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 RadOrigin-LLC/RAD-Claude-Skills --skill a11y-semantic-htmlgit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/radorigin-llc/rad-claude-skills/a11y-semantic-html)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/a11y-semantic-html"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/a11y-semantic-html/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/radorigin-llc/rad-claude-skills/a11y-semantic-html"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/a11y-semantic-html.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 | $0.00103 | $0.02453 |
| Opus 5 | $0.00051 | $0.01226 |
| Sonnet 5 | $0.00021 | $0.00491 |
| Haiku 4.5 | $0.00010 | $0.00245 |
Grade A, and why
a11y-semantic-html 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 11d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic HTML for Accessibility
Skill type: Reference. This is teaching/pattern content — it explains which element to use when and why. It is not a scanner. For static review of existing markup, use
/a11y-review. For runtime verification, use thea11y-testingskill to set up real axe.
Semantic HTML is the foundation of accessible web content. The right element provides built-in roles, keyboard behavior, and accessibility tree information that ARIA cannot fully replicate.
Core principle: Always use the most semantically specific native HTML element available. ARIA is a supplement for custom widgets — not a replacement for correct HTML.
Document Outline and Headings
The Heading Rule: One <h1>, Sequential Order, No Skips
Headings create a machine-readable outline that screen reader users navigate by jumping between levels.
<!-- CORRECT: Sequential, logical hierarchy -->
<h1>Guide to Accessible Design</h1>
<h2>Color and Contrast</h2>
<h3>Text Contrast Requirements</h3>
<h3>UI Component Contrast</h3>
<h2>Keyboard Navigation</h2>
<h3>Focus Management</h3>
<!-- WRONG: Skipped level — screen reader users think they missed content -->
<h1>Guide to Accessible Design</h1>
<h3>Color and Contrast</h3> <!-- ❌ jumped from h1 to h3 -->
Rules:
- One
<h1>per page — the primary descriptor of the page's topic - Never skip heading levels downward (
h1→h3skipsh2) - You CAN jump back up (
h3→h2when starting a new section) - Never use headings for visual size. Use CSS
font-size. Heading level = document structure, not visual hierarchy.
Heading Level vs. Visual Appearance (Tailwind/React pattern)
// WRONG: Using h4 because you want small text
<h4 className="text-sm font-medium text-gray-500">Card Label</h4>
// CORRECT: Use the right level, control size with CSS
<h3 className="text-sm font-medium text-gray-500">Card Label</h3>
// CORRECT: If it's not actually a heading, use a <p> or <span>
<p className="text-sm font-medium text-gray-500 uppercase tracking-wide">Card Label</p>
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.
- 11d ago First seen · 304 lines · 103 tokens per session scan A 01f9ba7584db
a11y-semantic-html is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 103 tokens to every session and 2,453 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
light-dark-mode
Load this skill whenever the project supports light/dark mode, colour theme switching, high-contrast mode, or responds to prefers-color-scheme. Under no circumstances hard-code colours that break in alternative themes. Absolutely always test colour contrast in both light and dark themes, and respect user OS-level…
tables
Load this skill whenever the project contains HTML data tables ( elements). Under no circumstances use tables for layout purposes. Absolutely always include elements with appropriate scope attributes, a or aria-labelledby, and ensure complex tables have headers associated with data cells. Apply these rules to every…
Load this skill whenever the project includes print stylesheets, print media queries (@media print), or any content intended for physical printing. Under no circumstances omit print CSS that ensures readable, accessible printed output. Absolutely always hide decorative elements, expand link URLs, and maintain…
progressive-enhancement
Load this skill when building any web feature, reviewing architecture decisions, or evaluating JavaScript dependencies. Under no circumstances build features that break completely when JavaScript is unavailable or fails. Absolutely always start with semantic HTML, layer CSS enhancements, and add JavaScript as the…
wes-bos-sick-picks
Research-first workflow for building frontend UI components (any framework), in the spirit of Wes Bos. Use when designing or implementing a UI component, layout, interaction, or CSS/HTML feature and you want a modern, accessible, best-practice solution rather than a first guess. Researches pitfalls and platform…
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…