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-immunologygit 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-immunology)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-immunology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-immunology/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-immunology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-immunology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00087 | $0.03621 |
| Opus 5.5 | $0.00035 | $0.01448 |
| Sonnet 5.5 | $0.00017 | $0.00724 |
| Haiku 4.5 | $0.00009 | $0.00362 |
Grade A, and why
tooluniverse-immunology 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 1mo 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Immunology Research Skill
KEY PRINCIPLES: Multi-layer evidence; source every claim; use immunology-specific databases first (IEDB, IMGT, SAbDab); always use English gene/protein names in tool calls.
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
For MC about immune mechanisms: Look up the specific pathway/receptor/cytokine before answering. Use PubMed_search_articles with the exact terms from the question. The answer is almost always in the first few search results.
Specific LOOK UP targets (never guess these):
- Immune cell markers: CD markers for cell subsets (e.g., Treg = CD4+CD25+FOXP3+, not just "CD4+"). Query UniProt or IEDB.
- Cytokine functions: IL-17 is pro-inflammatory (Th17), IL-10 is anti-inflammatory (Treg) — but context matters. Verify via KEGG pathway or PubMed.
- MHC/HLA restrictions: Which HLA allele presents which peptide — always check IEDB MHC binding data; allele-level differences are critical (HLA-A02:01 vs HLA-A02:07 have different peptide repertoires).
- Antibody Kd values: Never estimate binding affinity; check SAbDab, IEDB, or published literature.
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.
Reasoning Frameworks
Immune response reasoning — Every immune response has innate → adaptive phases. Ask: which arm is relevant to the question? Innate (neutrophils, macrophages, complement, pattern recognition) or adaptive (T cells, B cells, antibodies, memory)? Innate is fast (hours) and antigen-nonspecific; adaptive is slow (days) but specific and generates memory. The transition occurs when APCs present antigen to naive T/B cells. Targeting innate suppresses broad inflammation; targeting adaptive disrupts antigen-specific responses. This determines which databases and tools are most relevant.
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.
- 1mo ago First seen · 160 lines · 87 tokens per session scan A 42de77a80804
tooluniverse-immunology is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 3,621 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.