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-adverse-event-detectiongit 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-adverse-event-detection)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-adverse-event-detection"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-adverse-event-detection/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-adverse-event-detection"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-adverse-event-detection.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 | $0.00083 | $0.02987 |
| Opus 5 | $0.00042 | $0.01494 |
| Sonnet 5 | $0.00017 | $0.00597 |
| Haiku 4.5 | $0.00008 | $0.00299 |
Grade A, and why
tooluniverse-adverse-event-detection 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 12d 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 — 174 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.
Adverse Drug Event Signal Detection & Analysis
Automated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.
KEY PRINCIPLES:
- Signal quantification first - Every adverse event must have PRR/ROR/IC with confidence intervals
- Serious events priority - Deaths, hospitalizations, life-threatening events always analyzed first
- Multi-source triangulation - FAERS + FDA labels + OpenTargets + DrugBank + literature
- Context-aware assessment - Distinguish drug-specific vs class-wide vs confounding signals
- Report-first approach - Create report file FIRST, update progressively
- Evidence grading mandatory - T1 (regulatory/boxed warning) through T4 (computational)
- English-first queries - Always use English drug names in tool calls, respond in user's language
REASONING STRATEGY — Start Here: Start with the signal: What adverse event was reported more than expected? (PRR >= 2.0, N >= 3, lower CI > 1.0 is the threshold). Then ask three questions in order:
- Biologically plausible? Given the drug's mechanism of action and targets, does this adverse event make sense? An off-target kinase inhibitor causing cardiac events is plausible; a topical agent causing systemic toxicity needs more scrutiny. LOOK UP DON'T GUESS — use
OpenTargets_get_drug_mechanisms_of_action_by_chemblIdanddrugbank_get_targets_by_drug_name_or_drugbank_idto check targets before asserting plausibility. - Timing consistent? Acute reactions (within hours/days) suggest immune or direct pharmacologic mechanism. Delayed reactions (weeks/months) suggest cumulative toxicity or idiosyncratic response. Check FAERS time-to-onset distribution.
- Could confounders explain it? Patients taking this drug likely have the underlying disease — compare against background rate in that population, not the general population. Class-wide signals (appearing for all drugs in the class) suggest mechanism-based rather than molecule-specific toxicity.
What ships with it
4 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.
- 12d ago First seen · 174 lines · 83 tokens per session scan A d901125b646f
tooluniverse-adverse-event-detection is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 2,987 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
dfam-check
Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
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.
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.
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.