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-rare-disease-genomicsgit 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-rare-disease-genomics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-rare-disease-genomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-rare-disease-genomics/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-rare-disease-genomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-rare-disease-genomics.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 | $0.00083 | $0.04662 |
| Opus 5.5 | $0.00033 | $0.01865 |
| Sonnet 5.5 | $0.00017 | $0.00932 |
| Haiku 4.5 | $0.00008 | $0.00466 |
Grade A, and why
tooluniverse-rare-disease-genomics 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 — 293 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.
Rare Disease Genomics Research
Rare Disease Investigation Strategy
The order of investigation matters: phenotype -> disease -> gene -> variant, not the reverse. When starting from a gene, reverse it: gene -> diseases -> expected phenotypes -> does the patient match?
Resist the urge to skip to ClinVar immediately. A "Pathogenic" ClinVar entry is only meaningful if the gene is actually causative for the disease in question with the right inheritance mode.
Variant Prioritization Reasoning (CRITICAL)
LOOK UP DON'T GUESS -- when uncertain about any gene, variant, or disease association, search the database. Do not rely on memory.
How to filter thousands of variants down to one causal variant
-
Inheritance pattern first -- Check Orphanet_get_natural_history for inheritance mode. This determines your filtering strategy:
- Autosomal dominant: look for heterozygous variants in ONE copy; de novo if unaffected parents
- Autosomal recessive: need TWO hits (homozygous or compound heterozygous); check carrier parents
- X-linked recessive: hemizygous males affected; carrier females usually unaffected
- Mitochondrial: maternal inheritance only; heteroplasmy complicates penetrance
-
Allele frequency filter -- Rare disease variants should be RARE in population:
- Dominant diseases: allele frequency < 0.001 (1 in 1,000) in gnomAD
- Recessive diseases: allele frequency < 0.01 (1 in 100) for carriers
- Use gnomAD via Ensembl VEP annotation or OpenTargets variant info to check frequency
- LOOK UP the actual frequency -- do not assume a variant is rare
-
Consequence hierarchy -- Prioritize by predicted impact:
- Loss-of-function (frameshift, nonsense, splice-site): strongest candidates
- Missense in conserved domain: strong if in known functional domain
- Synonymous / intronic: usually benign unless at splice junction -- but "usually" is doing real work: a deep intronic variant can still be pathogenic by creating a cryptic splice site far from the canonical boundary, which consequence filtering alone won't flag. If a deep intronic or otherwise unannotated variant survives Steps 1-2 (rare, correct inheritance, phenotype match) despite a bland consequence label, don't dismiss it yet -- see
tooluniverse-regulatory-variant-analysisfor a direct sequence-based check on whether it actually disrupts splicing, expression, or another regulatory readout.
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 Changed · +2 lines 374cdb7263dc
- 1mo ago Changed bdf28f517fbe
- 1mo ago First seen · 291 lines · 83 tokens per session scan A 47b4f3f5b88e
tooluniverse-rare-disease-genomics 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 4,662 once invoked, about $0.0003 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.