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-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-clinical-trial-design)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-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-clinical-trial-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-trial-design.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 Data Exfiltration · line 249 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00093 | $0.03001 |
| Opus 5 | $0.00046 | $0.01501 |
| Sonnet 5 | $0.00019 | $0.00600 |
| Haiku 4.5 | $0.00009 | $0.00300 |
Grade A, and why
tooluniverse-clinical-trial-design scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.get("https://clinicaltrials.gov/api/v2/studies", params=params).json() How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Trial Design Feasibility Assessment
Systematically assess clinical trial feasibility by analyzing 6 research dimensions. Produces comprehensive feasibility reports with quantitative enrollment projections, endpoint recommendations, and regulatory pathway analysis.
IMPORTANT: Always use English terms in tool calls (drug names, disease names, biomarker names), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language.
Reasoning Before Searching
Trial design starts with the question, not the methods. Answer these four questions before running any tools — they determine everything else:
- What is the primary endpoint? Is it overall survival (gold standard but slow), PFS (faster but surrogate), ORR (single-arm friendly but not always accepted), or a biomarker (needs validation as surrogate first)? The endpoint determines FDA pathway, statistical design, and duration.
- Who is the population? Broad unselected vs. biomarker-enriched. Enriched populations have higher response rates, allowing smaller trials — but require a validated companion diagnostic and reduce the eligible patient pool.
- What is the comparator? Placebo (only if no standard of care exists), active control (requires non-inferiority or superiority framing), or single-arm with historical control (acceptable for rare diseases or breakthrough designations, but FDA scrutiny is high).
- Is the effect size realistic given the mechanism? A 20% improvement in ORR over SOC requires ~100 patients per arm. A 50% improvement requires ~30. If the mechanism only justifies a 10% improvement, the trial may be underpowered regardless of design. Check precedent effect sizes in similar trials before committing to an endpoint.
These four answers determine sample size, duration, and trial design. Look them up from precedent trials and FDA guidance — do not derive them from first principles.
What ships with it
9 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 · 275 lines · 93 tokens per session scan A a3f5c0752d24
tooluniverse-clinical-trial-design is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 93 tokens to every session and 3,001 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dfam-check
Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…
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.