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-clinical-trial-matchinggit 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-clinical-trial-matching)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-matching"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-matching/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-clinical-trial-matching"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00135 | $0.03361 |
| Opus 5 | $0.00068 | $0.01681 |
| Sonnet 5 | $0.00027 | $0.00672 |
| Haiku 4.5 | $0.00014 | $0.00336 |
Grade A, and why
tooluniverse-clinical-trial-matching 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 13d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Trial Matching for Precision Medicine
Transform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Patient-centric - Every recommendation considers the individual patient's profile
- Molecular-first matching - Prioritize trials targeting patient's specific biomarkers
Molecular Matching Priority
Match patients to trials by molecular profile FIRST (specific mutations), then by disease stage, then by prior treatments. A patient with EGFR L858R should match to EGFR-targeted trials regardless of other factors. 4. Evidence-graded - Every recommendation has an evidence tier (T1-T4) 5. Quantitative scoring - Trial Match Score (0-100) for every trial 6. Eligibility-aware - Parse and evaluate inclusion/exclusion criteria 7. Actionable output - Clear next steps, contact info, enrollment status 8. Source-referenced - Every statement cites the tool/database source 9. Completeness checklist - Mandatory section showing analysis coverage 10. English-first queries - Always use English terms in tool calls. Respond in user's language
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
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.
When to Use
Apply when user asks:
- "What clinical trials are available for my NSCLC with EGFR L858R?"
- "Patient has BRAF V600E melanoma, failed ipilimumab - what trials?"
- "Find basket trials for NTRK fusion"
- "Breast cancer with HER2 amplification, post-CDK4/6 inhibitor trials"
- "KRAS G12C colorectal cancer clinical trials"
- "Immunotherapy trials for TMB-high solid tumors"
- "Clinical trials near Boston for lung cancer"
- "What are my options after failing osimertinib for EGFR+ NSCLC?"
What ships with it
7 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.
- 13d ago First seen · 250 lines · 135 tokens per session scan A a4471968aaba
tooluniverse-clinical-trial-matching is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 135 tokens to every session and 3,361 once invoked, about $0.0007 per session on Opus 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 2026-08-30.
Other skills, from other repositories
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.
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
intermediate-outputs
Use this skill when working with circuit discovery in language models, mechanistic interpretability, activation patching, attribution patching, or Layer-wise Relevance Propagation (LRP) for neural network analysis.
clip-dissect
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…