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-cancer-genomics-tcgagit 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-cancer-genomics-tcga)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-cancer-genomics-tcga"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-cancer-genomics-tcga/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-cancer-genomics-tcga"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-cancer-genomics-tcga.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 303 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.
- medium Data Exfiltration · line 303 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.
- medium Data Exfiltration · line 303 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.
- medium Data Exfiltration · line 315 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 | $0.00086 | $0.04084 |
| Opus 5 | $0.00043 | $0.02042 |
| Sonnet 5 | $0.00017 | $0.00817 |
| Haiku 4.5 | $0.00009 | $0.00408 |
Grade B, and why
tooluniverse-cancer-genomics-tcga scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
resp = requests.post("https://api.gdc.cancer.gov/cases", json={ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.post("https://api.gdc.cancer.gov/cases", json={ How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cancer Genomics / TCGA Analysis
TCGA analysis starts with: what cancer type? what data type? Build your cohort FIRST (GDC filters), then analyze. Don't query mutations without defining the cohort — pan-cancer counts from GDC_get_mutation_frequency are uninformative without cancer-type context. A mutation frequency of 10% in one cancer type may be 0.5% in another; always specify project_id. Survival analysis (Kaplan-Meier) is hypothesis-generating in retrospective TCGA data — always report sample size and p-value, and note that TCGA cohorts are not treatment-stratified.
LOOK UP DON'T GUESS: never assume TCGA project IDs, NCIt codes, or gene coordinates — use GDC_list_projects to confirm project IDs and Progenetix_list_filtering_terms for NCIt codes.
Systematic TCGA/GDC analysis: define cohorts, retrieve clinical data, profile somatic mutations, query copy number variations, run survival analysis, and interpret variants with OncoKB.
When to Use
- "What is the mutation frequency of TP53 in TCGA-BRCA?"
- "Get survival data for TCGA-LUAD patients"
- "Find clinical data for breast cancer cases in GDC"
- "Which TCGA projects have KRAS G12C mutations?"
- "Show CNV amplifications of EGFR in glioblastoma"
- "Annotate BRAF V600E for clinical significance in melanoma"
NOT for (use other skills instead)
- Precision oncology treatment recommendations -> Use
tooluniverse-precision-oncology - Rare disease gene discovery -> Use
tooluniverse-rare-disease-genomics - GWAS variant interpretation -> Use
tooluniverse-gwas-snp-interpretation
Workflow Overview
Input (cancer type / gene / TCGA project ID)
|
v
Phase 1: Study Selection -- GDC_list_projects, GDC_search_cases
|
v
Phase 2: Clinical Data -- GDC_get_clinical_data
|
v
Phase 3: Somatic Mutations -- GDC_get_ssm_by_gene, GDC_get_mutation_frequency
|
v
Phase 4: CNV Analysis -- Progenetix_cnv_search, Progenetix_search_biosamples
|
v
Phase 5: Survival Analysis -- GDC_get_survival
|
v
Phase 6: Variant Interpretation -- OncoKB_annotate_variant
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 · 337 lines · 86 tokens per session scan B c557df51d6d5
tooluniverse-cancer-genomics-tcga is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 4,084 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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.