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-relaxnpx skills add learningmatter-mit/AtomisticSkills --skill chem-sorption-relaxgit 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-relax)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-sorption-relax"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-sorption-relax.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 | $0.00031 | $0.01131 |
| Opus 5 | $0.00015 | $0.00566 |
| Sonnet 5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
chem-sorption-relax 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chem-sorption-relax
Goal
To process porous frameworks (e.g., MOFs, COFs) for downstream molecular sorption calculations. It checks if the unit cell's interplanar distances are large enough (usually ≥ 12 Å for typical gases) to avoid self-interaction of gas molecules across periodic boundaries. If not, it builds an appropriate supercell. Finally, it uses a standard Machine Learning Interatomic Potential (MLIP) workflow to relax the structure.
Prerequisites
- Input: A framework structure in CIF (or XYZ) format.
- MLIP MCP Tool: A relaxation tool such as
mcp_fairchem_relax_structure,mcp_mace_relax_structure, ormcp_matgl_relax_structure. - Conda environment:
base-agentfor the supercell builder logic, followed by the specific environment for the chosen MLIP (e.g.,fairchem-agent).
Instructions
- Build Supercell (if necessary): Determine if the input framework needs to be expanded. Use the provided utility to read the input CIF, check interplanar distances, build a supercell if they are below the threshold, and save the result.
# Env: base-agent
python .agents/skills/chem-sorption-relax/scripts/build_supercell.py \
--structure path/to/framework.cif \
--min-plane-dist 12.0 \
--output-cif ./out/framework_supercell.cif
[!TIP] If the script output indicates a
1x1x1supercell was created (i.e. no expansion needed), you can just use your original CIF or the output CIF, as they will be identical.
- Relax the Framework: Relax the output structure using the MCP server environment. Ensure that the correct MLIP is loaded first.
# Env: fairchem-agent (via MCP server)
mcp_fairchem_load_model(
model_name="uma-s-1p2",
device="auto"
)
mcp_fairchem_relax_structure(
structure_data="./out/framework_supercell.cif",
fmax=0.05,
steps=500,
optimizer="LBFGS",
relax_cell=True,
output_dir="./out/relaxed_framework"
)
relax_structure.py Parameters
--structure: Path to input CIF or XYZ.--name: Identifier used in output filenames.--calculator: Backend MLIP (fairchem,mace,matgl).--model-name: Named model (e.g.uma-s-1p2) or full path to checkpoint.--task-name: Multi-task head (omol,omat,odac,oc20,omc).--optimizer:LBFGS(default) orFIRE.--fmax: Force convergence threshold in eV/Å (default: 0.05).--steps: Maximum optimizer steps (default: 500).--relax-cell: Relax unit cell (default: True). Use--fixed-cellto fix cell.--output-dir: Directory to save<name>.relaxed.cifandrelax_results.json.
What ships with it
6 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.
- 6d ago First seen · 106 lines · 31 tokens per session scan A 447ecefd6ca5
chem-sorption-relax is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (160 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,131 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…
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…
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…
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.