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 skills add tondevrel/scientific-agent-skills --skill pyscfgit clone --depth 1 https://github.com/tondevrel/scientific-agent-skillsWrote 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/tondevrel/scientific-agent-skills/pyscf)<a href="https://agentmods.dev/skills/tondevrel/scientific-agent-skills/pyscf"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pyscf/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tondevrel/scientific-agent-skills/pyscf"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pyscf.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.09781 |
| Opus 5 | $0.00030 | $0.04890 |
| Sonnet 5 | $0.00012 | $0.01956 |
| Haiku 4.5 | $0.00006 | $0.00978 |
Grade A, and why
pyscf 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 10d 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 — 1,387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PySCF - Quantum Chemistry Framework
Python library for ab initio electronic structure calculations and quantum chemistry.
When to Use
- Running Hartree-Fock (HF) and Density Functional Theory (DFT) calculations
- Calculating molecular energies and gradients
- Optimizing molecular geometries
- Computing post-HF methods (MP2, CCSD, CI, coupled-cluster)
- Analyzing molecular orbitals and electron density
- Calculating excited states (TD-DFT, CI, EOM-CCSD)
- Computing molecular properties (dipole, charges, NMR, IR)
- Performing periodic calculations (solids, surfaces)
- Benchmarking quantum chemistry methods
- Integrating quantum calculations with ML/AI workflows
Reference Documentation
Official docs: https://pyscf.org/
Search patterns: gto.M, scf.RHF, dft.RKS, mp.MP2, optimize, tddft.TDDFT
Core Principles
Use PySCF For
| Task | Module | Example |
|---|---|---|
| Build molecule | gto |
gto.M(atom='H 0 0 0; H 0 0 1') |
| Hartree-Fock | scf |
scf.RHF(mol).run() |
| DFT calculation | dft |
dft.RKS(mol, xc='B3LYP') |
| MP2 correlation | mp |
mp.MP2(mf).run() |
| Coupled-cluster | cc |
cc.CCSD(mf).run() |
| Geometry optimization | geomopt |
optimize(mf) |
| Excited states | tddft |
tddft.TDDFT(mf).run() |
| Periodic systems | pbc |
pbc.gto.Cell() |
Do NOT Use For
- Molecular dynamics simulations (use GROMACS, OpenMM, ASE)
- Very large systems (>1000 atoms) - use semi-empirical or force fields
- Interactive visualization (use PyMOL, VMD)
- High-throughput virtual screening (too slow)
- Real-time quantum simulations
Quick Reference
Installation
# pip (recommended)
pip install pyscf
# With extensions
pip install pyscf[geomopt,dftd3,dmrgscf]
# From conda
conda install -c pyscf pyscf
# Development version
pip install git+https://github.com/pyscf/pyscf
Standard Imports
# Core modules
from pyscf import gto, scf, dft
from pyscf import mp, cc, ci
from pyscf import grad, geomopt
from pyscf import tddft, tdscf
from pyscf import lo, ao2mo
# Tools
from pyscf.tools import molden, cubegen
import numpy as np
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.
- 10d ago First seen · 1,387 lines · 61 tokens per session scan A 6495bc470bc9
pyscf is a skill published in the GitHub repository tondevrel/scientific-agent-skills (21 stars, last pushed 7mo ago), licensed MIT. It adds 61 tokens to every session and 9,781 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
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
bioservices
Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…