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-guidelinesgit 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-guidelines)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-clinical-guidelines"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-guidelines/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-guidelines"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-clinical-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high System Prompt Leakage · line 16 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00094 | $0.04326 |
| Opus 5 | $0.00047 | $0.02163 |
| Sonnet 5 | $0.00019 | $0.00865 |
| Haiku 4.5 | $0.00009 | $0.00433 |
Grade A, and why
tooluniverse-clinical-guidelines 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 12d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Guidelines Search & Retrieval
Guideline Hierarchy
Not all guidelines carry equal weight. Evaluate sources in this order:
- NICE and WHO — Evidence-graded, regularly updated, rigorous systematic review process. NICE guidelines include explicit recommendation strength (e.g., "offer" vs "consider").
- Society guidelines (AHA, ADA, NCCN, SIGN) — Expert-consensus panels within a specialty. May lag behind the latest evidence by 1-3 years. Strong within their domain but narrower scope.
- Aggregator databases (GIN, TRIP, OpenAlex) — Index guidelines from multiple societies. Good for breadth and discovery, but you must verify the original source.
- Literature databases (PubMed, EuropePMC) — Return guideline-related publications, not curated guideline text. Useful as a fallback, not a primary source.
Always check publication date. A 2015 guideline may be superseded by a 2024 update. When presenting results, include the year prominently and note if newer guidance may exist.
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.
Search Strategy
Step 1: Start Narrow, Then Broaden
- Search the condition name + "guideline" in NICE, TRIP, and GIN simultaneously (parallel calls).
- If the question targets a specialty, add the society tool: AHA for cardiology, ADA for diabetes, NCCN for oncology, CPIC for pharmacogenomics.
- If initial searches return nothing, broaden to the disease category (e.g., "heart failure" instead of "HFpEF with SGLT2 inhibitors").
- If society-specific tools fail, fall back to PubMed/EuropePMC with
[condition] guideline [year].
Step 2: Search at Least 3 Sources
Always query a minimum of 3 databases to catch guidelines that one source may miss. Prioritize: NICE > GIN > TRIP > Society-specific > Literature databases.
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.
- 12d ago First seen · 304 lines · 94 tokens per session scan A 6c7a6aaffe62
tooluniverse-clinical-guidelines is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 4,326 once invoked, about $0.0005 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
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.
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.
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.