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 bionemo-nimsgit 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/bionemo-nims)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/bionemo-nims"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/bionemo-nims/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/bionemo-nims"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/bionemo-nims.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 | $0.00126 | $0.01095 |
| Opus 5.5 | $0.00050 | $0.00438 |
| Sonnet 5.5 | $0.00025 | $0.00219 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
bionemo-nims 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVIDIA BioNeMo NIMs (hosted)
The ten BioNeMo NIM adapters run against NVIDIA's hosted endpoints with the user's own
NVIDIA API key. Every request goes through the scientific_capability tool; nothing here
installs software or starts compute. The capability ids are boltz2, openfold2,
openfold3, msa-search, diffdock, proteinmpnn, rfdiffusion, genmol, molmim
and evo2.
Before the first request
scientific_capabilitywithaction: "list"shows the catalog and each entry's maturity.action: "doctor", id: "<id>"says whether the NVIDIA key is connected and the endpoint is reachable. Without a key, stop and tell the user: connect one under Customize → Connectors → NVIDIA API (annvapi-…key from build.nvidia.com); requests are billed to that NVIDIA account under NVIDIA's terms. Do not look for the key in the environment, in compute targets, or in Modal secrets; the hosted route is separate from the self-hosted BioNeMo containers thatprotein-binder-designruns on Modal.action: "describe", id: "<id>"returns the hostedrequest_schema, the endpoint, the API schema version and the terms. Buildpayloadfrom that schema exactly; field names and enumerations differ between NIMs (a sequence list for Boltz-2, a PDB string plus ligand SMILES for DiffDock, an alignment for OpenFold2).
Each request
action: "plan", id, payloadvalidates every cross-field requirement locally. Nothing is sent and nothing is spent. Fix what it reports before going on.action: "start", id, payload, name, purposesends the request. The user sees an approval card bound to this exact request: endpoint, schema version, payload size, request hash and what leaves the device (sequences, structures, ligands). The approval is one-time; a changed payload asks again. Say inpurposewhat the result is for.action: "wait", job_id(orstatus) until it settles; long predictions poll NVIDIA's status endpoint for you.action: "artifacts", job_idlists the delivered files with their SHA-256;reada structure or JSON from there, and save what the user keeps withartifact save_file.- Report the model, the API schema version from
describe, the request hash and the artifact hashes with the result. A predicted structure or pose is a prediction: give its confidence (pLDDT, iptm, DiffDock confidence) and never call it experimental validation.
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 · 75 lines · 126 tokens per session scan A c7776e098198
bionemo-nims is a skill published in the GitHub repository synthetic-sciences/openscience (4,025 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 1,095 once invoked, about $0.0005 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 2026-09-17.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
knowledge-model-and-provider-runtime-provider-resilience-admission-and-observability
A codebase guide for handling unreliable AI provider requests across agents and sessions, including retries, circuit breakers, fair queues, stalled streams, cache tracking, and health checks.
knowledge-model-and-provider-runtime-model-catalog-configuration-and-credentials
A codebase guide for defining AI models and providers, selecting endpoints and credentials, configuring fallback channels, and migrating model identifiers.
knowledge-model-and-provider-runtime
A codebase guide for choosing AI models and providers, sending requests, recovering from failures, and recording runtime information.