Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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-thermochemistry)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-thermochemistry"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-thermochemistry.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 | $0.00055 | $0.01665 |
| Opus 5 | $0.00028 | $0.00833 |
| Sonnet 5 | $0.00011 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
chem-thermochemistry scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gas-Phase Thermochemistry Skill
Goal
Compute temperature-dependent thermodynamic quantities — enthalpy ($H$), entropy ($S$), and Gibbs free energy ($G$) — for gas-phase molecules, and reaction thermochemistry ($\Delta H$, $\Delta S$, $\Delta G$) for balanced chemical reactions, using Machine Learning Interatomic Potentials (MLIPs) with ASE's ideal-gas / rigid-rotor / harmonic-oscillator (IGRRHO) framework.
[!IMPORTANT] This skill extends chem-vibration. It reuses the same MLIP-powered Hessian calculation and adds thermodynamic post-processing via
ase.thermochemistry.IdealGasThermo.
Background
The IGRRHO partition function decomposes into independent translational, rotational, vibrational, and electronic contributions:
$$q = q_\text{trans} \cdot q_\text{rot} \cdot q_\text{vib} \cdot q_\text{elec}$$
From the partition function, thermodynamic quantities at temperature $T$ and pressure $P$ are:
- Enthalpy: $H(T) = E_\text{pot} + E_\text{ZPE} + \sum_i \frac{h\nu_i}{e^{h\nu_i/k_BT}-1} + k_BT$ (+ rotational and translational terms)
- Entropy: $S(T,P) = S_\text{trans} + S_\text{rot} + S_\text{vib} + S_\text{elec}$
- Gibbs free energy: $G(T,P) = H(T) - TS(T,P)$
For a balanced reaction, $\Delta X = \sum_\text{products} n_i X_i - \sum_\text{reactants} n_j X_j$ where $X = H, S, G$.
1. Prerequisites
- An MLIP wrapper must be available (
MACEWrapper,MatGLWrapper, orFAIRCHEMWrapper). - ASE must be installed (provides
ase.thermochemistry.IdealGasThermo). - Structures must be molecules or gas-phase species (non-periodic).
2. Choosing a Foundation Potential
Refer to the foundation-potentials skill for model selection.
[!IMPORTANT] For molecular thermochemistry, use models with good force accuracy (e.g.,
MACE-OMAT-0-small,MACE-MH-1withomolhead). Accurate forces are critical for reliable vibrational frequencies and thus thermodynamic quantities.
What ships with it
60 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/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/relax.log 210 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0x-.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0x+.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0y-.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0y+.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0z-.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.0z+.json 188 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1x-.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1x+.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1y-.json 194 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1y+.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1z-.json 182 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.1z+.json 147 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_H2/vib/cache.eq.json 192 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/relax.log 369 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0x-.json 153 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0x+.json 192 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0y-.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0y+.json 190 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0z-.json 186 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.0z+.json 151 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1x-.json 153 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1x+.json 153 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1y-.json 192 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1y+.json 153 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1z-.json 151 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.1z+.json 188 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_N2/vib/cache.eq.json 153 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/relax.log 369 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0x-.json 307 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0x+.json 307 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0y-.json 308 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0y+.json 308 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0z-.json 316 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.0z+.json 317 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1x-.json 319 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1x+.json 318 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1y-.json 314 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1y+.json 317 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1z-.json 317 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.1z+.json 316 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2x-.json 315 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2x+.json 314 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2y-.json 314 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2y+.json 310 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2z-.json 317 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.2z+.json 315 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3x-.json 314 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3x+.json 315 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3y-.json 315 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3y+.json 313 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3z-.json 315 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.3z+.json 316 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/species_NH3/vib/cache.eq.json 330 B
- examples/benchmarks_uma-s-1p1-omol/ammonia_synthesis/thermochemistry_results.json 5.1 KB
- examples/benchmarks_uma-s-1p1-omol/methane_combustion/species_CH4/relax.log 210 B
- examples/benchmarks_uma-s-1p1-omol/methane_combustion/species_CH4/vib/cache.0x-.json 375 B
- examples/benchmarks_uma-s-1p1-omol/methane_combustion/species_CH4/vib/cache.0x+.json 374 B
- examples/benchmarks_uma-s-1p1-omol/methane_combustion/species_CH4/vib/cache.0y-.json 376 B
- examples/benchmarks_uma-s-1p1-omol/methane_combustion/species_CH4/vib/cache.0y+.json 376 B
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 · 138 lines · 55 tokens per session scan A 6b4fa13991be
chem-thermochemistry is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,665 once invoked, about $0.0003 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…
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.
torchdrug
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem…