Community-Access/accessibility-agents

Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.

What it solves

It prevents AI coding agents from ignoring accessibility standards (WCAG 2.2 AA) when generating code. It ensures that user-facing files are reviewed for accessibility before they can be edited and replaces memory-based audits with structured, data-driven reports.

How it works

The project provides a set of "Agent Skills" that can be read by various AI clients (like Claude Code, GitHub Copilot, and Gemini CLI). It uses a routing system where six main entry points dispatch work to 102 specialized helper and reference skills. It also includes a Model Context Protocol (MCP) server with 39 scanning tools (such as axe-core and Playwright) to perform behavioral and structural scans, and uses hooks to block unreviewed edits to user-facing files.

Who it’s for

Developers using agentic coding tools who need to enforce strict web, document, and markdown accessibility standards in their projects.

Highlights

  • Multi-client support: Works natively with Claude Code, Codex, GitHub Copilot, Gemini CLI, and Antigravity.
  • Comprehensive coverage: Reviews web UI, Office documents, PDFs, ePubs, and Markdown.
  • Guardrails: Implements hooks that refuse writes to user-facing files until an accessibility review is complete.
  • Structured reporting: Generates JSON findings and renders reports with scores and delta tracking.

Related

  • Project
    alirezarezvani/claude-skills

    A comprehensive library of 388 modular agent skills and plugins for AI coding tools, providing specialized domain expertise across engineering, business, and research.

  • Project
    borghei/Claude-Skills

    Claude Skills is an open‑source library of 385 ready‑to‑use “skills” – prompt‑plus‑Python bundles – that can be loaded into Claude, ChatGPT, Gemini, Copilot, Cursor and other LLM assistants. It ships 77 expert personas, 900 pure‑Python tools, and compliance workflows for 18 regulated frameworks, letting non‑engineers run real business, product‑management and compliance tasks via slash‑commands or plugin installation.

  • Project
    Aaronontheweb/dotnet-skills

    A comprehensive AI coding plugin providing 30 specialized skills and 5 expert agents to help AI assistants write production-grade .NET and C# code.

  • Project
    awslabs/agent-plugins

    A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.

  • Project
    Gabson0x/bountyforge

    An AI-powered pentesting framework for Claude Code that uses parallel specialized agents to audit smart contracts and web APIs, validating findings through a multi-gate process to generate submission-ready bug bounty reports.