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-toxicologygit 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-toxicology)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-toxicology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-toxicology/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-toxicology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-toxicology.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 | $0.00088 | $0.04863 |
| Opus 5.5 | $0.00035 | $0.01945 |
| Sonnet 5.5 | $0.00018 | $0.00973 |
| Haiku 4.5 | $0.00009 | $0.00486 |
Grade A, and why
tooluniverse-toxicology 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toxicology Assessment via Adverse Outcome Pathways & Signal Detection
Systematic toxicology analysis that links molecular initiating events (MIEs) through adverse outcome pathways (AOPs) to apical adverse outcomes, then triangulates with real-world FAERS signals, FDA label data, and toxicogenomic associations.
Domain Reasoning
Toxicity has many mechanisms, and the first interpretive question is temporal: is this acute toxicity (immediate effect from a high dose) or chronic toxicity (cumulative damage from long-term low-dose exposure)? Acute and chronic toxicity operate through different mechanisms — acute hepatotoxicity may reflect direct mitochondrial damage, while chronic hepatotoxicity may involve fibrosis from repeated low-level inflammation. They also have different regulatory frameworks: acute toxicity is captured by LD50 and emergency protocols, while chronic toxicity requires long-term carcinogenicity and repeat-dose studies.
LOOK UP DON'T GUESS
- Adverse outcome pathways for a chemical: query
AOPWiki_list_aopsandAOPWiki_get_aop; do not describe mechanisms from memory. - FAERS adverse event signals: retrieve from
FAERS_count_reactions_by_drug_eventandFAERS_calculate_disproportionality; never estimate PRR values. - FDA label warnings: call
DailyMed_parse_adverse_reactionsand related tools; do not state boxed warnings from memory. - CTD chemical-gene and chemical-disease associations: query
CTD_get_chemical_gene_interactionsandCTD_get_chemical_diseases; do not infer gene targets without database evidence. - EPA CompTox hazard values and ToxCast/Tox21 bioactivity: query
CompTox_get_hazard_dataandCompTox_get_bioactivity_summary/CompTox_get_bioactivity_assays; never estimate an LD50, a hazard classification, or an assay hit-call rate from memory — this is exactly the kind of chemical-specific quantitative data that must come from the database.
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.
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 · +56 lines · +13 tokens per session c3d2f0efd4c2
- 1mo ago First seen · 320 lines · 75 tokens per session scan A 9e0857b2bd29
tooluniverse-toxicology is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 4,863 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.