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 research-lookupgit 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/research-lookup)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/research-lookup"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/research-lookup/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/research-lookup"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/research-lookup.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 | $0.00095 | $0.00929 |
| Opus 5.5 | $0.00038 | $0.00372 |
| Sonnet 5.5 | $0.00019 | $0.00186 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
research-lookup 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research lookup
A lookup answers one question with the source that answers it. The failure modes are answering from memory with a confident tone, and turning a two-minute question into a survey. Both are avoided by deciding what would settle the question before searching.
Rules
- Decide the settling evidence first. A definition needs the defining source; a number needs the table it came from; "does library X do Y" needs the documentation or the code; "what did paper P find" needs paper P.
- Search where the answer lives. Scholarly claims:
literature search(OpenAlex and arXiv together), thenliterature readwith the DOI or arXiv id and aqueryfor the passage; PubMed, Crossref and the exact API requests are inskills/core/citations/references/apis.md. Software: the project's docs or repository. Current events, prices, availability: research_search. Do not use a general web search for a scholarly claim when the paper itself is one request away. - Read the source, not the snippet. Fetch the page or abstract and quote the sentence or number that answers the question, with its conditions.
- Two sources when the answer is contested or numeric. Agreement settles it; a disagreement is reported as one.
- Stop at the answer. If the question turns out to need a ranked reading of the field, say so and load literature-review instead of expanding this loop.
- Never present recall as lookup. If nothing was fetched, the answer says it comes from background knowledge and how confident that is.
Workflow
- Restate the question in one line and name the evidence that would settle it.
- Make one focused query per source (at most two sources); fetch the best hit.
- Extract the answer with its exact wording, number, units, date and conditions.
- Answer in one to three sentences, then the source links. Add the caveat if the source is a preprint, a blog, a vendor page, or older than the question implies.
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 · +6 lines 609523415379
- 1mo ago First seen · 67 lines · 95 tokens per session scan A 25bcca382784
research-lookup is a skill published in the GitHub repository synthetic-sciences/openscience (4,025 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 929 once invoked, about $0.0004 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 2026-09-14.
Other skills, from other repositories
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.
github-explorer
Explore and summarize popular GitHub projects. Use when the user wants to discover trending GitHub repositories, analyze project details, or get summaries of popular projects.
google-workspace-setup
One-time setup for gws: install, OAuth, scopes, auto-approve.
google-sheets
Google Sheets via gws: read/write cells, append rows, structured batch edits.
attachments
Move bytes between Gini upload space, external URLs, and workspace files. Used by every attachment / file-upload / file-download flow regardless of the target system (Linear, GitHub, S3, Notion, etc.).
google-docs
Google Docs via gws: read, append text, structured batch edits.