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-precision-oncologygit 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-precision-oncology)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-precision-oncology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-precision-oncology/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-precision-oncology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-precision-oncology.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 Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.02967 |
| Opus 5.5 | $0.00031 | $0.01187 |
| Sonnet 5.5 | $0.00016 | $0.00593 |
| Haiku 4.5 | $0.00008 | $0.00297 |
Grade A, and why
tooluniverse-precision-oncology 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Precision Oncology Treatment Advisor
Provide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.
Domain Reasoning
Treatment selection follows a strict evidence hierarchy: FDA-approved for this specific mutation in this cancer type ranks highest, followed by approval for this mutation in any cancer (tumor-agnostic), then active clinical trials, and finally off-label use. Skipping this hierarchy to recommend off-label therapies when an approved option exists is a clinical error. Always check current NCCN guidelines and recent literature, as approvals change rapidly — a drug that was investigational last year may now be first-line.
When looking up treatment for a specific mutation, search CIViC and OncoKB FIRST, not PubMed. These databases have curated evidence levels. PubMed is for when curated databases don't have the answer.
Treatment Selection Reasoning
Biomarker-to-drug logic — When a biomarker is identified, the first-line targeted therapy follows established mappings. Always verify current approval status via OncoKB/CIViC, but use this as a starting framework:
- NSCLC: EGFR exon 19 del / L858R → osimertinib (1L); ALK fusion → alectinib/lorlatinib; ROS1 fusion → crizotinib/entrectinib; KRAS G12C → sotorasib/adagrasib; MET exon 14 skip → capmatinib/tepotinib; RET fusion → selpercatinib; BRAF V600E → dabrafenib+trametinib; NTRK fusion → larotrectinib/entrectinib (tumor-agnostic)
- Breast: HER2+ → trastuzumab+pertuzumab (1L), T-DXd (2L); HR+/HER2- → CDK4/6i (palbociclib/ribociclib) + AI; BRCA1/2 mut → olaparib/talazoparib; PIK3CA mut → alpelisib+fulvestrant
- Colorectal: BRAF V600E → encorafenib+cetuximab; MSI-H/dMMR → pembrolizumab (tumor-agnostic); KRAS/NRAS wild-type → cetuximab/panitumumab (anti-EGFR)
- Melanoma: BRAF V600E/K → dabrafenib+trametinib or encorafenib+binimetinib; wild-type → immunotherapy (nivolumab+ipilimumab)
- Tumor-agnostic: MSI-H/dMMR → pembrolizumab; NTRK fusion → larotrectinib; TMB-H (>=10 mut/Mb) → pembrolizumab; RET fusion → selpercatinib
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.
- 1mo ago First seen · 167 lines · 78 tokens per session scan A 22c6d768068b
tooluniverse-precision-oncology is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 2,967 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.