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 skill_templategit 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.
![agentmods badge for tooluniverse-[domain-name]](/badge/skills/mims-harvard/tooluniverse/skill_template/github.svg?v=0-0-A){kind=icon}
[](https://agentmods.dev/skills/mims-harvard/tooluniverse/skill_template)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/skill_template"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/skill_template/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.
![agentmods 80×15 button for tooluniverse-[domain-name]](/badge/skills/mims-harvard/tooluniverse/skill_template.svg?v=A-x){kind=icon}
<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/skill_template"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/skill_template.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 | $0.00000 | $0.01624 |
| Opus 5.5 | $0.00000 | $0.00650 |
| Sonnet 5.5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
tooluniverse-[domain-name] 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[Domain Name] Analysis
[One paragraph overview describing what this skill does, what problems it solves, and what outputs it provides.]
When to Use This Skill
Triggers:
- "[Trigger phrase 1]"
- "[Trigger phrase 2]"
- "[Trigger phrase 3]"
Use Cases:
- [Use Case 1]: [Description]
- [Use Case 2]: [Description]
- [Use Case 3]: [Description]
Core Databases Integrated
| Database | Coverage | Strengths |
|---|---|---|
| Database 1 | [What it covers] | [What it's best for] |
| Database 2 | [What it covers] | [What it's best for] |
| Database 3 | [What it covers] | [What it's best for] |
Workflow Overview
Input → Phase 1: [Name] → Phase 2: [Name] → Phase 3: [Name] → Report
Phase 1: [Phase Name]
When: [When this phase runs - e.g., "When input_param_1 provided"]
Objective: [What this phase achieves]
Tools Used
TOOL_NAME_1:
- Input:
parameter1(type, required/optional): Descriptionparameter2(type, required/optional): Description
- Output: Description of what the tool returns
- Use: What this tool provides for the analysis
TOOL_NAME_2 (Fallback):
- Input: [Parameters]
- Output: [Description]
- Use: [Purpose]
Workflow
- Query TOOL_NAME_1 with [input description]
- Extract [specific data fields] from response
- If no results → try TOOL_NAME_2 (fallback)
- Process data and add to report
- Continue with available data
Decision Logic
- Successful query: Process and display top 10-15 results
- Empty results: Note "[Database] returned no results"
- API error: Fall back to TOOL_NAME_2
- Both fail: Document unavailability and continue
Phase 2: [Phase Name]
When: [Conditions]
Objective: [Goal]
Tools Used
[Similar structure to Phase 1]
Workflow
[Step-by-step process]
Decision Logic
[How to handle different scenarios]
Phase 3: [Phase Name]
[Similar structure]
What ships with it
3 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.
- 1mo ago First seen · 257 lines · 0 tokens per session scan A 73c46772da96
tooluniverse-[domain-name] is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,739 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,624 tokens. 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.
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.
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.
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.
clinical-research-session
Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.