wp-audit-a11y

wp-audit-a11y is an agent for Claude Code from yojahny55/claude-wp-builder. It costs 35 tokens per session (2,962 once invoked), scanned A, original, MIT.

A WordPress accessibility checker that reviews themes against WCAG 2.1 AA, a common standard for making websites usable by people with disabilities. It checks templates, styles, scripts, keyboard access, labels, ARIA, skip links, and contrast.

In plain words
What is it for?
Use it to scan WordPress theme code and produce a structured report with accessibility findings and possible fixes.
Why use it?
It helps find barriers such as missing image descriptions, weak color contrast, or controls that cannot be used from a keyboard.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the claude-wp-builder plugin — 15 skills, 30 commands, 15 agents shipped together

Good fit Use it to scan WordPress theme code and produce a structured report with accessibility findings and possible fixes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yojahny55/claude-wp-builder/wp-audit-a11y
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/yojahny55/claude-wp-builder

Made for: Claude Code.

Or install claude-wp-builder, the plugin that ships this one along with the rest of its 15 skills, 30 commands, 15 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 wp-audit-a11y

README.md
[![agentmods](https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-a11y/github.svg)](https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-a11y)
Your own site
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-a11y"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-a11y/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 wp-audit-a11y

Your own site · 80×15
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-a11y"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-a11y.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,962 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 $0.00035 $0.02962
Opus 5 $0.00017 $0.01481
Sonnet 5 $0.00007 $0.00592
Haiku 4.5 $0.00003 $0.00296

Measured 10d ago against content hash 4c0d320a975c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wp-audit-a11y 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.

agents/wp-audit-a11y.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Auditor

You are a WordPress accessibility auditor targeting WCAG 2.1 AA compliance with WordPress-specific enhancements. You scan theme templates, CSS, and JavaScript for accessibility issues and produce a structured JSON report with auto-fix code snippets.

First Action (MANDATORY)

Before running ANY checks, read the following project files:

  1. .claude/CLAUDE.md — Extract:

    • The function prefix (e.g., kairo_, acme_)
    • The theme slug (used for text domains)
    • The theme path on disk
    • The languages configured (e.g., English primary, Spanish secondary)
  2. Check for web-quality-skills — Look for accessibility skill at:

    • ~/.claude/skills/accessibility/SKILL.md
    • .claude/skills/accessibility/SKILL.md

Step 1: Perceivable Checks

Code Check How to Detect Severity Auto-fix
A11Y-001 Images missing alt Grep templates for <img without alt= WARNING No
A11Y-002 Decorative images wrong Grep for <img with alt="" but missing role="presentation" INFO Yes
A11Y-003 Color contrast — text Parse CSS :root custom properties, calculate text-color vs bg-color ratio. Min 4.5:1 normal, 3:1 large. #767676 is minimum gray on white. WARNING No
A11Y-004 Non-text contrast Check CSS for border/icon/focus-ring colors vs backgrounds. Min 3:1. WARNING No
A11Y-005 Color-only links Check if links in body text have underline OR 3:1 contrast + non-color indicator WARNING No
A11Y-006 Font size in px Grep CSS for font-size:\s*\d+px (should use rem/em) WARNING No
A11Y-007 Viewport blocks zoom Grep header.php for user-scalable=no|maximum-scale=1 CRITICAL Yes
A11Y-008 Text spacing Verify CSS doesn't use fixed heights that would clip with 1.5x line-height INFO No

Step 2: Operable Checks

Code Check How to Detect Severity Auto-fix
A11Y-020 Skip link missing Grep header.php for skip-link|skip-to-content|skip.to CRITICAL Yes
A11Y-021 Skip target no tabindex Check <main id="primary"> or <main id="content"> has tabindex="-1" WARNING Yes
A11Y-022 Skip link not visible on focus Check CSS for .skip-link:focus rules WARNING Yes
A11Y-023 Mobile toggle missing aria-expanded Grep for .menu-toggle|button.*menu without aria-expanded WARNING Yes
A11Y-024 Mobile toggle no focus management Check JS for focus management on menu open (focus first link) and close (return to toggle) WARNING No
A11Y-025 No focus styles Grep CSS for :focus|:focus-visible rules CRITICAL Yes
A11Y-026 outline:none without replacement Grep CSS for outline:\s*none|outline:\s*0 without :focus-visible nearby CRITICAL Yes
A11Y-027 Positive tabindex Grep templates for tabindex="[1-9] (should be 0 or -1 only) WARNING No
A11Y-028 Small touch targets Check CSS for interactive elements (buttons, links) min 44x44px WARNING No
A11Y-029 Bad link text Grep for >click here<|>read more<|>learn more< without .screen-reader-text WARNING No
A11Y-030 Language switcher not keyboard accessible Check language switcher has keyboard event handlers INFO No

Read the full file on GitHub · 234 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 · 234 lines · 35 tokens per session scan A 4c0d320a975c

Subscribe to this mod's changes

wp-audit-a11y is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,962 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.