synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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 synthetic-sciences/openscience --skill atomistic-workflowsgit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/atomistic-workflows)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/atomistic-workflows"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/atomistic-workflows/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/synthetic-sciences/openscience/atomistic-workflows"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/atomistic-workflows.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 | $0.00138 | $0.02327 |
| Opus 5.5 | $0.00055 | $0.00931 |
| Sonnet 5.5 | $0.00028 | $0.00465 |
| Haiku 4.5 | $0.00014 | $0.00233 |
Grade A, and why
atomistic-workflows 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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atomistic workflows
An atomistic number is defined only together with its code, units, convergence parameters and stopping criteria; a "DFT energy" without k-mesh and cutoff cannot be reproduced.
ASE
Atoms(symbols, positions, cell, pbc);ase.io.readandwriteconvert between formats (read("traj.xyz", index=":")for all frames). Internal units are eV and angstrom;ase.unitssuppliesfs,kB,HartreeandBohrfor conversion (the native time unit is about 10.18 fs, so always multiply byunits.fs). Attach a calculator withatoms.calc = ...(EMT,ase.calculators.vasp.Vasp,espresso.Espresso,lammpslib.LAMMPSlib, a machine-learned potential), thenget_potential_energy(),get_forces(),get_stress()(eV per cubic angstrom).- Relaxation:
from ase.optimize import BFGS, LBFGS, FIRE, thenopt = BFGS(atoms, trajectory="opt.traj", logfile="opt.log")andopt.run(fmax=0.01, steps=500).fmaxis the largest force on any atom in eV per angstrom: 0.05 is loose, 0.01 standard, 0.001 for phonons. Relax the cell withFrechetCellFilterfromase.filterswrapped around the atoms; fix atoms withFixAtoms. Check thatopt.runreturned converged rather than exhaustingsteps. - MD:
MaxwellBoltzmannDistribution(atoms, temperature_K=300)andStationary(atoms), thenLangevin(atoms, 1.0 * units.fs, temperature_K=300, friction=0.01 / units.fs)orNVTBerendsen,NPT;dyn.run(steps)with a trajectory attached; record the seed.
pymatgen
Structure.from_file("POSCAR")or a CIF;structure.to(filename="out.cif"). Symmetry viaSpacegroupAnalyzer(structure, symprec=0.01, angle_tolerance=5)withget_space_group_symbol()andget_conventional_standard_structure();symprecchanges the answer (0.01 angstrom strict, 0.1 loose), so report it.Kpoints.automatic_density(structure, kppa=1000)sets k-mesh density per reciprocal atom.Vasprun("vasprun.xml")exposesfinal_energy,converged_electronicandconverged_ionic; read both flags.AseAtomsAdaptorbridges to ASE.- Materials Project:
from mp_api.client import MPRester, thenmpr.materials.summary.search(formula="Fe2O3", fields=[...])with fields such asmaterial_id,structure,energy_above_hullandband_gap. Database energies carry their own functional and correction scheme; never mix them with raw energies from your own runs without applying the same corrections. Record the database release and thematerial_id.
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.
- 1mo ago First seen · 121 lines · 138 tokens per session scan A dc92ff1e4194
atomistic-workflows is a skill published in the GitHub repository synthetic-sciences/openscience (4,025 stars, last pushed today), licensed Apache-2.0. It adds 138 tokens to every session and 2,327 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
arxiv
Search arXiv papers by keyword, author, category, or ID.
research-paper-writing
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
paper-plot-stub
Plot a results CSV (x, ybaseline, yours) as a two-line matplotlib chart and write a PDF. Demo-only.
knowledge-extension-ecosystem-lsp-code-intelligence
A codebase guide to LSP, the standard protocol behind editor features such as symbol queries, file diagnostics, and language-aware code information.