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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mims-harvard/ToolUniversenpx agentmods add skills/mims-harvard/tooluniverse/devtu-docs-qualityWrote 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/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/devtu-docs-quality"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-docs-quality.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 | $0.00141 | $0.04202 |
| Opus 5.5 | $0.00056 | $0.01681 |
| Sonnet 5.5 | $0.00028 | $0.00840 |
| Haiku 4.5 | $0.00014 | $0.00420 |
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 18d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- devtu-docs-quality — 100% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 353 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.
- 18d ago Changed · +2 lines · +1 tokens per session be380d66ddda
- 1mo ago 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 (1,757 stars, last pushed yesterday), licensed Apache-2.0. It adds 141 tokens to every session and 4,202 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
intake
Inspect configured Sources and propose evidence-backed Backlog work.
orchestrate
Toolbox for driving HumanLayer from the CLI - log in, pick a host, launch tasks in their own worktrees, launch sessions, list tasks and their PRs, and copy, move, or upload task artifacts.
team-lead
Run a goal as a team when you can also do the work yourself: decide what you keep, dispatch the rest, and keep the status board honest. The delta over goal-conductor, which carries the dispatch, patrol and acceptance procedure this one points at. Load it when you are handed a goal, not a task.
product-management
Product management expertise for product strategy, roadmap planning, feature prioritization (RICE, ICE, MoSCoW), customer research, A/B testing, product analytics, and product-market fit. Use when building product roadmaps, prioritizing features, or defining product strategy.
style-show
Show CocoStyle conventions for the current project.
yak-worktree-workflow
Use when starting work on a yak - sets up an isolated git worktree, reads yak context, and guides the full cycle from claiming through merge and cleanup.