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-lipidomicsgit 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-lipidomics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-lipidomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-lipidomics/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-lipidomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-lipidomics.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 | $0.00084 | $0.03119 |
| Opus 5.5 | $0.00034 | $0.01248 |
| Sonnet 5.5 | $0.00017 | $0.00624 |
| Haiku 4.5 | $0.00008 | $0.00312 |
Grade A, and why
tooluniverse-lipidomics 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lipidomics Analysis
Integrated pipeline for lipid identification, classification, pathway mapping, and disease association analysis. Distinct from general metabolomics because lipids have unique classification systems (LIPID MAPS), specialized pathways (sphingolipid, eicosanoid, steroid), and disease associations (cardiovascular, neurodegeneration, metabolic syndrome).
Reasoning Strategy
Lipid identification starts with mass spectrometry: the lipid class is determined by the head group fragment mass (e.g., m/z 184 for phosphocholine in positive mode), total chain length and saturation from the precursor exact mass, and individual fatty acid chains from neutral loss or product ion scans. LIPID MAPS classification organizes lipids by chemical structure into 8 categories — knowing the category immediately tells you the likely biological context (sphingolipids → apoptosis/neurodegeneration; glycerophospholipids → membrane remodeling; eicosanoids → inflammation). Structural specificity matters biologically: Cer(d18:1/16:0) and Cer(d18:1/24:1) have different membrane properties and disease associations despite being the same lipid class. Always map changed lipids back to metabolic pathways because lipids are intermediates — an elevated ceramide could mean increased synthesis (CERS activity up), decreased degradation (ASAH1 down), or shunting from sphingomyelin (SMPD1 up).
LOOK UP DON'T GUESS: Do not assume a lipid's LIPID MAPS ID, exact mass, or pathway membership — query LipidMaps_search_by_name first. Do not guess which diseases are associated with a lipid class; retrieve them from HMDB or CTD.
Key principles:
- LIPID MAPS classification first — use the 8-category system (fatty acyls, glycerolipids, glycerophospholipids, sphingolipids, sterol lipids, prenol lipids, saccharolipids, polyketides)
- Structural specificity matters — chain length, unsaturation, and sn-position affect biological function
- Connect to pathways — lipids are metabolic intermediates; always map to biosynthesis/degradation pathways
- Disease context — many lipids are disease biomarkers (sphingolipids in neurodegeneration, oxidized lipids in CVD)
- Evidence grading — T1: clinical biomarker studies, T2: mechanistic studies, T3: association data, T4: computational prediction
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 · +28 lines 7c03f56c3f02
- 1mo ago First seen · 178 lines · 84 tokens per session scan A 05d88deb58c0
tooluniverse-lipidomics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 3,119 once invoked, about $0.0003 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.