accessibility

A frontend accessibility audit command that checks a website or component against WCAG 2.1, the main international web-accessibility standard.

In plain words
What is it for?
Use it to check semantic HTML, ARIA labels, colour contrast, keyboard navigation, and screen-reader support, with optional fixes.
Why use it?
It helps find barriers that can prevent people using keyboards, screen readers, or other assistive technology from using the interface.

Command

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.

agentmods
npx agentmods add commands/alphaaiservice/cortex/accessibility
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.11841
Opus 5 $0.00026 $0.05921
Sonnet 5 $0.00010 $0.02368
Haiku 4.5 $0.00005 $0.01184

Measured yesterday against content hash 934c95caf233, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.md · 1,397 lines

How it starts

The opening of the file, as written. The whole thing — 1,397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Audit — WCAG 2.1 Compliance

You are a senior accessibility engineer performing a thorough WCAG 2.1 audit of this frontend codebase. You have deep expertise in assistive technologies, screen readers, keyboard navigation, and inclusive design patterns.

Arguments: $ARGUMENTS

Parse flags from arguments:

  • --fix = Auto-fix common accessibility issues that can be safely remediated
  • --level=AA = Audit against WCAG 2.1 AA criteria (default)
  • --level=AAA = Audit against WCAG 2.1 AAA criteria (stricter)
  • A specific page or component name = Scope the audit to that file or directory only
  • No arguments = Scan the entire frontend codebase

Step 0: Project Discovery and Scope

Before auditing, understand the frontend architecture and determine the scope.

echo "=== Project Root ==="
pwd

echo "=== Frontend Framework Detection ==="
cat package.json 2>/dev/null | grep -E "(next|react|vue|angular|svelte|astro)" | head -10

echo "=== App Directory (Next.js) ==="
find . -maxdepth 1 -type d \( -name "app" -o -name "src" -o -name "pages" \) 2>/dev/null

echo "=== Components Directory ==="
find . -maxdepth 3 -type d -name "components" 2>/dev/null

echo "=== Style Files ==="
find . -maxdepth 4 -type f \( -name "*.css" -o -name "*.scss" -o -name "*.module.css" -o -name "tailwind.config.*" \) -not -path "*/node_modules/*" -not -path "*/.next/*" 2>/dev/null

echo "=== Total Frontend Files ==="
find . -maxdepth 6 -type f \( -name "*.tsx" -o -name "*.jsx" -o -name "*.vue" -o -name "*.svelte" -o -name "*.html" \) -not -path "*/node_modules/*" -not -path "*/.next/*" 2>/dev/null | wc -l

Use the output to determine:

  • Which framework is in use (Next.js, React, Vue, etc.)
  • Where pages and components live
  • Whether Tailwind CSS or traditional CSS is used
  • Total number of files to audit

If $ARGUMENTS specifies a page or component, narrow the scope to only those files. Otherwise, audit the entire frontend.

Initialize an accessibility findings tracker. Track every finding as:

{
  severity: "CRITICAL|MAJOR|MINOR|INFO",
  wcag_criterion: "X.X.X",
  criterion_name: "...",
  category: "Perceivable|Operable|Understandable|Robust",
  file: "...",
  line: N,
  description: "...",
  code_snippet: "...",
  remediation: "..."
}

Read the full file on GitHub · 1,397 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. yesterday First seen · 1,397 lines · 52 tokens per session scan A 934c95caf233

Subscribe to this mod's changes

accessibility is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 52 tokens to every session and 11,841 once invoked, about $0.0003 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.