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-compound-retrievalgit 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-compound-retrieval)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-chemical-compound-retrieval"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-chemical-compound-retrieval/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-compound-retrieval"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-chemical-compound-retrieval.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 | $0.00106 | $0.01221 |
| Opus 5 | $0.00053 | $0.00611 |
| Sonnet 5 | $0.00021 | $0.00244 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
tooluniverse-chemical-compound-retrieval 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 13d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chemical Compound Information Retrieval
Retrieve comprehensive chemical compound data with proper disambiguation and cross-database validation.
LOOK UP DON'T GUESS: Never assume a CID, ChEMBL ID, or molecular property value. Always retrieve from PubChem/ChEMBL.
English-first: Always use English compound names in tool calls. Respond in user's language.
Domain Reasoning: Disambiguation
"Aspirin" = one compound. "Vitamin D" = multiple forms (D2/D3/active metabolite). For generic class names (steroids, vitamins, acids), present candidates and confirm before proceeding.
Workflow
Phase 0: Clarify (only if highly ambiguous -- skip for unambiguous names or specific IDs)
Phase 1: Disambiguate → resolve PubChem CID + ChEMBL ID
Phase 2: Retrieve data (silent)
Phase 3: Report compound profile
Phase 1: Disambiguation
# By name
result = tu.tools.PubChem_get_CID_by_compound_name(compound_name=name)
# By SYSTEMATIC (IUPAC) name -> structure, deterministic parser (no DB lookup)
opsin = tu.tools.OPSIN_name_to_structure(name="2-acetoxybenzoic acid")
# Returns {parsed, smiles, inchi, inchikey}; use the SMILES/InChIKey to anchor a
# PubChem_get_CID_by_SMILES lookup. Trade/trivial names give parsed=false -> fall
# back to PubChem_get_CID_by_compound_name for those.
# By SMILES
result = tu.tools.PubChem_get_CID_by_SMILES(smiles=smiles)
# Cross-reference
chembl_result = tu.tools.ChEMBL_search_molecules(query=name, limit=5)
Verify: CID + ChEMBL ID + canonical SMILES + stereochemistry + salt forms.
Phase 2: Data Retrieval
PubChem: PubChem_get_compound_properties_by_CID, PubChemBioAssay_get_assay_summary, PubChemTox_get_acute_effects, PubChem_get_compound_2D_image_by_CID
ChEMBL: ChEMBL_get_compound_record_activities, ChEMBL_get_molecule_targets, ChEMBL_get_assay_activities
Optional: PubChem_get_associated_patents_by_CID, PubChem_search_compounds_by_similarity
Phase 3: Report
Compound Profile with: Identity (CID, ChEMBL ID, IUPAC, SMILES), Chemical Properties (MW, LogP, HBD, HBA, PSA, Lipinski), Bioactivity (targets, IC50/Ki), Drug Info (if approved), Data Sources.
What ships with it
2 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.
- 13d ago First seen · 99 lines · 106 tokens per session scan A 5ce73ce70cb0
tooluniverse-chemical-compound-retrieval is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,221 once invoked, about $0.0005 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.
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.