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-gwas-trait-to-genegit 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-gwas-trait-to-gene)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-gwas-trait-to-gene"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-trait-to-gene/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-gwas-trait-to-gene"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-trait-to-gene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00083 | $0.03220 |
| Opus 5.5 | $0.00033 | $0.01288 |
| Sonnet 5.5 | $0.00017 | $0.00644 |
| Haiku 4.5 | $0.00008 | $0.00322 |
Grade A, and why
tooluniverse-gwas-trait-to-gene scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
assocs = requests.get(f"https://www.ebi.ac.uk/gwas/rest/api/studies/{study_id}/associations").json() How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GWAS Trait-to-Gene Discovery
Nearest gene is often wrong. Use L2G (locus-to-gene) scores from Open Targets which integrate eQTL, chromatin interaction, and distance data. L2G > 0.5 is a strong prediction; positional mapping alone should not be used to claim a causal gene. A single GWAS study with p < 5e-8 is suggestive — replication across independent cohorts is required for high confidence. GWAS hits are associations in the studied population; effect sizes and even the implicated gene can differ across ancestries due to differing LD patterns. Treat gene lists from GWAS as ranked candidates for validation, not confirmed causal genes.
LOOK UP DON'T GUESS: never assume trait-to-gene mappings or L2G scores — always call gwas_search_associations and OpenTargets_get_study_credible_sets to retrieve current data; associations are updated as new GWAS are published.
Discover genes associated with diseases and traits using genome-wide association studies (GWAS)
Overview
This skill enables systematic discovery of genes linked to diseases/traits by analyzing GWAS data from two major resources:
- GWAS Catalog (EBI/NHGRI): Curated catalog of published GWAS with >500,000 associations
- Open Targets Genetics: Fine-mapped GWAS signals with locus-to-gene (L2G) predictions
Use Cases
Clinical Research
- "What genes are associated with type 2 diabetes?"
- "Find genetic risk factors for coronary artery disease"
- "Which genes contribute to Alzheimer's disease susceptibility?"
Drug Target Discovery
- Identify genes with strong genetic evidence for disease causation
- Prioritize targets based on L2G scores and replication across studies
- Find genes with genome-wide significant associations (p < 5e-8)
Functional Genomics
- Map disease-associated variants to candidate genes
- Analyze genetic architecture of complex traits
- Understand polygenic disease mechanisms
Workflow
1. Trait Search → Search GWAS Catalog by disease/trait name
↓
2. SNP Aggregation → Collect genome-wide significant SNPs (p < 5e-8)
↓
3. Gene Mapping → Extract mapped genes from associations
↓
4. Evidence Ranking → Score by p-value, replication, fine-mapping
↓
5. Annotation (Optional) → Add L2G predictions from Open Targets
What ships with it
2 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.
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 · +1 lines 3ac32cf90072
- 1mo ago First seen · 304 lines · 83 tokens per session scan A a6c04b88ba29
tooluniverse-gwas-trait-to-gene is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 3,220 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.