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-phewasgit 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-phewas)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-phewas"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-phewas/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-phewas"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-phewas.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 | $0.00000 | $0.02567 |
| Opus 5.5 | $0.00000 | $0.01027 |
| Sonnet 5.5 | $0.00000 | $0.00513 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
tooluniverse-phewas 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 1mo 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.
Cross-Biobank PheWAS & Replication
A PheWAS is the inverse of a GWAS: a GWAS fixes a phenotype and scans variants; a PheWAS fixes a variant (or gene) and scans the entire phenome. The scientific payoff of running it across several biobanks is replication and ancestry resolution — an association seen in one population that reappears in another (with the same effect direction) is far more credible, while one that appears only in East-Asian cohorts may reflect ancestry-specific LD, allele frequency, or biology.
This skill orchestrates one variant/gene across four ancestries plus a gene-burden layer. Look up, don't guess — never assert a variant's phenotype associations or effect sizes from memory; the whole point is the live cross-biobank numbers.
The biobank panel
| Tool | Biobank | Ancestry | Build | Evidence type |
|---|---|---|---|---|
UKBTOPMed_phewas_by_variant |
UKB-TOPMed | European (UK) | GRCh38 | per-phenotype assoc (phecodes, ~1,400) |
FinnGen_get_variant_finemapping |
FinnGen | Finnish | GRCh38 | credible-set membership (fine-mapping) |
BioBankJapan_phewas_by_variant |
BioBank Japan | Japanese | GRCh37 | per-phenotype assoc |
TPMI_phewas_by_variant |
TPMI | Taiwanese (Han) | GRCh38 | per-phenotype assoc (ICD-based) |
Genebass_gene_burden_phewas |
Genebass (UKB exomes) | European | GRCh38 | gene-level rare-variant burden |
The four *_phewas_by_variant tools (UKB-TOPMed, BBJ, TPMI) and Genebass_gene_burden_phewas accept an rsID (Genebass also accepts a gene symbol) and resolve coordinates themselves via Ensembl, picking the correct allele for multi-allelic SNPs; the build difference between BBJ-GRCh37 and the others is handled internally — just pass the rsID. You normally do not need to hand-convert coordinates for these.
FinnGen_get_variant_finemapping is the exception: it does NOT accept an rsID. It requires an explicit GRCh38 variant string in chr:pos:ref:alt format (e.g. "10:112998590:C:T"). Resolve the rsID to GRCh38 coordinates first — the simplest way is to read the variant/rsids field returned by the UKB-TOPMed (GRCh38) call, then pass that coordinate string to FinnGen.
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.
- 1mo ago First seen · 102 lines · 0 tokens per session scan A 55b8479835f8
tooluniverse-phewas is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,567 tokens. 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.