openauditB85out of 100: openaudit's audit of itself
agent.a11y-journeys

Accessibility journeys (keyboard & screen reader)

Walks key user journeys keyboard-only and through the accessibility tree to find what automated checkers like axe cannot: focus management, dialogs, errors, live regions, reflow, zoom and motion. (agentic, uses Claude)

Engine
Agent
Targets
Web app, URL
Areas
Accessibility
Runs
Opt-in: only when selected with --only
Network
Contacts services beyond the target

Run only this auditor

bunx openaudit https://example.com --browser --only agent.a11y-journeys

Runs a playbook with the Claude Agent SDK. Needs ANTHROPIC_API_KEY or a Claude Code login; host agents can run the same playbook over MCP without a key.

Playbook

Walks key user journeys keyboard-only and through the accessibility tree to find what automated checkers like axe cannot: focus management, dialogs, errors, live regions, reflow, zoom and motion.

Host agents fetch it with get_playbook over MCP. How playbooks work