accessibility-verification

accessibility-verification is a skill for Claude Code from bacchus-labs/wrangler. It costs 39 tokens per session (2,159 once invoked), scanned A, original, MIT.

A checklist and testing process for checking whether user interfaces can be used by people with disabilities. It covers automated checks, keyboard use, screen-reader announcements, and Lighthouse audits.

In plain words
What is it for?
It is for verifying new or changed interface components, checking existing interfaces during reviews, and collecting evidence before declaring UI work complete.
Why use it?
It helps find missing labels, broken keyboard controls, and other accessibility problems before an interface is released. Accessibility means making software usable by people with different abilities.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wrangler plugin — 25 skills, 16 commands, 13 agents shipped together

Good fit It is for verifying new or changed interface components, checking existing interfaces during reviews, and collecting evidence before declaring UI work complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bacchus-labs/wrangler/accessibility-verification
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 bacchus-labs/wrangler --skill accessibility-verification
Clone the repo
git clone --depth 1 https://github.com/bacchus-labs/wrangler

Made for: Claude Code.

Or install wrangler, the plugin that ships this one along with the rest of its 25 skills, 16 commands, 13 agents.

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-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/bacchus-labs/wrangler/accessibility-verification.svg)](https://agentmods.dev/skills/bacchus-labs/wrangler/accessibility-verification)
Your own site
<a href="https://agentmods.dev/skills/bacchus-labs/wrangler/accessibility-verification"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/accessibility-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,159 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 $0.00039 $0.02159
Opus 5 $0.00019 $0.01079
Sonnet 5 $0.00008 $0.00432
Haiku 4.5 $0.00004 $0.00216

Measured 8d ago against content hash b8316c49b68e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

accessibility-verification 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (example.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.wrangler/memory/knowledge-base/reference-prompts/skills/ui-related-skills/accessibility-verification/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Accessibility Verification

Overview

Accessibility testing ensures UI is usable by everyone, including users with disabilities. It's both a legal requirement (WCAG compliance) and fundamental to good UX.

When to use this skill:

  • Implementing any UI component
  • Modifying existing UI
  • Before marking UI work complete
  • During code review (verify accessibility tested)

The Iron Law

NO UI SHIP WITHOUT ACCESSIBILITY VERIFICATION

If you created or modified UI:

  • You MUST run automated accessibility tests (axe-core)
  • You MUST test keyboard navigation
  • You MUST verify screen reader announcements
  • You CANNOT claim "UI complete" without accessibility evidence

Why Accessibility Matters

Legal requirement:

  • WCAG 2.1 Level AA compliance mandatory in many industries
  • ADA lawsuits for inaccessible websites
  • Section 508 compliance for government contracts

Better UX for everyone:

  • Accessible sites work better for all users
  • Many a11y issues are actual bugs (missing labels, broken keyboard nav)
  • If button has no accessible name, it's both unusable AND untestable

Automated testing catches ~57% of issues:

  • axe-core finds definite violations (zero false positives)
  • Manual testing required for remaining ~43%
  • Both automated AND manual testing necessary

Step-by-Step Process

Step 1: Automated Testing (axe-core)

Run axe-core on all UI components:

Playwright Integration
import { injectAxe, checkA11y } from 'axe-playwright';

test('component is accessible', async ({ page }) => {
  await page.goto('/checkout');

  // Inject axe-core into page
  await injectAxe(page);

  // Run accessibility audit
  await checkA11y(page, null, {
    detailedReport: true,
    detailedReportOptions: {
      html: true,
    },
  });
});
Cypress Integration
import 'cypress-axe';

describe('Accessibility', () => {
  it('has no a11y violations', () => {
    cy.visit('/checkout');
    cy.injectAxe();
    cy.checkA11y();
  });
});

Read the full file on GitHub · 361 lines

Files

What ships with it

2 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.

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. 8d ago First seen · 361 lines · 39 tokens per session scan A b8316c49b68e

Subscribe to this mod's changes

accessibility-verification is a skill published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 2,159 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.