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-dft-orca-advanced-calculationWrote 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-dft-orca-advanced-calculation)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-dft-orca-advanced-calculation"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-dft-orca-advanced-calculation.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 | $0.00057 | $0.01989 |
| Opus 5 | $0.00028 | $0.00994 |
| Sonnet 5 | $0.00011 | $0.00398 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
chem-dft-orca-advanced-calculation 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 7d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advanced ORCA Calculation
Goal
Enable advanced ORCA quantum chemistry calculations by constructing a custom ORCA input file from scratch. This skill covers methods and features not available through the SCINE wrapper, including multi-reference methods, excited states, relativistic effects, advanced SCF settings, NMR/EPR properties, and more.
[!IMPORTANT] For standard DFT single-point calculations (energy, gradients, Hessian), use the singlepoint skill instead. For geometry optimization, use the optimization skill. This skill is for cases where those wrappers do not expose the needed method or settings.
1. Prerequisites
- Conda environment:
orca-agentwithaseinstalled (SCINE not required for this skill) - ORCA binary: The environment variable
ORCA_BINARY_PATHmust point to the ORCA executableexport ORCA_BINARY_PATH=/path/to/orca - ORCA documentation: Consult the ORCA 6.1 tutorials for method-specific input syntax, keyword blocks, and recommended settings
2. Workflow
Step 1: Understand the user's request
Identify the target method, property, and system. Determine which ORCA keywords and blocks are needed. If unsure, consult the tutorials linked above for the specific method.
Step 2: Write the ORCA input file
Create a .inp file following ORCA input syntax. Every input file should include:
Mandatory elements:
- A keyword line starting with
!specifying the method, basis set, and job type - A
*xyzfileentry referencesing an external .xyz file
Strongly recommended elements:
%pal nprocs N end: parallelization (always set this to avoid single-core runs)%maxcore M: memory per core in MB (e.g. 4000 for 4 GB per core)
Example — TD-DFT excited states:
! B3LYP def2-TZVP TightSCF
%pal nprocs 4 end
%maxcore 4000
%tddft
NRoots 10
MaxDim 5
end
* xyzfile 0 1 molecule.xyz
What ships with it
4 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.
- 7d ago First seen · 171 lines · 57 tokens per session scan A c3cbd6edc953
chem-dft-orca-advanced-calculation is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 1,989 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
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.