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.
git clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/plugins/radorigin-llc/rad-claude-skills/rad-a11y)<a href="https://agentmods.dev/plugins/radorigin-llc/rad-claude-skills/rad-a11y"><img src="https://agentmods.dev/badge/plugins/radorigin-llc/rad-claude-skills/rad-a11y/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.
<a href="https://agentmods.dev/plugins/radorigin-llc/rad-claude-skills/rad-a11y"><img src="https://agentmods.dev/badge/plugins/radorigin-llc/rad-claude-skills/rad-a11y.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rad-a11y 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 9d 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.
What it actually says
{
"name": "rad-a11y",
"version": "2.2.1",
"description": "WCAG 2.2 AA accessibility toolkit for Claude Code. Six skills covering semantic HTML, ARIA patterns, keyboard/focus, forms, automated testing setup, and a static-analysis review pass; one autonomous reviewer agent. **Four pure-stdlib Python validators** (scan-jsx-patterns, check-tailwind-contrast with real WCAG sRGB math, check-target-size for WCAG 2.5.8, lint-aria wrapping eslint-plugin-jsx-a11y when installed) run in parallel before LLM judgment. **Stack-aware phase routing** detects React, Next.js, Astro, Tailwind, Radix, Headless UI from package.json + config files; framework-specific Phase 8 slices only execute when the stack matches. **Cross-model**: Opus- and Sonnet-class models issue Phase 0 + Phase 1 as a single parallel tool-call burst; Haiku-class models fall back to sequential phases if parallel batching misbehaves — final report is identical. The /a11y-review skill performs static pattern matching over JSX/HTML/CSS source — it is not an audit and does not run axe-core, does not test runtime focus behavior, does not test with screen readers. Findings tagged [STATIC] / [HEURISTIC] / [NEEDS-MANUAL] by detection confidence; no Pass/Fail compliance verdict is issued because static analysis cannot defensibly produce one. Pair with the a11y-testing skill for real axe runtime via jest-axe / Playwright, and manual screen reader testing for full coverage.",
"author": {
"name": "RAD",
"url": "https://github.com/RadOrigin-LLC"
},
"license": "Apache-2.0",
"homepage": "https://github.com/RadOrigin-LLC/RAD-Claude-Skills/tree/main/plugins/rad-a11y",
"repository": "https://github.com/RadOrigin-LLC/RAD-Claude-Skills",
"keywords": ["accessibility", "wcag", "a11y", "aria", "wcag22", "keyboard", "focus", "contrast", "screen-reader", "axe-core", "react", "astro", "tailwind", "semantic-html", "forms"]
}
What it installs
The manifest is a name and a version. 6 skills, 1 agent travel with it, and installing the plugin installs all of them — 939 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 9d ago First seen · 14 lines scan A 6018e4acf77c
rad-a11y is a plugin published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 22d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
wes-bos-sick-picks
Research-first workflow for building modern, accessible frontend UI components in the spirit of Wes Bos. Researches pitfalls and platform capabilities before planning, designs for WCAG accessibility with modern web standards, then verifies the approach against Wes Bos on X plus trusted sources (MDN, web.dev…
agent-scaffolders
Meta-plugin containing ecosystem generation and evolution auditing primitives. Includes scaffolding for Agent Skills, Plugins, CLI sub-agents, custom GitHub Copilot agents, GitHub Agentic Workflows (gh-aw), CI/CD Smart Failure agents, Azure Foundry agents, and skill evolution auditing (audit-skill).
android-reverse-engineering
Decompile Android APK/JAR/AAR with jadx, trace call flows through libraries, and document extracted APIs.
ai-cli-harness-better-practices
Harness-agnostic session continuity: goal statements, status snapshots, handoffs, cold resume, replanning, and wrap-up. No git or GitHub required.
codeql-resolver
Systematic CodeQL alert analysis and resolution for GitHub Actions workflows.
script-guards
Prevents unnecessary script generation - enforces research-first, native-tool-first patterns via PreToolUse and UserPromptSubmit hooks.