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-enzyme-designgit 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-enzyme-design)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-enzyme-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-enzyme-design/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-enzyme-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-enzyme-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00085 | $0.03161 |
| Opus 5.5 | $0.00034 | $0.01264 |
| Sonnet 5.5 | $0.00017 | $0.00632 |
| Haiku 4.5 | $0.00009 | $0.00316 |
Grade A, and why
tooluniverse-enzyme-design 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 today.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
De Novo Enzyme Designer
Design enzymes for a named reaction by scaffolding a catalytic motif, then triage the output with filters derived from the reaction's mechanism. Built around AlphaProtein Novo (AP Novo), whose own finding is that the filters, not the generator, decided success.
KEY PRINCIPLES:
- Motif-first — the input motif dominates the outcome more than any model choice
- Mechanism-inspired metrics — catalytic geometry beats generic confidence
- Multi-state — fold every state along the mechanism, require agreement across them
- Backbone quality is an ensemble property — score a backbone by how many resequences of it pass
- Report the funnel, not the survivors — know which filter killed what
- In-silico pass is not activity — grade designs, never promise them
- English-first queries — always use English terms in tool calls
De novo enzyme design starts with chemistry, not protein. You must be able to draw the transition state or a covalent intermediate as 3D coordinates — catalytic side-chain atoms plus ligand — before any model is useful. Everything downstream is scaffolding that geometry and then asking whether a predictor still believes it.
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first 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 the user asks to:
- Design an enzyme for a specific reaction or substrate
- Scaffold a catalytic motif / active site into a new protein
- Filter, score, rank or triage an existing set of enzyme designs
- Decide which designs are worth ordering, and why
- Optimize an already-active design (recycled scaffold / partial diffusion)
What ships with it
2 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.
- today First seen · 186 lines · 85 tokens per session scan A 9d091c6df060
tooluniverse-enzyme-design is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,747 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 3,161 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 2026-10-20.
Other skills, from other repositories
experiment-design
Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies. Triggers on phrases like "design ablation", "plan experiment", "what experiments should I run", "baseline comparison", or "experiment matrix".
m4-api
Query M4 clinical datasets (MIMIC-IV, MIMIC-IV-Note, MIMIC-IV-ED, eICU, MIMIC-III, MIMIC-CXR-JPG, and demos) from Python with import m4: find tables, run SQL into pandas, search clinical notes, select chest X-ray cohorts and fetch their images, handle M4's errors. Use before writing Python or SQL against M4 data.
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…
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.