ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
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 mims-harvard/ToolUniverse --skill tooluniverse-bioinformatics-resource-discoverygit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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/mims-harvard/tooluniverse/tooluniverse-bioinformatics-resource-discovery)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-bioinformatics-resource-discovery"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-bioinformatics-resource-discovery/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/mims-harvard/tooluniverse/tooluniverse-bioinformatics-resource-discovery"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-bioinformatics-resource-discovery.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 | $0.00158 | $0.02563 |
| Opus 5.5 | $0.00063 | $0.01025 |
| Sonnet 5.5 | $0.00032 | $0.00513 |
| Haiku 4.5 | $0.00016 | $0.00256 |
Grade A, and why
tooluniverse-bioinformatics-resource-discovery 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bioinformatics Resource Discovery
Answers "what already exists for this task" — software, APIs, R packages, or training material — before writing new analysis code, choosing an nf-core pipeline, or wrapping a new REST API by hand.
LOOK UP, DON'T GUESS: Never assert that a tool/package/API does or doesn't exist for a task from memory. These 5 registries are live and current — search them.
When to Use This Skill
- "Is there existing software for [bioinformatics task]?" -> bio.tools
- "What biomedical APIs exist for [domain], and where's the base URL/spec?" -> SmartAPI
- "Is there a tutorial/course on [technique]?" -> ELIXIR TeSS
- "What R package does [analysis] in Bioconductor?" -> Bioconductor
- "What does CRAN package X do / what version / what does it depend on?" -> CRAN
NOT for: actually running an nf-core pipeline once you've picked one (-> tooluniverse-nfcore-pipelines); resolving IDs between databases (-> tooluniverse-sequence-retrieval's Bioregistry/Identifiers.org/TogoID section); retrieving biological data itself (sequences, structures, expression) rather than software/APIs about it.
1. bio.tools — Bioinformatics Software & Database Registry
ELIXIR's registry of 30,000+ bioinformatics tools, web services, and databases.
| Tool | Use for | Key params |
|---|---|---|
BioTools_search |
Free-text keyword search across name/description/topics | q, page, size (max 50) |
BioTools_get_tool |
Full record for a known tool by its bio.tools ID | biotoolsID |
BioTools_search_by_topic |
Filter by EDAM scientific topic (e.g. "Genomics", "Proteomics") | topic, page, size |
BioTools_search_by_operation |
Filter by EDAM operation — what the tool DOES (e.g. "Sequence alignment", "Variant calling") | operation, page, size |
BioTools_search_by_type |
Filter by resource type | toolType (e.g. "Database portal"), q, page, size |
Which tool for "what software does X?": start with BioTools_search (free text). Results are relevance-ranked (sort=score): q="blast" returns BLAST first and q="variant calling" returns the GATK tools first. The _by_topic / _by_operation / _by_type filters are for narrowing and counting: they return the exact EDAM set (multi-word terms are sent as exact phrases, so operation="Variant calling" matches 1,015 tools, not the 4,165 a loose match gives), but upstream's ordering within a filter is not by relevance, so do not read the first few hits as "the best tools". Combine both: read the count from a filter, then rank with a text query.
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.
- 10d ago First seen · 102 lines · 158 tokens per session scan A afde8eabf656
tooluniverse-bioinformatics-resource-discovery is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 158 tokens to every session and 2,563 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 2026-10-07.
Other skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.