ai-agent-automation: Skill for Claude Code

.agents/skills/wcag-audit-patterns/SKILL.md

wcag-audit-patterns is a skill for Claude Code, Codex from vmDeshpande/ai-agent-automation. It costs 45 tokens per session (535 once invoked), scanned A, a copy of wcag-audit-patterns, Apache-2.0.

A guide for checking websites against WCAG 2.2, an international accessibility standard. Accessibility means making websites usable by people with disabilities, including people who use keyboards or assistive technology.

In plain words
What is it for?
Use it for accessibility audits, fixing WCAG issues, building accessible components, or preparing for accessibility and compliance reviews.
Why use it?
It helps identify barriers such as missing image descriptions, poor color contrast, or forms without labels. It also explains the severity levels and ways to correct violations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is vmDeshpande/ai-agent-automation's own configuration. It tells Claude Code and Codex how to work on ai-agent-automation itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agent-automation configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vmDeshpande/ai-agent-automation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vmDeshpande/ai-agent-automation/main/.agents/skills/wcag-audit-patterns/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vmDeshpande/ai-agent-automation

Made for: Claude Code, Codex.

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 wcag-audit-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns/github.svg)](https://agentmods.dev/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns)
Your own site
<a href="https://agentmods.dev/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns"><img src="https://agentmods.dev/badge/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns/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 wcag-audit-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns"><img src="https://agentmods.dev/badge/skills/vmdeshpande/ai-agent-automation/wcag-audit-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 535 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 100% copy Near-identical to another mod 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 $0.00045 $0.00535
Opus 5 $0.00023 $0.00267
Sonnet 5 $0.00009 $0.00107
Haiku 4.5 $0.00005 $0.00053

Measured 12d ago against content hash db263a3405de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wcag-audit-patterns 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.

Origin

This is a copy

100% identical to wcag-audit-patterns — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/wcag-audit-patterns/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WCAG Audit Patterns

Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation strategies.

When to Use This Skill

  • Conducting accessibility audits
  • Fixing WCAG violations
  • Implementing accessible components
  • Preparing for accessibility lawsuits
  • Meeting ADA/Section 508 requirements
  • Achieving VPAT compliance

Core Concepts

1. WCAG Conformance Levels

Level Description Required For
A Minimum accessibility Legal baseline
AA Standard conformance Most regulations
AAA Enhanced accessibility Specialized needs

2. POUR Principles

Perceivable:  Can users perceive the content?
Operable:     Can users operate the interface?
Understandable: Can users understand the content?
Robust:       Does it work with assistive tech?

3. Common Violations by Impact

Critical (Blockers):
├── Missing alt text for functional images
├── No keyboard access to interactive elements
├── Missing form labels
└── Auto-playing media without controls

Serious:
├── Insufficient color contrast
├── Missing skip links
├── Inaccessible custom widgets
└── Missing page titles

Moderate:
├── Missing language attribute
├── Unclear link text
├── Missing landmarks
└── Improper heading hierarchy

Detailed patterns and worked examples

Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.

Best Practices

Do's

  • Start early - Accessibility from design phase
  • Test with real users - Disabled users provide best feedback
  • Automate what you can - 30-50% issues detectable
  • Use semantic HTML - Reduces ARIA needs
  • Document patterns - Build accessible component library

Don'ts

  • Don't rely only on automated testing - Manual testing required
  • Don't use ARIA as first solution - Native HTML first
  • Don't hide focus outlines - Keyboard users need them
  • Don't disable zoom - Users need to resize
  • Don't use color alone - Multiple indicators needed

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file 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. 12d ago First seen · 81 lines · 45 tokens per session scan A db263a3405de

Subscribe to this mod's changes

wcag-audit-patterns is a skill published in the GitHub repository vmDeshpande/ai-agent-automation (178 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 535 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to wcag-audit-patterns, differing in 0 lines, and is treated as a copy.