accessibility-audit

accessibility-audit is a command for Claude Code from navraj007in/architecture-cowork-plugin. It costs 16 tokens per session (1,826 once invoked), scanned A, original, Apache-2.0.

A command that checks frontend code—code for a website or app interface—against WCAG 2.1 AA accessibility guidelines. It reports scored findings for issues such as contrast, keyboard use, focus, labels, and semantic HTML.

In plain words
What is it for?
Auditing web, mobile, and desktop frontend components with automated accessibility scans and heuristic checks that may need manual review.
Why use it?
It helps identify barriers that can prevent people using keyboards or screen readers from using the interface, while also flagging contrast and other accessibility problems.

Command for Claude Code

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

Part of the architect plugin — 48 skills, 63 commands, 19 agents, 7 MCP servers shipped together

Good fit Auditing web, mobile, and desktop frontend components with automated accessibility scans and heuristic checks that may need manual review.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/navraj007in/architecture-cowork-plugin/accessibility-audit
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.

Clone the repo
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-plugin

Made for: Claude Code.

Or install architect, the plugin that ships this one along with the rest of its 48 skills, 63 commands, 19 agents, 7 MCP servers.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/accessibility-audit/github.svg)](https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/accessibility-audit)
Your own site
<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/accessibility-audit"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/accessibility-audit/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-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/accessibility-audit"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/accessibility-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,826 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 $0.00016 $0.01826
Opus 5 $0.00008 $0.00913
Sonnet 5 $0.00003 $0.00365
Haiku 4.5 $0.00002 $0.00183

Measured 12d ago against content hash 8b07da0dadc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

accessibility-audit 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 12d 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.

commands/accessibility-audit.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/architect:accessibility-audit

Trigger

/architect:accessibility-audit [options]

Options:

  • [non_interactive:true] — skip questions, scan all frontend components
  • [components:web-app,mobile-app] — audit specific components only

Purpose

Accessible products serve more users and reduce liability. This command scans scaffolded frontend code for WCAG 2.1 AA compliance: color contrast (from design tokens), focus management, ARIA labels, keyboard navigation, semantic HTML, screen reader support. Uses axe-core/pa11y/playwright-axe for automated scanning plus heuristic checks for manual review items.

Workflow

Quick Navigation

Phase Steps
Setup Step 1
Scanning Step 2 · Step 3
Completion Step 4 · Step 5 · Step 6

Step 1: Read Context & Detect Frontends

ℹ️ CONTEXT LOADING: _state.json → SDL → scaffolded frontends

Read:

  • _state.json.components[] with type: web, mobile, desktop
  • _state.json.design for color palette (used for contrast checking)
  • Scaffolded frontend paths (web-app/src/, app/src/, etc.)

Check for frontend technologies:

  • React/Next.js: component files in src/components/
  • Vue: component files in src/components/
  • Angular: component files in src/components/
  • Svelte: component files in src/components/
  • Flutter/React Native: view files (accessibility different - report separately)

If no frontends found:

"I need scaffolded frontend code to audit. Run /architect:scaffold first, then come back here."

Step 2: Scan Frontend Code

QUALITY GATE: Run accessibility scanning

For each frontend component, use axe-core patterns to check:

Automated Checks (via code scanning):

  1. Color Contrast — Check all text against design tokens primary/secondary colors
    • Success Criterion 1.4.3 (AA): contrast ratio ≥ 4.5:1 for normal text, 3:1 for large text
  2. ARIA Labels — Missing alt text, aria-label, aria-labelledby
    • Success Criterion 1.1.1: All images have alt text
    • Success Criterion 4.1.2: All form inputs have labels
  3. Keyboard Navigation — Check for keyboard trap, focus visible, tabindex
    • Success Criterion 2.1.1: All functionality available via keyboard
    • Success Criterion 2.4.7: Focus visible
  4. Semantic HTML — Check for proper heading hierarchy, list structure
    • Success Criterion 1.3.1: Semantic structure (no div-based button without proper ARIA)
  5. Form Accessibility — Label association, error messaging
    • Success Criterion 3.3.1: Error identification
    • Success Criterion 3.3.4: Error prevention

Read the full file on GitHub · 200 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. 12d ago First seen · 200 lines · 16 tokens per session scan A 8b07da0dadc4

Subscribe to this mod's changes

accessibility-audit is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,826 once invoked, about $0.0001 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.