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 protein-binder-designgit 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/protein-binder-design)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/protein-binder-design"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/protein-binder-design/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/protein-binder-design"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/protein-binder-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00959 |
| Opus 5.5 | $0.00014 | $0.00384 |
| Sonnet 5.5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
protein-binder-design 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protein binder design
Use this workflow for an end-to-end binder campaign: target preparation, backbone generation, sequence design, independent complex prediction, interface scoring, diversity analysis, ranking, structures, and a reproducible report.
The reviewed upstream source is NVIDIA BioNeMo Agent Toolkit commit 0e67a612e4045f007e38fa77adc8f3ebfc5616b6. Its canonical workflows are workflows/generative-protein-binder-design/protein-binder-design and workflows/generative-protein-binder-design/complexa-binder-design (skills/bionemo-agent-toolkit/ is the generated aggregate). Record that commit and every model/version actually used.
This adapted skill is self-contained; it has no local helper files or references to inspect. Resolve upstream details through the pinned public repository only when the active route needs them.
For a single hosted prediction (Boltz-2, OpenFold, DiffDock, ProteinMPNN, RFdiffusion) with the user's own NVIDIA API key, load bionemo-nims instead: it goes through the scientific_capability tool and needs no Modal target. This skill is the self-hosted campaign route.
Start with capabilities
- Call
compute_jobwithaction: "targets"once. Respect the returned Modal network and credential capabilities. - Use the configured Modal target for detached GPU work. Never call the Modal CLI/SDK directly and never place credentials in commands.
- If
nvidia_nimis reported available bytargets, the supported BioNeMo NIM funnel is RFdiffusion backbones -> ProteinMPNN sequences -> Boltz2 or validated OpenFold3 complexes -> self-consistency and interface ranking. Never submit an unavailable secret reference merely to probe it. - If a reviewed NGC/private-image route is actually available, Proteina-Complexa may co-design sequence and structure before an independent Boltz2/OpenFold3 refold. Do not claim this route when the target reports no private-registry support.
- If NVIDIA credentials are absent, do not stop merely because the branded endpoints are unavailable. Inspect the pinned toolkit workflow, then test whether the corresponding public open-source RFdiffusion, ProteinMPNN, and Boltz releases can be installed and run on Modal. Proceed only when exact public sources and weights are accessible under their licenses. Label this clearly as an open-source adaptation of the BioNeMo workflow, not a hosted NIM run.
- If neither route can execute, return a precise preflight blocker and the smallest missing setup. Never fabricate structures or scores.
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 Changed · +10 lines 9dabe01d7799
- 1mo ago First seen · 42 lines · 35 tokens per session scan A ea1f90c93e8a
protein-binder-design is a skill published in the GitHub repository synthetic-sciences/openscience (4,249 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 959 once invoked, about $0.0001 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 2026-08-30.
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.