties (solubility, potency, etc.), (2) User provides a molecule and asks to "make it more X" or "improve Y", (3) User wants to generate molecule variants…
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…
chembl-query
Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based search), (2) Getting bioactivity profile for a molecule (molecule-based search), (3) Finding drugs for a disease indication (indication-based search).