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-target-researchgit 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-target-research)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-target-research"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-target-research/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-target-research"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-target-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00084 | $0.04538 |
| Opus 5.5 | $0.00034 | $0.01815 |
| Sonnet 5.5 | $0.00017 | $0.00908 |
| Haiku 4.5 | $0.00008 | $0.00454 |
Grade A, and why
tooluniverse-target-research 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive Target Intelligence Gatherer
Gather complete target intelligence by exploring 9 parallel research paths. Supports targets identified by gene symbol, UniProt accession, Ensembl ID, or gene name.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Tool parameter verification - Verify params via
get_tool_infobefore calling unfamiliar tools - Evidence grading - Grade all claims by evidence strength (T1-T4)
- Citation requirements - Every fact must have inline source attribution
- Mandatory completeness - All sections must exist with data minimums or explicit "No data" notes
- Disambiguation first - Resolve all identifiers before research
- Negative results documented - "No drugs found" is data; empty sections are failures
- Collision-aware literature search - Detect and filter naming collisions
- English-first queries - Always use English terms in tool calls, even if the user writes in another language. Translate gene names, disease names, and search terms to English. Only try original-language terms as a fallback if English returns no results. Respond in the user's language
LOOK UP, DON'T GUESS
When asked about a specific protein or gene target, look it up in UniProt/Ensembl/OpenTargets BEFORE reasoning about it. Verify the gene name, function, and disease associations from databases. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.
When to Use This Skill
Apply when users:
- Ask about a drug target, protein, or gene
- Need target validation or assessment
- Request druggability analysis
- Want comprehensive target profiling
- Ask "what do we know about [target]?"
- Need target-disease associations
- Request safety profile for a target
When NOT to use: Simple protein lookup, drug-only queries, disease-centric queries, sequence retrieval, structure download — use specialized skills instead.
What ships with it
5 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.
- 10d ago Changed · +1 lines 100f7da44400
- 1mo ago First seen · 309 lines · 84 tokens per session scan A 096b1ec435fa
tooluniverse-target-research 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 4,538 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.