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-gene-disease-associationgit 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-gene-disease-association)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-gene-disease-association"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gene-disease-association/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-gene-disease-association"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gene-disease-association.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 | $0.00121 | $0.03733 |
| Opus 5.5 | $0.00048 | $0.01493 |
| Sonnet 5.5 | $0.00024 | $0.00747 |
| Haiku 4.5 | $0.00012 | $0.00373 |
Grade A, and why
tooluniverse-gene-disease-association 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gene-Disease Association Analysis
Systematically query and compare gene-disease associations across 6+ databases to produce a unified, evidence-graded report. Cross-references DisGeNET scores, OpenTargets evidence, Monarch Initiative cross-species data, OMIM Mendelian mappings, GenCC curated validity, and Orphanet rare disease links.
IMPORTANT: Always use English gene names and disease terms in tool calls. Respond in the user's language.
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
Core Principles
- Report-first approach - Create report file FIRST, then populate progressively
- Multi-database triangulation - Query 4+ sources minimum, cross-validate
- Quantitative scoring - Report numeric scores from each database
- Concordance analysis - Count how many databases support each association and reason about independence
- Evidence reasoning - Assess each association using evidence hierarchy, concordance, and mechanism plausibility
- Mendelian vs complex - Distinguish monogenic (OMIM/Orphanet) from complex (GWAS/DisGeNET) associations
- Negative results documented - "No association found in [database]" is informative
Workflow Overview
Phase 1: Gene/Disease Identification & ID Resolution
Resolve gene symbol to Ensembl ID, HGNC CURIE, MIM number
OR resolve disease name to UMLS CUI, EFO ID, MONDO ID, ORPHA code
|
Phase 2: DisGeNET Associations (scored, multi-evidence)
Gene-disease association scores with evidence type filtering
|
Phase 3: OpenTargets Associations (integrated evidence)
Disease phenotypes and genetic associations from OpenTargets
|
Phase 4: Monarch Initiative (cross-species evidence)
Gene-disease associations integrating OMIM, ClinVar, model organisms
|
Phase 5: Mendelian Disease Evidence (curated)
OMIM gene-disease map, GenCC validity classifications, Orphanet rare diseases,
Gene2Phenotype (G2P) clinical-panel assertions
|
Phase 6: Variant-Disease Associations (optional, if gene query)
DisGeNET variant-disease links, ClinVar pathogenic variants
|
Phase 7: Evidence Synthesis
Unified table, concordance scoring, confidence levels, final report
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 Changed · +35 lines · +31 tokens per session 47cf1a0b0859
- 1mo ago First seen · 217 lines · 90 tokens per session scan A 1f7672828c59
tooluniverse-gene-disease-association is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 3,733 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 2026-09-03.
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.