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 database-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/database-lookup)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/database-lookup"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/database-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/database-lookup"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/database-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 | $0.00050 | $0.06781 |
| Opus 5.5 | $0.00020 | $0.02712 |
| Sonnet 5.5 | $0.00010 | $0.01356 |
| Haiku 4.5 | $0.00005 | $0.00678 |
Grade B, and why
database-lookup scanned grade B with 2 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 29d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| Open Targets | GraphQL endpoint | `curl -X POST -H "Content-Type: application/json" -d '{"query":"..."}' https://api.platform.opentargets.org/api/v4/graphql` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
These databases require HTTP POST and **will not work with WebFetch** (GET-only). Use `curl` via your platform's shell tool instead: This is a copy
95% identical to database-lookup — 95 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Lookup
This skill catalogs 80 public databases with documented API access patterns. Your job is to turn the user's intent into a reproducible retrieval: select the authoritative database(s), make bounded and rate-limited API calls, verify counts when completeness matters, and return results with enough provenance that another agent or human can repeat the lookup.
For complex biomedical retrievals, assume small filtering differences can change downstream conclusions. Prefer deterministic APIs, explicit identifiers, exhaustive pagination, and auditable logs over broad searching or plausible summaries.
Core Workflow
-
Define the retrieval contract — Identify the target entity, accepted identifiers, organism/taxon/build/date constraints, filters, expected output fields, and whether the user needs an exhaustive dataset or a targeted lookup. If a required scientific constraint is missing and affects correctness, ask a clarifying question rather than guessing.
-
Select authoritative database(s) — Use the database selection guide below. Prefer the primary database for the user's intent, then add cross-check databases only for identifier resolution, validation, or known coverage gaps. Do not fan out across many APIs just because they are available.
-
Read the reference file and retrieval contract — Each database has a reference file in
references/with endpoint details, query formats, and example calls. Read the relevant file(s) andreferences/retrieval-contract.mdbefore making API calls. -
Plan filter semantics before calling — Separate filters the API enforces server-side from filters that must be checked locally. Note identifier conversions, fields with ambiguous meanings, pagination strategy, rate limits, and any data-source conventions such as RefSeq vs GenBank or genome build.
-
Make bounded API calls — See the Making API Calls section below. For exhaustive retrievals, count first when the API supports it, estimate cost, paginate or batch until retrieved counts reconcile, and fail visibly if the final dataset is incomplete. Ask for confirmation before a retrieval would exceed 10,000 records, 100 API calls, or the selected API's documented bulk-use guidance.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/addgene.md 960 B
- references/alphafold.md 2.7 KB
- references/alphavantage.md 7.5 KB
- references/bea.md 14 KB
- references/bindingdb.md 2.9 KB
- references/biogrid.md 3.6 KB
- references/bls.md 9.1 KB
- references/brenda.md 2.2 KB
- references/cbioportal.md 7.1 KB
- references/census.md 8.5 KB
- references/chebi.md 3.3 KB
- references/chembl.md 2.3 KB
- references/clinicaltrials.md 3.1 KB
- references/clinpgx.md 1.2 KB
- references/clinvar.md 3.1 KB
- references/cod.md 2.7 KB
- references/cosmic.md 1.4 KB
- references/dailymed.md 1.7 KB
- references/database_selection_guide.md 9.9 KB
- references/datacommons.md 6.9 KB
- references/dbsnp.md 3.2 KB
- references/disgenet.md 1.4 KB
- references/drugbank.md 1.6 KB
- references/ecb.md 6.2 KB
- references/emdb.md 895 B
- references/ena.md 9.5 KB
- references/encode.md 1.5 KB
- references/ensembl.md 14 KB
- references/epa.md 6.3 KB
- references/eurostat.md 7.4 KB
- references/fda.md 1.9 KB
- references/federal-reserve.md 6.7 KB
- references/fred.md 9.9 KB
- references/gene-ontology.md 4.2 KB
- references/geo.md 3.7 KB
- references/gnomad.md 2.9 KB
- references/gtex.md 3.6 KB
- references/gwas-catalog.md 1.4 KB
- references/hca.md 870 B
- references/hpo.md 1.4 KB
- references/human-protein-atlas.md 1.3 KB
- references/interpro.md 3.3 KB
- references/jaspar.md 1.4 KB
- references/kegg.md 2.3 KB
- references/lincs-l1000.md 1.9 KB
- references/materials-project.md 3.3 KB
- references/metabolomics-workbench.md 3.3 KB
- references/monarch.md 1.4 KB
- references/mousemine.md 1.2 KB
- references/myvariant.md 1.5 KB
- references/nasa-exoplanet-archive.md 4.0 KB
- references/nasa.md 3.1 KB
- references/ncbi-gene.md 1.6 KB
- references/ncbi-protein.md 2.9 KB
- references/ncbi-taxonomy.md 3.4 KB
- references/nist.md 3.4 KB
- references/noaa.md 6.4 KB
- references/omim.md 3.2 KB
- references/opentargets.md 8.7 KB
- references/openweathermap.md 6.9 KB
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.
- 29d ago Changed · +5 lines 43c74f6fa638
- 1mo ago First seen · 408 lines · 50 tokens per session scan B 2b7d1b88ee6c
database-lookup is a skill published in the GitHub repository synthetic-sciences/openscience (4,004 stars, last pushed 3d ago), licensed Apache-2.0. It adds 50 tokens to every session and 6,781 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 95% identical to database-lookup, differing in 95 lines, and is treated as a copy.
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.