accessibility-wcag

accessibility-wcag is a skill for Claude Code from medy-gribkov/arcana. It costs 38 tokens per session (2,868 once invoked), scanned A, original, Apache-2.0.

Guidance for checking and fixing web accessibility against WCAG, a set of standards for making websites usable by people with disabilities. It covers semantic HTML, ARIA, keyboard use, screen readers, focus, colour contrast, and automated checks.

In plain words
What is it for?
Use it to audit web pages, fix inaccessible controls and forms, improve keyboard and screen-reader support, manage focus, and run accessibility tests.
Why use it?
It helps reveal barriers that may prevent people from navigating, reading, or completing tasks on a website.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to audit web pages, fix inaccessible controls and forms, improve keyboard and screen-reader support, manage focus, and run accessibility tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/medy-gribkov/arcana/accessibility-wcag
Install

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.

Any agent
npx skills add medy-gribkov/arcana --skill accessibility-wcag
Clone the repo
git clone --depth 1 https://github.com/medy-gribkov/arcana

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin accessibility-wcag/plugin install accessibility-wcag after adding the marketplace above.

Wrote 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.

agentmods badge for accessibility-wcag

README.md
[![agentmods](https://agentmods.dev/badge/skills/medy-gribkov/arcana/accessibility-wcag/github.svg)](https://agentmods.dev/skills/medy-gribkov/arcana/accessibility-wcag)
Your own site
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/accessibility-wcag"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/accessibility-wcag/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.

agentmods 80×15 button for accessibility-wcag

Your own site · 80×15
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/accessibility-wcag"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/accessibility-wcag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.02868
Opus 5 $0.00019 $0.01434
Sonnet 5 $0.00008 $0.00574
Haiku 4.5 $0.00004 $0.00287

Measured 10d ago against content hash 0f675d600ad2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

accessibility-wcag 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 10d 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.

skills/accessibility-wcag/SKILL.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility & WCAG Compliance

Audit web applications for WCAG 2.1/2.2 compliance, fix accessibility barriers, implement proper semantic HTML and ARIA patterns.

BAD: Common Accessibility Violations

// BAD: Div button without keyboard support
<div className="btn" onClick={handleClick}>
  Submit
</div>

// BAD: Color-only error indication
<input className="border-red-500" />
<span style={{color: 'red'}}>Error</span>

// BAD: Image without alt text
<img src="/chart.png" />

// BAD: Aria-label overuse
<button aria-label="Click me">Click me</button>

// BAD: Auto-focus abuse
<input autoFocus />
<Modal open={isOpen}>
  <input autoFocus /> {/* Steals focus */}
</Modal>

// BAD: No heading hierarchy
<h1>Page Title</h1>
<h4>Section</h4> {/* Skips h2, h3 */}

// BAD: Form without labels
<input type="text" placeholder="Email" />
<select>
  <option>Choose...</option>
</select>

// BAD: Custom dropdown without keyboard support
<div onClick={toggle}>
  {options.map(opt => <div onClick={() => select(opt)}>{opt}</div>)}
</div>

GOOD: Accessible Implementations

// GOOD: Semantic button with proper keyboard support
<button type="button" onClick={handleClick}>
  Submit
</button>

// GOOD: Multi-sensory error indication
<input
  className="border-red-500"
  aria-invalid="true"
  aria-describedby="email-error"
/>
<span id="email-error" className="text-red-600" role="alert">
  <span className="sr-only">Error:</span>
  Invalid email format
</span>

// GOOD: Descriptive alt text (or empty for decorative)
<img src="/sales-chart.png" alt="Sales increased 40% in Q4" />
<img src="/decorative-line.svg" alt="" role="presentation" />

// GOOD: Redundant aria-label removed
<button>Click me</button>

// GOOD: Managed focus with trap
function Modal({ open, onClose, children }) {
  const modalRef = useRef<HTMLDivElement>(null);

  useEffect(() => {
    if (!open) return;

    const previousFocus = document.activeElement as HTMLElement;
    modalRef.current?.focus();

    return () => previousFocus?.focus();
  }, [open]);

  return (
    <div
      ref={modalRef}
      role="dialog"
      aria-modal="true"
      tabIndex={-1}
      onKeyDown={(e) => {
        if (e.key === 'Escape') onClose();
      }}
    >
      {children}
    </div>
  );
}

// GOOD: Proper heading hierarchy
<h1>Page Title</h1>
<h2>Main Section</h2>
<h3>Subsection</h3>
<h2>Another Section</h2>

// GOOD: Labeled form controls
<label htmlFor="email">Email address</label>
<input
  id="email"
  type="email"
  aria-required="true"
  aria-describedby="email-hint"
/>
<span id="email-hint" className="text-gray-600">
  We'll never share your email
</span>

<label htmlFor="country">Country</label>
<select id="country" aria-required="true">
  <option value="">Select a country</option>
  <option value="us">United States</option>
</select>

// GOOD: Accessible custom dropdown
function Dropdown({ options, value, onChange, label }) {
  const [open, setOpen] = useState(false);
  const [activeIndex, setActiveIndex] = useState(0);
  const buttonRef = useRef<HTMLButtonElement>(null);
  const listRef = useRef<HTMLUListElement>(null);

  const handleKeyDown = (e: KeyboardEvent) => {
    switch (e.key) {
      case 'ArrowDown':
        e.preventDefault();
        setActiveIndex(prev => Math.min(prev + 1, options.length - 1));
        break;
      case 'ArrowUp':
        e.preventDefault();
        setActiveIndex(prev => Math.max(prev - 1, 0));
        break;
      case 'Enter':
      case ' ':
        e.preventDefault();
        onChange(options[activeIndex]);
        setOpen(false);
        buttonRef.current?.focus();
        break;
      case 'Escape':
        setOpen(false);
        buttonRef.current?.focus();
        break;
    }
  };

  return (
    <div>
      <button
        ref={buttonRef}
        type="button"
        aria-haspopup="listbox"
        aria-expanded={open}
        aria-labelledby="dropdown-label"
        onClick={() => setOpen(!open)}
      >
        <span id="dropdown-label">{label}</span>: {value}
      </button>

      {open && (
        <ul
          ref={listRef}
          role="listbox"
          aria-labelledby="dropdown-label"
          onKeyDown={handleKeyDown}
          tabIndex={-1}
        >
          {options.map((opt, i) => (
            <li
              key={opt}
              role="option"
              aria-selected={i === activeIndex}
              onClick={() => {
                onChange(opt);
                setOpen(false);
                buttonRef.current?.focus();
              }}
            >
              {opt}
            </li>
          ))}
        </ul>
      )}
    </div>
  );
}

Read the full file on GitHub · 464 lines

Changes

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.

  1. 10d ago First seen · 464 lines · 38 tokens per session scan A 0f675d600ad2

Subscribe to this mod's changes

accessibility-wcag is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,868 once invoked, about $0.0002 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.