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-variant-interpretationgit 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-variant-interpretation)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-cancer-variant-interpretation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-cancer-variant-interpretation/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-variant-interpretation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-cancer-variant-interpretation.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 | $0.00093 | $0.04549 |
| Opus 5.5 | $0.00037 | $0.01820 |
| Sonnet 5.5 | $0.00019 | $0.00910 |
| Haiku 4.5 | $0.00009 | $0.00455 |
Grade A, and why
tooluniverse-cancer-variant-interpretation 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 20d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cancer Variant Interpretation for Precision Oncology
Comprehensive clinical interpretation of somatic mutations in cancer. Transforms a gene + variant input into an actionable precision oncology report covering clinical evidence, therapeutic options, resistance mechanisms, clinical trials, and prognostic implications.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Evidence-graded - Every recommendation has an evidence tier (T1-T4)
- Actionable output - Prioritized treatment options, not data dumps
- Clinical focus - Answer "what should we treat with?" not "what databases exist?"
- Resistance-aware - Always check for known resistance mechanisms
- Cancer-type specific - Tailor all recommendations to the patient's cancer type when provided
- Source-referenced - Every statement must cite the tool/database source
- English-first queries - Always use English terms in tool calls (gene names, drug names, cancer types), even if the user writes in another language. Respond in the user's language
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) 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 treatments exist for EGFR L858R in lung cancer?"
- "Patient has BRAF V600E melanoma - what are the options?"
- "Is KRAS G12C targetable?"
- "Patient progressed on osimertinib - what's next?"
- "What clinical trials are available for PIK3CA E545K?"
- "Interpret this somatic mutation: TP53 R273H"
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.
- 20d ago Changed · +35 lines d5dd298f77e0
- 1mo ago First seen · 211 lines · 93 tokens per session scan A 22ffed07f9fb
tooluniverse-cancer-variant-interpretation is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,760 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 4,549 once invoked, about $0.0004 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 2026-08-30.
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.
simulation-orchestrator
Orchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hypercube sampling), initialize and track batch job campaigns, monitor job completion status, and aggregate results with summary statistics across all runs. Use when running a parameter study across dt, kappa, or…
ontology-explorer
Parse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with domain/range, search for ontology terms by keyword, and parse or summarize raw OWL/XML files. Currently supports CMSO and ASMO…
hpc-runtime-doctor
Diagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler portability, and resource mismatch. Use when an ALREADY-SUBMITTED job failed, ran slowly, got killed, or behaved…
simulation-failure-triage
First-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signature (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up, missing potentials/pseudopotentials, memory exhaustion, process crash/segfault, corrupted output, incomplete runs) and…