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 agentmods add skills/mims-harvard/tooluniverse/devtu-docs-qualitynpx skills add mims-harvard/ToolUniverse --skill devtu-docs-qualitygit 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/devtu-docs-quality)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-docs-quality"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-docs-quality.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.03991 |
| Opus 5 | $0.00070 | $0.01996 |
| Sonnet 5 | $0.00028 | $0.00798 |
| Haiku 4.5 | $0.00014 | $0.00399 |
Grade A, and why
devtu-docs-quality 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- devtu-docs-quality — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Quality Assurance
Two Equal Priorities
Both of the following must be satisfied before an audit is done. Neither overrides the other.
1. Technical correctness — wrong code is worse than no code; it actively breaks users' workflows.
2. Less is more — redundant content is worse than no content; it creates confusion, dilutes trust, and makes maintenance harder.
When in doubt about technical accuracy: verify against source (
src/tooluniverse/execute_function.py). When in doubt about whether content is needed: delete it.
Less Is More — The Core Philosophy
ToolUniverse is a serious research tool. Documentation should reflect that with restraint and precision, not volume.
What "less is more" means in practice
Remove, don't add. Every edit should end with fewer words, fewer pages, fewer links. The field moves fast — outdated instructions are actively harmful. When two approaches both work, keep one.
Each concept appears exactly once. If setup instructions appear in three places, a user reading one doesn't know the others exist, and maintainers must update all three on every change. Pick one canonical location and cross-link everywhere else.
No emojis. Emojis in headings, nav items, card titles, and bullet points signal "AI-generated" and undermine trust in a serious scientific tool. Remove them unconditionally — no exceptions for "emphasis."
Shrink, don't summarize. A page reduced from 1000 lines to 30 pointer lines is better than a 1000-line page summarized with a TL;DR box. Do the surgery.
Size budgets (hard limits):
| Page type | Max lines |
|---|---|
Per-platform setup page (claude_desktop.rst, cursor.rst, etc.) |
15 |
| Homepage grid sections | 4 cards max per grid |
| "See Also" / "Related" link lists | 4 links max |
| Tutorial pages that duplicate the Python guide | 0 — delete or make a pointer |
Less-is-more decision tree
When reviewing any piece of content, ask:
What ships with it
4 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.
- yesterday First seen · 351 lines · 140 tokens per session scan A 7d4aeca9b1b1
devtu-docs-quality is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,672 stars, last pushed today), licensed Apache-2.0. It adds 140 tokens to every session and 3,991 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.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…
external-repo-setup
Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.
multi-agent-focus
Generic skill for self-organizing multi-agent teams that collaborate on an optimization problem. Agents discuss dimensions, form teams, run experiments, and adapt when stagnating. Uses AnonAPI posts for discussion and workspaces for shared state.
agentic-patterns
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent"…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.