🔌 pluginActivePromisingmedium

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.

Stars

306

Skill Type

🔍 Code Quality & Review

Quality Score

119/200

License

MIT

Forks

Last Updated

Jun 11, 2026

Discovered

Mar 26, 2026

Validation

Passed

github.com/Community-Access/accessibility-agents

Quality Breakdown

119/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

✓Verification/Safety+20

✓Code Examples+15

✓Composability+15

Repo Health

✓Recent Activity+15

✓Scripts/Automation+10

✓Real Usage (Issues)+10

○Single Responsibility+10

✓Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

Multiple persistent configuration modifications across .claude/, .codex/, and .gemini/ directories that alter AI tool behavior and settings
Multi-agent spawning architecture with 11+ specialist agents and multiple hubs designed to orchestrate autonomous workflows
Hook system (.claude/hooks/, .gemini/extensions/.../hooks/) with Python scripts (detect-web-project.py, enforce-edit-gate.py, mark-reviewed.py, session-start.py, session-end.py) that execute during session lifecycle without explicit user approval gates
Plugin manifest and extension definitions (.claude-plugin/marketplace.json, gemini-extension.json) designed to auto-integrate with multiple AI coding tools
Repository appears designed to modify behavior of Claude, GitHub Copilot, Codeium, and Gemini simultaneously through configuration files and hooks