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-variant-to-mechanismgit 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-variant-to-mechanism)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-variant-to-mechanism"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-variant-to-mechanism/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-variant-to-mechanism"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-variant-to-mechanism.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 208 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00097 | $0.04599 |
| Opus 5 | $0.00048 | $0.02299 |
| Sonnet 5 | $0.00019 | $0.00920 |
| Haiku 4.5 | $0.00010 | $0.00460 |
Grade A, and why
tooluniverse-variant-to-mechanism 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 8d 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.
vep = requests.get(f"https://rest.ensembl.org/vep/human/id/{rsid}?content-type=application/json").json() How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Variant-to-Mechanism Analysis Skill
Trace the full causal chain from a genetic variant to its disease mechanism: regulatory context, target gene(s), molecular pathways, and phenotypic consequences. Integrates 7+ databases across 3 evidence layers (regulatory, molecular, disease) to build an evidence-graded mechanistic model.
IMPORTANT: Always use English 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.
When to Use This Skill
Apply when users:
- Ask "how does rs7903146 cause type 2 diabetes?"
- Want to trace a GWAS variant to its biological mechanism
- Need to connect a non-coding variant to downstream pathways
- Ask "what gene does this variant affect and through what pathway?"
- Want a mechanistic narrative for a regulatory variant
- Need to identify the causal gene for a GWAS locus
- Ask "what is the functional impact of this intronic SNP?"
NOT for (use other skills instead):
- Coding variant pathogenicity / ACMG classification -> Use
tooluniverse-variant-interpretation - Pure regulatory element annotation without mechanism -> Use
tooluniverse-regulatory-genomics - Pure GWAS hit listing without mechanism -> Use
tooluniverse-gwas-snp-interpretation - Pharmacogenomic variant annotation -> Use
tooluniverse-pharmacogenomics - Gene-disease association without variant context -> Use
tooluniverse-gene-disease-association
Input Parameters
| Parameter | Required | Description | Example |
|---|---|---|---|
| variant | Yes | rsID or genomic coordinates | "rs7903146" or "10:112998590:C:T" |
| trait | No | Disease/trait context (helps prioritize) | "type 2 diabetes" |
| tissue | No | Tissue of interest for eQTL/expression | "pancreas" |
Workflow Overview
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.
- 8d ago First seen · 378 lines · 97 tokens per session scan A d1c30cb5d81f
tooluniverse-variant-to-mechanism is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 4,599 once invoked, about $0.0005 per session on Opus 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
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.
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
intermediate-outputs
Use this skill when working with circuit discovery in language models, mechanistic interpretability, activation patching, attribution patching, or Layer-wise Relevance Propagation (LRP) for neural network analysis.
clip-dissect
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…