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-chemical-sourcinggit 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-chemical-sourcing)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-chemical-sourcing"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-chemical-sourcing/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-chemical-sourcing"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-chemical-sourcing.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 | $0.00086 | $0.03104 |
| Opus 5 | $0.00043 | $0.01552 |
| Sonnet 5 | $0.00017 | $0.00621 |
| Haiku 4.5 | $0.00009 | $0.00310 |
Grade A, and why
tooluniverse-chemical-sourcing 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chemical Compound Sourcing & Procurement
Pipeline for identifying, sourcing, and purchasing chemical compounds from commercial vendors. Resolves compound identity through PubChem/ChEMBL, searches multiple vendor databases (ZINC, Enamine, eMolecules, Mcule), compares pricing and availability, and identifies purchasable analogs when exact compounds are unavailable.
Guiding principles:
- Identity first -- confirm the compound's structure (SMILES, InChI) before searching vendors; names can be ambiguous
- Multi-vendor comparison -- always check multiple sources; pricing and stock vary significantly
- Analog fallback -- if the exact compound is unavailable, search for close analogs
- Purity and quantity awareness -- note catalog purity grades and minimum order quantities
- Structure over name -- vendor searches by SMILES/InChI are more reliable than name searches
- English-first queries -- use English compound names in tool calls
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
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.
When to Use
Typical triggers:
- "Where can I buy [compound]?"
- "Find commercial sources for [SMILES]"
- "Compare prices for [compound] across vendors"
- "Is [compound] commercially available?"
- "Find purchasable analogs of [compound]"
- "I need [quantity] of [compound] -- who sells it?"
- "Search ZINC/Enamine for [compound]"
Not this skill: For ADMET/toxicity assessment, use tooluniverse-admet-prediction. For drug-target interaction analysis, use tooluniverse-drug-target-validation.
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 · 267 lines · 86 tokens per session scan A c231d894b4ca
tooluniverse-chemical-sourcing is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 3,104 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
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.
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.
clip-dissect
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…