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-protein-sae-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-protein-sae-variant-interpretation)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-protein-sae-variant-interpretation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-sae-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-protein-sae-variant-interpretation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-sae-variant-interpretation.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 | $0.00144 | $0.03107 |
| Opus 5 | $0.00072 | $0.01554 |
| Sonnet 5 | $0.00029 | $0.00621 |
| Haiku 4.5 | $0.00014 | $0.00311 |
Grade A, and why
tooluniverse-protein-sae-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 8d 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.
Protein SAE Variant Interpretation
Interpret a single missense variant by comparing reference vs mutant Sparse Autoencoder (SAE) feature activations from the ESMC-6B protein language model. SAE features are interpretable latent dimensions of the model's hidden state — many activate on biologically meaningful patterns (active sites, ligand-binding pockets, PTM sequons, structural motifs).
When to use this skill
Apply when users:
- Ask "why is variant X (a missense) loss-of-function?" and need a mechanistic answer beyond a pathogenicity score
- Have an AlphaMissense / ClinVar "damaging" variant and want to know which functional feature breaks (catalytic? binding? PTM site? structural?)
- Want to compare ref vs mutant protein representation at a specific residue
- Are interpreting why a structurally subtle change (single AA) has a big functional impact
Not for (use other skills instead):
- ACMG pathogenicity classification →
tooluniverse-variant-interpretation - Regulatory / non-coding variants →
tooluniverse-variant-to-mechanism - Variant-to-disease association without mechanism →
tooluniverse-gene-disease-association - Cancer-specific variant interpretation →
tooluniverse-cancer-variant-interpretation
Required inputs
| Input | Format | Example |
|---|---|---|
| Protein identifier | UniProt accession or HGNC gene symbol | P04637 or TP53 |
| Variant | Single-letter code: {ref_aa}{position_1idx}{alt_aa} |
R175H |
Optional:
- Window radius (default 8): residues around the mutation to analyze
- Reference protein sequence (skip the UniProt lookup if already known)
Prerequisites
- ESM_API_KEY env var with a valid EvolutionaryScale Forge token (https://forge.evolutionaryscale.ai)
- esm package with SAE support:
The PyPI release ofpip install 'esm @ git+https://github.com/evolutionaryscale/esm@ee891c52'esmdoes NOT yet include SAEConfig. Install from the upstream feature branch.
License note: SAE outputs from Forge are governed by the Cambrian Inference Clickthrough License — non-commercial / academic research use only unless a separate commercial agreement applies.
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.
- 8d ago First seen · 246 lines · 144 tokens per session scan A 308365b4038c
tooluniverse-protein-sae-variant-interpretation is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 144 tokens to every session and 3,107 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
mechanism-audit
Audit the mechanistic experiment rigor for a specific claim. Catalogue currently has six slots A–F: A (steering coefficient sweep) is implemented; B–F are reserved for future checks (direction extraction quality, site/layer selection, neffective sufficiency, probe-vs-causal disentanglement, intervention scope). Uses…
shap
Use this skill when working with SHAP (SHapley Additive exPlanations) to explain machine learning model predictions, compute feature importance, generate SHAP values for tree ensembles (XGBoost, LightGBM, CatBoost, scikit-learn), deep learning models (TensorFlow, Keras, PyTorch), NLP transformers, or any…
mechanism-skills
Routing entry point for eleven families of mechanistic-interpretability methods that localize which internal object (layer, attention head, neuron, SAE feature, weight, or input feature) drives a model's behavior, how influential it is, and what changes when it is intervened on. Use this skill whenever the question is…
dynamic-components
Identify and manipulate language-specific neurons in multilingual Large Language Models (LLMs) to understand and control language-specific behaviors in models like LLaMA-2, BLOOM, OPT, Mistral, and Phi-2.
zennit-crp
Use this skill when working with Concept Relevance Propagation (CRP) and Relevance Maximization for explainable AI in PyTorch models, including generating concept-conditional heatmaps, feature visualizations, attribution graphs, and identifying which latent concepts neural networks use for predictions.