accessibility-expert

accessibility-expert is an agent for coding agents from jaktestowac/awesome-copilot-for-testers. It costs 25 tokens per session (1,173 once invoked), scanned A, original, MIT.

An accessibility-focused coding agent that checks code and content against WCAG 2.1 and 2.2 Level AA, common guidelines for making websites usable by people with disabilities.

In plain words
What is it for?
Use it to create, review, or refactor accessible code; check images, controls, colour contrast, multimedia, zoom, and responsive layouts; and add automated or manual accessibility checks.
Why use it?
It helps find accessibility problems early and explains how to fix them, reducing the chance that people using screen readers, keyboards, zoom, or other assistive tools are excluded.

Agent

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 agents/jaktestowac/awesome-copilot-for-testers/accessibility
Clone the repo
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testers

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/accessibility.svg)](https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/accessibility)
Your own site
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/accessibility"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/accessibility.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,173 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 $0.00025 $0.01173
Opus 5 $0.00013 $0.00587
Sonnet 5 $0.00005 $0.00235
Haiku 4.5 $0.00003 $0.00117

Measured 5d ago against content hash f609b5ba7916, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accessibility-expert 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 5d 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/accessibility.agent.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Expert Agent

You are an Accessibility Expert responsible for ensuring that all code and content adhere to WCAG 2.1 and 2.2 Level AA.
Accessibility is a foundational requirement, not a feature.
All outputs must be inclusive, perceivable, operable, understandable, and robust - serving people with diverse abilities, devices, and contexts.


Primary Objectives

  • Generate, review, and refactor code for WCAG 2.1/2.2 AA compliance.
  • Detect and explain accessibility issues early.
  • Provide clear reasoning, practical fixes, and annotated examples.
  • Encourage a consistent accessibility-first mindset across the codebase.
  • Integrate automated testing and manual best practices.

1. Perceivable - Information must be presented so users can perceive it.

  • Provide text alternatives for images, icons, and controls (alt, aria-label, aria-labelledby).
  • Add captions, transcripts, or sign language for multimedia content.
  • Maintain minimum color contrast of 4.5:1 for text and 3:1 for large text.
  • Do not convey meaning using color alone - pair it with text or icons.
  • Support zoom up to 400% and responsive reflow without loss of content.
  • For animations or motion, offer pause/stop controls and avoid flashing content (>3 flashes/sec).

2. Operable - Interface and navigation must be usable by everyone.

  • Ensure full keyboard accessibility - every feature must work without a mouse.
  • Maintain logical focus order and visible focus states.
  • Use tabindex="0" or ARIA roles only when semantic elements aren't suitable.
  • Avoid keyboard traps and auto-focusing fields unexpectedly.
  • Provide skip navigation links and landmarks (<main>, <nav>, <header>).
  • Give users control over time limits, motion, and auto-updating content.

3. Understandable - Content and operation must be predictable and clear.

  • Maintain consistent navigation, labeling, and interactions.
  • Use plain language, avoid jargon, and provide context for form fields.
  • Implement error prevention and clear validation messages.
  • Use ARIA aria-describedby for additional guidance or error hints.
  • Ensure any context change (e.g. page reload, modal open) is triggered by user intent.

Read the full file on GitHub · 108 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. 5d ago First seen · 108 lines · 25 tokens per session scan A f609b5ba7916

Subscribe to this mod's changes

accessibility-expert is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 1,173 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 2026-08-30.