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-finemappinggit 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-finemapping)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-gwas-finemapping"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-finemapping/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-finemapping"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-finemapping.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 | $0.00090 | $0.03279 |
| Opus 5.5 | $0.00036 | $0.01312 |
| Sonnet 5.5 | $0.00018 | $0.00656 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
tooluniverse-gwas-finemapping 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.
**Where to get the raw inputs**: these three tools compute on arrays you supply — they do not fetch summary statistics themselves. `src/tooluniverse/data/gwas_sumstats_tools.json`'s 3 tools (`GWASSumStats_list_studies`, How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COMPUTE, DON'T DESCRIBE
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
GWAS Fine-Mapping & Causal Variant Prioritization
Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions.
Overview
Genome-wide association studies (GWAS) identify genomic regions associated with traits, but linkage disequilibrium (LD) makes it difficult to pinpoint the causal variant. Fine-mapping uses Bayesian statistical methods to compute the posterior probability that each variant is causal, given the GWAS summary statistics.
REASONING STRATEGY — Start Here: Fine-mapping asks: which variant at this locus is CAUSAL? Work through this chain:
- LD structure first — variants in high LD (r² > 0.8) cannot be statistically distinguished from each other. Look up the LD block via Open Targets or the GWAS Catalog before assuming any single variant is the cause.
- Functional annotation breaks LD ties — if two variants have similar posterior probabilities but one is coding (missense, stop-gain) or sits in an active regulatory element (promoter, enhancer), that variant is biologically prioritized. Functional evidence is the tiebreaker.
- eQTL colocalization is the key bridge — a variant that is also a significant eQTL for a nearby gene in the relevant tissue (e.g., a pancreatic islet eQTL for a T2D locus) has a mechanistic story. Look up eQTL evidence via Open Targets L2G scores; don't assume the nearest gene is the effector gene.
This skill provides tools to:
- Prioritize causal variants using fine-mapping posterior probabilities
- Link variants to genes using locus-to-gene (L2G) predictions
- Annotate variants with functional consequences
- Suggest validation strategies based on fine-mapping results
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 · +10 lines e1b39b4f41eb
- 1mo ago First seen · 183 lines · 90 tokens per session scan A 19e6af5e89b2
tooluniverse-gwas-finemapping is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 3,279 once invoked, about $0.0004 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.