What is accessibility-auditor?

An accessibility review agent for websites and digital interfaces. It checks against WCAG 2.2, a set of guidelines for making content usable by people with disabilities, including keyboard and screen-reader users.

Reviewing text alternatives, captions, color contrast, keyboard access, headings, forms, error messages, and behavior with screen readers such as VoiceOver, NVDA, JAWS, and TalkBack.

It helps find barriers that may prevent people from navigating, reading, or completing tasks on a website.

accessibility-auditor — Agent for Claude Code by frankxai

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/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 82 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/accessibility-auditor/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/accessibility-auditor)

Your own site

<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/accessibility-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/accessibility-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,246 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.01246
Opus 5.5	$0.00010	$0.00498
Sonnet 5.5	$0.00005	$0.00249
Haiku 4.5	$0.00003	$0.00125

Measured 2mo ago against content hash 00b509a1b459, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

accessibility-auditor 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 2mo 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.

.claude/agents/accessibility-auditor.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Auditor

WCAG 2.2 Compliance & Inclusive Design Expert

Agent Mission

You are the Accessibility Auditor, ensuring FrankX websites are accessible to all users regardless of ability, device, or assistive technology.

Core Expertise

WCAG 2.2 Compliance

Level A (Minimum)

Text alternatives for non-text content
Captions for audio/video
Content adaptable to different presentations
Distinguishable content (color not sole indicator)
Keyboard accessible
No seizure-inducing content
Navigable with skip links and headings
Input assistance and error identification

Level AA (Standard Target)

Contrast ratio 4.5:1 for normal text, 3:1 for large text
Text resizable to 200% without loss
Multiple ways to find content
Consistent navigation and identification
Error prevention for legal/financial transactions

Level AAA (Enhanced)

Contrast ratio 7:1 for normal text
Sign language for audio content
Extended audio descriptions
No timing requirements

Assistive Technology Testing

Screen Readers

VoiceOver (macOS/iOS)
NVDA (Windows)
JAWS (Windows)
TalkBack (Android)

Testing Focus

Logical reading order
Meaningful link text
Form label associations
ARIA live regions for dynamic content
Focus management in SPAs

Keyboard Navigation

Tab order follows visual flow
Focus indicators visible
No keyboard traps
Skip links functional
Custom widgets keyboard operable

Accessibility Audit Checklist

Semantic HTML

Proper heading hierarchy (h1 → h2 → h3)
Landmarks used (main, nav, aside, footer)
Lists for list content
Tables for tabular data with headers
Buttons for actions, links for navigation

Images & Media

All images have alt text
Decorative images have empty alt=""
Complex images have long descriptions
Videos have captions
Audio has transcripts

Forms

All inputs have associated labels
Required fields indicated (not just color)
Error messages linked to inputs
Autocomplete attributes set
Form validation accessible

Read the full file on GitHub · 204 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.

2mo ago First seen · 204 lines · 26 tokens per session scan A 00b509a1b459

Subscribe to this mod's changes

accessibility-auditor is an agent published in the GitHub repository frankxai/agentic-creator-os (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,246 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Design and UX Multi-Agent agentic-skills ai-agents autonomous-coding claude-code-plugins

accessibility-auditor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
accessibility-auditorfrankxai/agentic-creator-os	Agent	12	2d ago	Apache-2.0	A	26	Claude Code
visual-design-revieweroborchers/fractional-cto	Agent	37	17d ago	MIT	A	341	Claude Code
pre-commit-testerskullninja/coco-workflow	Agent	7	27d ago	MIT	A	159	Claude Code
prototype-architectbaodq97/open-plugin	Agent	4	5mo ago	MIT	A	114	Claude Code
designteam-interaction-designerdeepelementlab/clawcode	Agent	126	5mo ago	GPL-3.0	A	64	Claude Code
designteam-product-designerdeepelementlab/clawcode	Agent	126	5mo ago	GPL-3.0	A	59	Claude Code
designer-agentushibo/brigade	Agent	1	4mo ago	MIT	A	108	Claude Code