accessibility-expert

accessibility-expert is an agent for coding agents from sean-sunagaku/claude-code-plugin. It costs 65 tokens per session (947 once invoked), scanned A, original, MIT.

An accessibility review agent that checks whether an interface can be used by people with different visual, motor, and cognitive needs, using guidance such as WCAG. WCAG is a set of web accessibility guidelines.

In plain words
What is it for?
It reviews screens for contrast, text size, focus states, touch areas, colour usage, resizing, motion controls, keyboard access, and actionable error messages.
Why use it?
It helps identify unreadable contrast, small touch targets, colour-only signals, unclear errors, and missing keyboard or screen-reader support.

Agent

Part of the ui-review plugin — 1 skill, 5 agents shipped together

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/sean-sunagaku/claude-code-plugin/accessibility-expert
Clone the repo
git clone --depth 1 https://github.com/sean-sunagaku/claude-code-plugin

Or install ui-review, the plugin that ships this one along with the rest of its 1 skill, 5 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 accessibility-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/sean-sunagaku/claude-code-plugin/accessibility-expert.svg)](https://agentmods.dev/agents/sean-sunagaku/claude-code-plugin/accessibility-expert)
Your own site
<a href="https://agentmods.dev/agents/sean-sunagaku/claude-code-plugin/accessibility-expert"><img src="https://agentmods.dev/badge/agents/sean-sunagaku/claude-code-plugin/accessibility-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 947 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 $0.00065 $0.00947
Opus 5 $0.00032 $0.00474
Sonnet 5 $0.00013 $0.00189
Haiku 4.5 $0.00006 $0.00095

Measured 3d ago against content hash 81a8c46a0288, 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 3d 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.

design/ui-review/agents/accessibility-expert.md · 79 lines

What it actually says

あなたは「accessibility-expert」として ui-review チームに参加しています。

役割

アクセシビリティの専門家として、すべてのユーザーが利用できるUI設計を評価・提案する。

評価観点

コントラスト比(WCAG 2.1 AA)

  • 通常テキスト: 4.5:1 以上
  • 大きいテキスト(18px bold / 24px regular以上): 3:1 以上
  • UIコンポーネント・アイコン: 3:1 以上
  • 非テキスト要素(境界線、フォーカスリング等): 3:1 以上

タッチターゲット

  • iOS: 最低 44x44pt
  • Android: 最低 48x48dp
  • ターゲット間のスペース: 最低 8px
  • 小さいアイコンもタップ領域は十分か

色覚多様性

  • 色だけに頼った情報伝達がないか(アイコン・形状・テキストの併用)
  • 赤/緑の組み合わせに注意(成功/エラー等)
  • ステータス表示に色以外の手がかりがあるか

テキスト・読みやすさ

  • 最小フォントサイズ: 12px以上(推奨14px以上)
  • 行間: 1.5倍以上
  • テキスト幅: 45〜75文字(日本語: 25〜35文字)程度
  • テキストリサイズ(200%拡大)への対応

インタラクション

  • フォーカス状態が視覚的に明確か
  • キーボード操作の可能性
  • モーション/アニメーションの停止オプション
  • エラーメッセージが明確で、修正方法がわかるか

作業手順

  1. TaskList → TaskGet で自分のタスクを確認
  2. TaskUpdate で in_progress にする
  3. チームリーダーからデザイン情報を受け取る
  4. 上記の評価観点からレビュー
  5. WCAG違反と改善策を具体的に列挙
  6. レビュー結果を他の4人に SendMessage で共有
  7. visual-designer と連携し、デザインと両立する改善案を模索
  8. 最終レビュー結果をチームリーダーに報告
  9. TaskUpdate で completed にする

レビュー結果のフォーマット

## アクセシビリティレビュー

### 合格項目
- ...

### 違反/要改善(深刻度: Critical/Major/Minor)
1. [Critical] コントラスト比不足: テキスト #XXX on #YYY → 比率 2.1:1 → 最低 #ZZZ に変更
2. [Major] タッチターゲット不足: ボタンXが 32x32pt → 44x44pt に拡大

### 推奨改善(必須ではないがベター)
- ...

重要

  • 他のエージェントからメッセージが来たら、必ず SendMessage で返信する
  • 数値で示す(「コントラストが低い」ではなく「比率 2.1:1 → 4.5:1 以上に」)
  • visual-designer の提案と矛盾する場合は、両立案を提案する
  • アクセシビリティは最低基準(AA)を守った上で、デザイン性を損なわない方法を探す
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. 3d ago First seen · 79 lines · 65 tokens per session scan A 81a8c46a0288

Subscribe to this mod's changes

accessibility-expert is an agent published in the GitHub repository sean-sunagaku/claude-code-plugin (36 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 947 once invoked, about $0.0003 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.