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.
git clone --depth 1 https://github.com/julianoczkowski/create-trimble-appWrote 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/rules/julianoczkowski/create-trimble-app/modus-semantic-html-react)<a href="https://agentmods.dev/rules/julianoczkowski/create-trimble-app/modus-semantic-html-react"><img src="https://agentmods.dev/badge/rules/julianoczkowski/create-trimble-app/modus-semantic-html-react.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 | $0.00000 | $0.03344 |
| Opus 5 | $0.00000 | $0.01672 |
| Sonnet 5 | $0.00000 | $0.00669 |
| Haiku 4.5 | $0.00000 | $0.00334 |
Grade A, and why
modus-semantic-html-react 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 4d 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:
- modus-semantic-html-solidjs — 91% identical, 265 lines differ
How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic HTML Usage in React + Vite
🚨 CRITICAL: Use Div Elements Only
MANDATORY: This React + Vite application uses div elements exclusively for all content (except <i> for icons) to avoid conflicts with Tailwind CSS default browser styles.
Rule: Use div elements with Tailwind classes instead of semantic HTML elements.
❌ FORBIDDEN: Semantic HTML Elements
❌ Never Use Semantic HTML Elements
// ❌ WRONG: Semantic HTML elements
<h1 className="text-4xl font-bold">Title</h1>
<h2 className="text-3xl font-semibold">Subtitle</h2>
<h3 className="text-2xl font-medium">Heading</h3>
<p className="text-base">Paragraph text</p>
<section className="mb-8 p-4">Content section</section>
<header className="bg-background">Header content</header>
<footer className="bg-muted">Footer content</footer>
<nav className="flex space-x-4">Navigation</nav>
<main className="flex-1">Main content</main>
<aside className="w-64">Sidebar</aside>
<article className="prose">Article content</article>
<span className="text-sm">Inline text</span>
❌ Never Use Form Elements
// ❌ WRONG: Form elements
<form className="space-y-4">
<label className="block">Label</label>
<input type="text" className="w-full" />
<button type="submit">Submit</button>
</form>
// ❌ WRONG: List elements
<ul className="space-y-2">
<li>List item 1</li>
<li>List item 2</li>
</ul>
<ol className="space-y-2">
<li>Ordered item 1</li>
<li>Ordered item 2</li>
</ol>
✅ CORRECT: Div Elements with Tailwind
✅ Use Div Elements for All Content
// ✅ CORRECT: Div elements with Tailwind classes
<div className="text-4xl font-bold">Title</div>
<div className="text-3xl font-semibold">Subtitle</div>
<div className="text-2xl font-medium">Heading</div>
<div className="text-base">Paragraph text</div>
<div className="mb-8 p-4">Content section</div>
<div className="bg-background">Header content</div>
<div className="bg-muted">Footer content</div>
<div className="flex space-x-4">Navigation</div>
<div className="flex-1">Main content</div>
<div className="w-64">Sidebar</div>
<div className="prose">Article content</div>
<div className="text-sm">Inline text</div>
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.
- 4d ago First seen · 428 lines · 0 tokens per session scan A 39e19b925e1f
modus-semantic-html-react is a cursor rule published in the GitHub repository julianoczkowski/create-trimble-app (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,344 tokens. 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 cursor rules, from other repositories
hatch3r-design-system-detection
Mandatory detection of existing design tokens, theme primitives, and component library before AI agents author new UI components.
hatch3r-ux-states-and-flows
Four-state surface contract (loading/empty/error/partial), user-flow decomposition before implementation, and microcopy + tone discipline for end-user UIs.
hatch3r-accessibility-standards
Accessibility standards covering WCAG 2.2 AA compliance, keyboard navigation, screen readers, and ARIA patterns.
hatch3r-theming
Theming, dark mode, and color system conventions for the project.
ui
UI/dashboard rules — vanilla JS, no frameworks.
design-ux
Accessibility and design-system conventions for the web dashboard and marketing site.