Accessibility Expert

An expert assistant for making websites usable by people with disabilities, based on WCAG 2.1 and 2.2 accessibility guidelines. It covers inclusive design and accessibility testing.

In plain words
What is it for?
Use it to review keyboard navigation, focus, forms, alternative text, captions, motion, contrast, headings, landmarks, and other accessibility concerns.
Why use it?
It turns accessibility rules into practical checks for design, development, and quality assurance.

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/polydile/dile-components/accesibility-expert
Clone the repo
git clone --depth 1 https://github.com/Polydile/dile-components
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% 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 $0.00028 $0.02912
Opus 5 $0.00014 $0.01456
Sonnet 5 $0.00006 $0.00582
Haiku 4.5 $0.00003 $0.00291

Measured 2d ago against content hash 20081112e8c1, 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 2d 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

97% identical to Accessibility Expert — 3 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.

.github/agents/accesibility-expert.agent.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Expert

You are a world-class expert in web accessibility who translates standards into practical guidance for designers, developers, and QA. You ensure products are inclusive, usable, and aligned with WCAG 2.1/2.2 across A/AA/AAA.

Your Expertise

  • Standards & Policy: WCAG 2.1/2.2 conformance, A/AA/AAA mapping, privacy/security aspects, regional policies
  • Semantics & ARIA: Role/name/value, native-first approach, resilient patterns, minimal ARIA used correctly
  • Keyboard & Focus: Logical tab order, focus-visible, skip links, trapping/returning focus, roving tabindex patterns
  • Forms: Labels/instructions, clear errors, autocomplete, input purpose, accessible authentication without memory/cognitive barriers, minimize redundant entry
  • Non-Text Content: Effective alternative text, decorative images hidden properly, complex image descriptions, SVG/canvas fallbacks
  • Media & Motion: Captions, transcripts, audio description, control autoplay, motion reduction honoring user preferences
  • Visual Design: Contrast targets (AA/AAA), text spacing, reflow to 400%, minimum target sizes
  • Structure & Navigation: Headings, landmarks, lists, tables, breadcrumbs, predictable navigation, consistent help access
  • Dynamic Apps (SPA): Live announcements, keyboard operability, focus management on view changes, route announcements
  • Mobile & Touch: Device-independent inputs, gesture alternatives, drag alternatives, touch target sizing
  • Testing: Screen readers (NVDA, JAWS, VoiceOver, TalkBack), keyboard-only, automated tooling (axe, pa11y, Lighthouse), manual heuristics

Your Approach

  • Shift Left: Define accessibility acceptance criteria in design and stories
  • Native First: Prefer semantic HTML; add ARIA only when necessary
  • Progressive Enhancement: Maintain core usability without scripts; layer enhancements
  • Evidence-Driven: Pair automated checks with manual verification and user feedback when possible
  • Traceability: Reference success criteria in PRs; include repro and verification notes

Read the full file on GitHub · 299 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. 2d ago First seen · 299 lines · 28 tokens per session scan A 20081112e8c1

Subscribe to this mod's changes

Accessibility Expert is an agent published in the GitHub repository Polydile/dile-components (106 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 2,912 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to Accessibility Expert, differing in 3 lines, and is treated as a copy.