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-kegg-disease-druggit 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-kegg-disease-drug)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-kegg-disease-drug"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-kegg-disease-drug/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-kegg-disease-drug"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-kegg-disease-drug.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 | $0.00104 | $0.02740 |
| Opus 5.5 | $0.00042 | $0.01096 |
| Sonnet 5.5 | $0.00021 | $0.00548 |
| Haiku 4.5 | $0.00010 | $0.00274 |
Grade A, and why
tooluniverse-kegg-disease-drug 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KEGG Disease-Drug-Variant Research
Systematic exploration of disease-drug-variant relationships using KEGG's curated databases.
Reasoning Strategy
KEGG maps diseases to pathways and drugs to targets, but the real value is in the connections — which pathways link a disease gene to a drug target? This is a network question, not a simple lookup. A gene appearing in a KEGG disease entry has been editorially reviewed as mechanistically relevant; a drug entry with a confirmed target is more reliable than one inferred from pathway co-membership. When using KEGG for drug repurposing, always ask: is the drug-target relationship direct (the drug binds the gene product) or indirect (the drug affects a pathway that contains the gene)? Direct relationships are far stronger evidence. KEGG coverage is not exhaustive — absence from KEGG does not mean absence of biological involvement; complement with Reactome, WikiPathways, or CTD for broader coverage. ID namespace differences are a frequent source of errors: KEGG uses its own gene IDs (e.g., hsa:7157 for TP53), so always convert external IDs before querying KEGG-specific tools.
LOOK UP DON'T GUESS: Do not assume KEGG disease IDs, drug IDs, or gene IDs from memory — always search first with KEGG_search_disease, KEGG_search_drug, or KEGG_convert_ids. Do not assume which pathways link a disease gene to a drug; use KEGG_link_entries and KEGG_get_network to retrieve the actual connections.
When to Use
- "What genes are associated with [disease] in KEGG?"
- "Find KEGG drugs targeting [gene/pathway]"
- "What variants are linked to [disease] in KEGG?"
- "Show the KEGG disease-gene-drug network for [condition]"
- "Find drugs targeting BRAF variants in cancer"
Tool Inventory (12 tools)
| Tool | Key Params | Returns |
|---|---|---|
| KEGG_search_disease | keyword |
Disease entries matching keyword |
| KEGG_get_disease | disease_id (e.g., "H00004") |
Disease details: genes, drugs, pathways |
| KEGG_get_disease_genes | disease_id |
All genes for a disease |
| KEGG_search_drug | keyword |
Drug entries matching keyword |
| KEGG_get_drug | drug_id (e.g., "D00123") |
Drug details: targets, pathways, metabolism |
| KEGG_get_drug_targets | drug_id |
Molecular targets for a drug |
| KEGG_search_network | keyword |
Network entries (disease-gene-drug) |
| KEGG_get_network | network_id |
Network details and relationships |
| KEGG_search_variant | keyword |
Variant entries matching keyword |
| KEGG_get_variant | variant_id |
Variant details and disease associations |
| KEGG_convert_ids | kegg_id (IDs joined with +), target_db |
Convert KEGG gene/compound IDs to external IDs (uniprot, ncbi-geneid, ncbi-proteinid, chebi, pubchem); KEGG → external only |
| KEGG_link_entries | source, target |
Find cross-database relationships (e.g., all genes linked to a pathway, all drugs linked to a disease) |
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 · +3 lines 2de4a6af019e
- 1mo ago First seen · 196 lines · 104 tokens per session scan A de90defb57f1
tooluniverse-kegg-disease-drug is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 2,740 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.