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-therapeutic-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-protein-therapeutic-design)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-protein-therapeutic-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-therapeutic-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-protein-therapeutic-design"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-therapeutic-design.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 | $0.00075 | $0.01578 |
| Opus 5 | $0.00037 | $0.00789 |
| Sonnet 5 | $0.00015 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
tooluniverse-protein-therapeutic-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 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Therapeutic Protein Designer
AI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.
KEY PRINCIPLES:
- Structure-first - Generate backbone geometry before sequence
- Target-guided - Design binders with target structure in mind
- Iterative validation - Predict structure to validate designs
- Developability-aware - Consider aggregation, immunogenicity, expression
- Evidence-graded - Grade designs by confidence metrics
- Actionable output - Provide sequences ready for experimental testing
- English-first queries - Always use English terms in tool calls
Therapeutic protein design starts with the target interaction. What binding surface do you need to cover? A small pocket = nanobody or peptide. A large flat surface = designed protein. Stability, immunogenicity, and manufacturability constrain the design space.
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 user asks to:
- Design a protein binder, therapeutic protein, or scaffold
- Optimize a protein sequence for function
- Design a de novo enzyme
- Generate protein variants for target binding
Workflow Overview
Phase 1: Target Characterization
Get structure (PDB, EMDB cryo-EM, AlphaFold), identify binding epitope
Phase 2: Backbone Generation (RFdiffusion)
Define constraints, generate >= 5 backbones, filter by geometry
Phase 3: Sequence Design (ProteinMPNN)
Design >= 8 sequences per backbone, sample with temperature control
Phase 4: Structure Validation (ESMFold/AlphaFold2)
Predict structure, compare to backbone, assess pLDDT/pTM
Phase 5: Developability Assessment
Aggregation, pI, expression prediction
Phase 6: Report Synthesis
Ranked candidates, FASTA, experimental recommendations
What ships with it
5 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.
- 8d ago First seen · 146 lines · 75 tokens per session scan A 55ff2c0e1110
tooluniverse-protein-therapeutic-design is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 3d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,578 once invoked, about $0.0004 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.