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 kok-o/contextos-agents --skill web-accessibilitygit clone --depth 1 https://github.com/kok-o/contextos-agentsWrote 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/kok-o/contextos-agents/web-accessibility)<a href="https://agentmods.dev/skills/kok-o/contextos-agents/web-accessibility"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/web-accessibility/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/kok-o/contextos-agents/web-accessibility"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/web-accessibility.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 | $0.00034 | $0.01253 |
| Opus 5.5 | $0.00014 | $0.00501 |
| Sonnet 5.5 | $0.00007 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
Web Accessibility 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 today.
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:
- Web Accessibility — 100% identical, 83 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Accessibility & Interface Guidelines
Overview
Enforces universal accessibility compliance (WCAG 2.1 AA / AAA), rigorous semantic markup, keyboard navigability with focus traps, screen reader live regions, and Web Interface Guidelines standards.
When to Use
Activate whenever building, styling, or reviewing user interfaces, forms, modals, menus, navigation drawers, custom interactive widgets, or media elements.
Negative Constraints (What NOT to Do)
- NEVER use
outline: nonewithout a custom:focus-visiblereplacement: Keyboard users must always have a distinct, high-contrast visual focus ring. - NEVER use non-semantic elements (
<div onClick>) for interactive triggers: Always use native<button>or<a href>. - NEVER create modals or dialogs without keyboard focus traps: Focus must remain trapped inside open dialogs during Tab / Shift-Tab navigation and restore to trigger on close.
- NEVER rely exclusively on color to indicate state or errors: Always pair colors with text labels, icons, or ARIA attributes (
aria-invalid="true"). - NEVER trap screen readers with missing form labels or error associations: Every input must link to
<label htmlFor="id">and errors viaaria-describedby. - NEVER play animations without honoring
prefers-reduced-motion: Respect user OS motion reduction preferences.
Rules & Patterns
1. Focus Visible & High-Contrast Focus Rings
button:focus-visible,
a:focus-visible,
input:focus-visible {
outline: 2px solid #6366f1;
outline-offset: 2px;
border-radius: 4px;
}
button:focus:not(:focus-visible) {
outline: none;
}
2. Accessible Modal & Focus Trap Contract
import React, { useEffect, useRef } from 'react';
interface AccessibleModalProps {
isOpen: boolean;
onClose: () => void;
titleId: string;
children: React.ReactNode;
}
/**
* Accessible Modal Dialog (W3C ARIA APG Compliant)
* Uses native HTMLDialogElement with .showModal() to guarantee:
* 1. Native inert background (blocks screen reader and click bleed-through).
* 2. Native keyboard focus trap (strictly keeps Tab cycles within dialog).
* 3. Native Escape key cancellation and focus restoration to trigger element.
*/
export function AccessibleModal({ isOpen, onClose, titleId, children }: AccessibleModalProps) {
const dialogRef = useRef<HTMLDialogElement>(null);
useEffect(() => {
const dialog = dialogRef.current;
if (!dialog) return;
if (isOpen) {
if (!dialog.open) {
dialog.showModal();
}
} else {
if (dialog.open) {
dialog.close();
}
}
}, [isOpen]);
return (
<dialog
ref={dialogRef}
aria-labelledby={titleId}
onCancel={(e) => {
e.preventDefault();
onClose();
}}
className="w-full max-w-lg rounded-xl bg-background p-6 shadow-2xl border backdrop:bg-black/60 outline-none"
>
{children}
</dialog>
);
}
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.
- today First seen · 152 lines · 34 tokens per session scan A 2b73d98ad7b0
Web Accessibility is a skill published in the GitHub repository kok-o/contextos-agents (10 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,253 once invoked, about $0.0001 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 2026-10-25.
Other skills, from other repositories
tailwind-design-system
Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
scrollcraft-layout
Turn a static site into a premium, multi-layered, scroll-driven experience (the "ScrollCraft" approach from Nate Herk's Claude design-skill video, adapted to Anton's no-npm static sites). Use when Anton asks for "multi-layered layout", "layers when you scroll", "interactive scrolling", "make it gorgeous / premium"…
brand-guidelines
Applies brand colors and typography to any artifact requiring visual styling. Use it when brand colors, style guidelines, visual formatting, or design standards apply. Works with any brand palette, not just Anthropic's.
tailwind-expert
Expert Tailwind CSS: utility-first styling, responsive/dark mode, theming, and design systems. Trigger keywords: Tailwind, CSS, utility classes, responsive, breakpoints, dark mode, design tokens, theme, @apply, cva, clsx, class-variance-authority, arbitrary values, shadcn. Use for styling UIs, responsive layouts…
ui
Generation d'interfaces SaaS — basic, premium dark-mode, ou landing page complete. Choisir le mode selon le besoin.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…