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

AI coding tools often generate inaccessible code by default, frequently ignoring ARIA rules, keyboard navigation, and contrast ratios. Accessibility Agents provides a specialized team of AI agents designed to enforce WCAG AA standards and ensure that software is inclusive for blind and low-vision users.

How it works

The project provides 79 specialized agents organized into eight teams (such as Web Accessibility, Document Accessibility, and GitHub Workflow) across five different AI platforms. These agents use custom instructions, skills, and prompts to evaluate code and documents for accessibility barriers.

Supported platforms include:

  • Claude Code: Direct invocation for accessibility evaluation.
  • GitHub Copilot: Workspace instructions and agents for continuous guidance in VS Code and CLI.
  • Gemini CLI: Skills-based extensions with always-on WCAG AA context.
  • Codex CLI: Native plugins with router skills and specialist dispatch.
  • MCP Server: An HTTP-based server providing 24 accessibility scanning tools to any MCP-compatible client.

Who it’s for

Developers and teams who want to automate accessibility auditing and remediation in their development workflow to ensure compliance with WCAG standards.

Highlights

  • Comprehensive Agent Team: Includes specialists for ARIA, modals, color contrast, keyboard navigation, and more.
  • ** Endgame-to-End Integration**: Works across multiple LLM ecosystems (Claude, Copilot, Gemini, Codex).
  • Document Support: Extends beyond web code to include Office documents (DOCX, XLSX, PPTX), PDFs, and EPUBs.
  • MCP Integration: Provides a standardized server for accessibility scanning tools compatible with Claude Desktop and CI/CD pipelines.

Related

  • Project
    plugin87/ux-ui-agent-skills

    A comprehensive kit of instructions, design tokens, and runnable skills that turns AI agents into senior UX/UI architects capable of producing accessible, production-ready UI across any framework.

  • Project
    Aaronontheweb/dotnet-skills

    A library of 30 skills and 5 specialized agents for AI coding assistants to ensure professional, production-grade .NET development patterns.

  • Project
    borghei/Claude-Skills

    A comprehensive open-source library of AI skills, personas, and Python tools that enables professional workflows across engineering, product management, and regulated compliance domains.

  • Project
    xintaofei/codeg

    A multi-agent coding workspace that aggregates various AI coding agents into a single interface, enabling collaboration and collaboration and task management via git worktrees.

  • 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.