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-vaccine-designgit 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-vaccine-design)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-vaccine-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-vaccine-design/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-vaccine-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-vaccine-design.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 | $0.00098 | $0.03140 |
| Opus 5.5 | $0.00039 | $0.01256 |
| Sonnet 5.5 | $0.00020 | $0.00628 |
| Haiku 4.5 | $0.00010 | $0.00314 |
Grade A, and why
tooluniverse-vaccine-design 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vaccine Design
Computational pipeline for designing peptide/subunit vaccine candidates through epitope prediction, population coverage optimization, and immunogenicity assessment.
Reasoning Strategy
Vaccine design requires presenting the right epitopes to elicit protective immunity — not just any immune response, but one that is neutralizing, durable, and broadly applicable. For T-cell vaccines, the core tool is MHC binding prediction (IEDB tools): predict peptide-MHC affinity across multiple HLA alleles, then select epitopes with broad coverage of the target population. For antibody vaccines, prioritize surface-exposed conserved regions — a deeply buried or hypervariable region makes a poor antibody target. MHC binding does not equal immunogenicity; many good binders are not immunogenic in vivo due to tolerance, poor processing, or lack of T-cell help. A multi-epitope strategy (combining MHC-I for CD8+ CTL response, MHC-II for CD4+ helper response, and B-cell epitopes for antibody induction) is more robust than any single epitope. Conservation across pathogen strains is critical — an epitope that mutates under immune pressure (like HIV envelope hypervariable regions) is a poor vaccine target.
LOOK UP DON'T GUESS: Do not predict MHC binding or population coverage from memory — use IEDB_predict_mhci_binding / IEDB_predict_mhcii_binding for T-cell predictions, IEDB_predict_bcell_epitopes for antibody (B-cell) epitope prediction, and iedb_search_epitopes for validated experimental data. Do not assume what's on the pathogen surface; retrieve annotated sequences from UniProt or BVBRC.
Key principles:
- Epitope-driven — vaccines work by presenting epitopes to T/B cells; start with epitope prediction
- Population coverage matters — HLA diversity means no single epitope covers everyone; design for breadth
- Multi-epitope is better — combine CD8+ (MHC-I) and CD4+ (MHC-II) epitopes for robust immunity
- Conservation = broad protection — conserved epitopes across strains provide cross-protective immunity
- Evidence grading — T1: clinical trial data, T2: in-vivo immunogenicity, T3: in-vitro binding, T4: computational prediction only
What ships with it
1 file 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.
- 1mo ago First seen · 239 lines · 98 tokens per session scan A ebd9ab4bb66c
tooluniverse-vaccine-design is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 3,140 once invoked, about $0.0004 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.