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-drug-discoverygit 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-drug-discovery)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-gwas-drug-discovery"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-drug-discovery/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-drug-discovery"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-gwas-drug-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00093 | $0.02624 |
| Opus 5.5 | $0.00037 | $0.01050 |
| Sonnet 5.5 | $0.00019 | $0.00525 |
| Haiku 4.5 | $0.00009 | $0.00262 |
Grade A, and why
tooluniverse-gwas-drug-discovery 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 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.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GWAS-to-Drug Target Discovery
Transform genome-wide association studies (GWAS) into actionable drug targets and repurposing opportunities.
IMPORTANT: Always use English terms in tool calls. Respond in the user's language.
Overview
This skill bridges genetic discoveries from GWAS with drug development by:
- Identifying genetic risk factors - Finding genes associated with diseases
- Assessing druggability - Evaluating which genes can be targeted by drugs
- Prioritizing targets - Ranking candidates by genetic evidence strength
- Finding existing drugs - Discovering approved/investigational compounds
- Identifying repurposing opportunities - Matching drugs to new indications
Key insight: Targets with genetic support have 2x higher probability of clinical approval (Nelson et al., Nature Genetics 2015).
Reasoning Strategy
GWAS-to-drug translation succeeds when you think causally. A genetic association provides causal direction that observational data cannot: if a loss-of-function variant protects against disease, an inhibitor of that gene's product is the hypothesis to test. The direction of effect (LOF vs. GOF) determines whether you need an inhibitor or an agonist — get this wrong and the drug works backwards. GWAS effect sizes are small (odds ratios of 1.1–1.5 are typical), but the drug effect may be much larger or smaller than the genetic effect; the genetic signal validates the target, not the dose. Always integrate multiple lines of evidence (eQTL colocalization, pQTL, L2G score) before committing to a target, because many GWAS variants tag the causal gene only indirectly.
LOOK UP DON'T GUESS: Do not assume which gene a GWAS variant implicates — use OpenTargets_get_variant_credible_sets or gwas_get_associations_for_snp to get the actual mapped gene and L2G score. Do not guess the direction of effect, odds ratio, or whether a drug already exists for the target; always query the tools.
Workflow Steps
What ships with it
6 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 275ef79244ac
- 1mo ago First seen · 214 lines · 93 tokens per session scan A 3265e4c45925
tooluniverse-gwas-drug-discovery is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 2,624 once invoked, about $0.0004 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.