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-drug-repurposinggit 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-drug-repurposing)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-drug-repurposing"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-repurposing/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-drug-repurposing"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-repurposing.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 | $0.00078 | $0.03067 |
| Opus 5 | $0.00039 | $0.01533 |
| Sonnet 5 | $0.00016 | $0.00613 |
| Haiku 4.5 | $0.00008 | $0.00307 |
Grade A, and why
tooluniverse-drug-repurposing 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug Repurposing with ToolUniverse
Systematically identify and evaluate drug repurposing candidates using multiple computational strategies.
IMPORTANT: Always use English terms in tool calls. Respond in the user's language.
Reasoning Before Searching
Start by asking: WHY might this drug work for a new disease? Three strategies:
- (a) Same target: The drug's primary target is also involved in the new disease. This is the strongest hypothesis — use OpenTargets to check if the target has genetic evidence in both diseases before any other search.
- (b) Off-target activity: The drug has secondary targets or off-target effects that are relevant to the new disease. Check ChEMBL bioactivity data for all known targets of the drug, not just its primary one.
- (c) Shared pathways: The original indication and new disease share molecular pathways, even if the target itself is not genetically linked. Use Reactome and STRING to compare pathway overlap between diseases.
Each strategy uses different tools and has different evidentiary weight. Identify which strategy applies FIRST, then choose the corresponding workflow below. Do not run all three strategies blindly — reason about which is most plausible given the drug's mechanism.
LOOK UP DON'T GUESS: Never assume a drug hits a target, never assume a target is disease-relevant, never assume pathway overlap. Verify each link with tool calls.
Core Strategies
- Target-Based: Disease targets -> Find drugs that modulate those targets
- Compound-Based: Approved drugs -> Find new disease indications
- Disease-Driven: Disease -> Targets -> Match to existing drugs
Workflow Overview
Phase 1: Disease & Target Analysis
Get disease info (OpenTargets), find associated targets, get target details
Phase 2: Drug Discovery
Search DrugBank, DGIdb, ChEMBL for drugs targeting disease-associated genes
Get drug details, indications, pharmacology
Phase 3: Safety & Feasibility Assessment
FDA warnings, FAERS adverse events, drug interactions, ADMET predictions
Phase 4: Literature Evidence
PubMed, Europe PMC, clinical trials for existing evidence
Phase 5: Scoring & Ranking
Composite score: target association + safety + literature + drug properties
What ships with it
5 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 · 247 lines · 78 tokens per session scan A b399a42d329f
tooluniverse-drug-repurposing is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 3,067 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.