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/chem-sorption-widomnpx skills add learningmatter-mit/AtomisticSkills --skill chem-sorption-widomgit 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/chem-sorption-widom)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-sorption-widom"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-sorption-widom.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 | $0.00032 | $0.00909 |
| Opus 5 | $0.00016 | $0.00454 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
chem-sorption-widom scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chem-sorption-widom
Goal
To determine the initial affinity of a porous material (e.g., MOFs, COFs) for a specific gas molecule at infinite dilution. This is done by computing the Henry coefficient ($K_H$) and the isosteric heat of adsorption ($\Delta H_{ads}$) using Widom insertion, calculating interaction energies with a generic Machine Learning Interatomic Potential (MLIP) such as MACE, FairChem, or MatGL.
Prerequisites
- Input: A relaxed framework structure in CIF (or XYZ) format. The structure should ideally be processed by chem-sorption-relax to ensure proper supercell dimensions.
- Conda environment: Depends on the MLIP used (e.g.,
fairchem-agent,mace-agent,matgl-agent).
Instructions
- Perform Widom Insertion: Use the
run_widom.pyscript, specifying the structure, gas, temperature, and your MLIP of choice.
# Env: fairchem-agent (if using fairchem), mace-agent (if using mace), etc.
python .agents/skills/chem-sorption-widom/scripts/run_widom.py \
--structure path/to/relaxed_supercell.cif \
--name MY_FRAMEWORK \
--calculator fairchem \
--model-name uma-s-1p2 \
--task-name omol \
--gas CO2 \
--temperature 298 \
--output-dir ./results
Parameters
--structure: Path to the relaxed host framework (must be large enough, see Constraints).--name: Identifier for the output files.--calculator: The backend MLIP (fairchem,mace,matgl).--model-name: Name or path to the MLIP weights (e.g.,uma-s-1p1.pt,MACE-MH-1).--task-name: Optional, but highly recommended for multi-task models (e.g.,omolfor FairChem UMA and MACE-MH).--gas: The adsorbate gas (e.g.,CO2,N2,CH4).--temperature: Temperature in Kelvin.--num-insertions: Number of Monte Carlo insertion attempts (default: 50,000).--output-dir: Directory to save thewidom_results.json.
Examples
Example 1: Using FairChem UMA-S-1p2 for CO2 adsorption at 298K
# Env: fairchem-agent
python .agents/skills/chem-sorption-widom/scripts/run_widom.py \
--structure ./results/COF-1_supercell.cif \
--name COF-1 \
--calculator fairchem \
--model-name uma-s-1p2 \
--task-name omol \
--gas CO2 \
--temperature 298 \
--output-dir ./results
What ships with it
15 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/input_configs.yaml 418 B
- examples/README.md 1.5 KB
- examples/test_widom.sh 473 B runs code
- scripts/run_widom.py 3.8 KB runs code
- scripts/widom_common.py 6.1 KB runs code
- scripts/widom_src/widom/__init__.py 644 B runs code
- scripts/widom_src/widom/analyze.py 5.5 KB runs code
- scripts/widom_src/widom/LICENSE 11 KB
- scripts/widom_src/widom/NOTICE 305 B
- scripts/widom_src/widom/pyproject.toml 642 B
- scripts/widom_src/widom/README.md 5.0 KB
- scripts/widom_src/widom/run.py 5.7 KB runs code
- scripts/widom_src/widom/sample_compute_energies.py 3.0 KB runs code
- scripts/widom_src/widom/structure_preparation.py 2.4 KB runs code
- scripts/widom_src/widom/utils.py 11 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.
- 5d ago First seen · 76 lines · 32 tokens per session scan A c2bbddf3802f
chem-sorption-widom is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 909 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…
hypogenic
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use…
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.
medchem
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.