Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsnpx agentmods add skills/learningmatter-mit/atomisticskills/chem-sorption-gcmcWrote 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-gcmc)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-sorption-gcmc"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-sorption-gcmc.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 5.1 | $0.00030 | $0.01040 |
| Opus 5 | $0.00015 | $0.00520 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
chem-sorption-gcmc 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chem-sorption-gcmc
Goal
To predict the macroscopic adsorption uptake of a gas (or gas mixture) in a porous material at a specific temperature and pressure. The skill relies on Grand Canonical Monte Carlo (GCMC) simulations where the host-guest and guest-guest interactions are calculated using a Machine Learning Interatomic Potential (MLIP: MACE, FairChem, 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 Single-Component GCMC (Optional): If you are investigating a single gas species, use
run_gcmc.py.
# Env: fairchem-agent (or other MLIP-specific env)
python .agents/skills/chem-sorption-gcmc/scripts/run_gcmc.py \
--cif path/to/relaxed_supercell.cif \
--calculator fairchem \
--model-name uma-s-1p1 \
--task-name omol \
--steps 50000 \
--temperature-K 298 \
--pressure-bar 1.0 \
--adsorbate CO2 \
--output-dir ./results/single_gcmc
- Perform Multi-Component GCMC (Optional): If you are simulating a gas mixture (e.g. flue gas separation 15% CO2 / 85% N2), use
run_gcmc_multi.py.
# Env: fairchem-agent
python .agents/skills/chem-sorption-gcmc/scripts/run_gcmc_multi.py \
--cif path/to/relaxed_supercell.cif \
--calculator fairchem \
--model-name uma-s-1p1 \
--task-name omol \
--steps 50000 \
--temperature-K 298 \
--gases CO2 N2 \
--y 0.15 0.85 \
--p-total-bar 1.0 \
--output-dir ./results/multi_gcmc
Key Parameters
--cif: Path to the relaxed host framework.--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, required by some models (omolfor UMA and MACE-MH).--steps: Number of Monte Carlo steps (minimum 50,000 recommended for equilibration).--temperature-K: Sim temperature.--pressure-bar(Single): Gas pressure in bar.--p-total-bar(Multi): Total mixture pressure in bar.--gases/--y(Multi): Species list and corresponding mole fractions in the vapor phase.
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/multi_gas/input_configs.yaml 380 B
- examples/README.md 2.2 KB
- examples/single_gas/input_configs.yaml 307 B
- examples/test_gcmc.sh 818 B runs code
- scripts/ase_mc/__init__.py 320 B runs code
- scripts/ase_mc/AtomisticSkills.code-workspace 74 B
- scripts/ase_mc/ensembles.py 12 KB runs code
- scripts/ase_mc/logger.py 2.6 KB runs code
- scripts/ase_mc/mc.py 8.9 KB runs code
- scripts/ase_mc/moves.py 32 KB runs code
- scripts/ase_mc/moveset.py 3.3 KB runs code
- scripts/ase_mc/utility.py 4.4 KB runs code
- scripts/gcmc_common.py 46 KB runs code
- scripts/run_gcmc_multi.py 18 KB runs code
- scripts/run_gcmc.py 12 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.
- 6d ago First seen · 90 lines · 30 tokens per session scan A 92be87844bba
chem-sorption-gcmc is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,040 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
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…
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…
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…
molfeat
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
pytdc
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.