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-acmg-variant-classificationgit 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-acmg-variant-classification)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-acmg-variant-classification"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-acmg-variant-classification/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-acmg-variant-classification"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-acmg-variant-classification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00127 | $0.04107 |
| Opus 5 | $0.00063 | $0.02054 |
| Sonnet 5 | $0.00025 | $0.00821 |
| Haiku 4.5 | $0.00013 | $0.00411 |
Grade A, and why
tooluniverse-acmg-variant-classification 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 11d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACMG/AMP Variant Classification
ACMG Reasoning
Each criterion (PS, PM, PP for pathogenic; BS, BP for benign) contributes a weighted piece of evidence for or against pathogenicity. The classification is the COMBINATION of all activated criteria, not any single criterion. Do not overweight a single finding.
The hierarchy is: PVS1 (very strong) > PS (strong) > PM (moderate) > PP (supporting). On the benign side: BA1 (stand-alone) > BS (strong) > BP (supporting). A frameshift in a LOF-intolerant gene (PVS1) plus a ClinVar expert-panel pathogenic entry (PS1) is pathogenic. A single PP criterion alone is not. The combination rule is what matters.
Two common errors to avoid: (1) seeing a "Pathogenic" ClinVar entry and stopping — that is PP5 (supporting) unless it has expert-panel review, not automatic confirmation; (2) dismissing a variant because one predictor says "tolerated" — discordant predictors mean neither PP3 nor BP4 applies, which is neutral evidence, not benign evidence.
Always apply criteria conservatively. When evidence is ambiguous, leave the criterion unmet. Cite the source for every criterion you activate so clinicians can audit the reasoning.
KEY PRINCIPLES:
- Criteria-driven — cite which criteria were activated and why
- Conservative — do not upgrade a criterion when evidence is ambiguous
- Gene-aware — adjust thresholds based on gene mechanism (LOF vs. gain-of-function)
- Population-calibrated — use ancestry-specific gnomAD frequencies, not just global AF
- Transparent — show evidence for each criterion
- Source-referenced — every criterion activation must cite the database/tool source
- English-first queries — always use English terms in tool calls; respond in 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.
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.
- 11d ago First seen · 244 lines · 127 tokens per session scan A c2dfba517147
tooluniverse-acmg-variant-classification is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 4,107 once invoked, about $0.0006 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.