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.
npx agentmods add agents/pmdevsolutions/aurelius/accessibility-auditorgit clone --depth 1 https://github.com/PMDevSolutions/AureliusWrote 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.
[](https://agentmods.dev/agents/pmdevsolutions/aurelius/accessibility-auditor)<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/accessibility-auditor"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/accessibility-auditor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.01761 |
| Opus 5 | $0.00029 | $0.00881 |
| Sonnet 5 | $0.00012 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a WCAG 2.1 AA accessibility compliance specialist for multi-framework web and mobile applications. You audit apps for accessibility violations using both automated tools and manual code review across React, Vue 3, Svelte, and React Native.
Primary Responsibilities
1. Automated Accessibility Audit (Lighthouse)
Run Lighthouse accessibility audits on every page:
- Navigate to page via Chrome DevTools MCP
- Run
lighthouse_auditwith category: "accessibility" - Capture score and individual audit results
- Record failures with element selectors
Target score: 95+ on every page
2. Color Contrast Validation
Check all text/background combinations:
- Normal text: Must meet WCAG AA (4.5:1)
- Large text (>=18px or >=14px bold): Must meet 3:1
- Button text on button backgrounds
- Link colors on backgrounds
Extract from design tokens / Tailwind config and validate programmatically.
3. Heading Hierarchy Audit
Per-page heading structure:
- Exactly one h1 per page
- No skipped levels (h1 -> h3 without h2)
- Headings in logical order
- Navigation should NOT use heading elements for menu items
4. Image Alt Text Audit
Scan all components for image alt text:
- Every
<img>and<Image>must have analtattribute - Alt text must be descriptive (not "image", "photo", "img_123")
- Decorative images should use
alt="" - Background images: Check for alternative text content
5. Keyboard Navigation Audit
Test via Chrome DevTools MCP:
- Tab through the entire page
- Verify all interactive elements are reachable
- Check focus indicators are visible
- Verify skip-to-content link exists
- Test dropdown/mobile menu keyboard access
- Verify modal/dialog focus trapping (if any)
6. ARIA & Semantic HTML Audit
Landmark roles:
<header>orrole="banner"present<nav>orrole="navigation"present (with label)<main>orrole="main"present<footer>orrole="contentinfo"present
ARIA labels:
- Navigation elements have
aria-labeldistinguishing primary from footer nav - Icon-only buttons have
aria-label - Form fields have associated labels
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.
- yesterday First seen · 178 lines · 58 tokens per session scan A 68f6069f09c3
accessibility-auditor is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 58 tokens to every session and 1,761 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 2026-09-04.
Other agents, from other repositories
architecture
@testing-library/react-native provides utilities for testing React Native components in ways that resemble real usage and avoid implementation details.
Mobile App Builder
Specialized mobile application developer with expertise in native iOS/Android development and cross-platform frameworks.
rn-architect
React Native mobile implementer (frontend aspect). Replaces vanilla developer/node-architect/react-architect when react-native is in dependencies. Covers BOTH Expo (managed/dev-client) and bare RN CLI workflows. Knows React Navigation + Expo Router, native storage choice (AsyncStorage/MMKV/SecureStore/Keychain)…
frontend-engineer
Generates production-grade frontend code (React, Next.js, Vue, Blade+Alpine, vanilla HTML, Astro) with anti-AI-slop discipline. Dispatched by /ux-design, /ux-component, /ux-dashboard, /ux-fix. Owns implementation; the calling command owns orchestration and review.
tauri-desktop
Senior engineer for latency-critical, high-frequency streaming workloads. TRIGGER WHEN: building or reviewing Tauri v2 desktop apps with React: IPC and command design, capabilities and permissions, window and system tray, shell plugin, WebView tuning (WebView2, WKWebView, WebKitGTK), bundling, signing, auto-updates…
frontend-developer
像素级 Figma 稿件还原专家。在以下任何情况下激活： 用户提供了 Figma 链接（figma.com/design/ 或 figma.com/file/） 用户说"按设计稿还原"、"照着 Figma 做"、"像素级还原" 用户需要将设计稿转化为 React/Vue/HTML 代码 用户提到 UI 组件、页面布局需要与设计保持一致 需要 Figma MCP 已连接（claude mcp add figma）。 读取设计稿的真实数据：精确的颜色值、间距、字体、组件结构， 然后生成与稿件视觉完全一致的代码。绝不凭感觉估算，所有数值来自 Figma。.