I realized I let the agent start coding before I was sure it was working on the right thing, so I built this. Now it doesn't get to write code before there's a reason. The agent asks who this is for. It asks what you're assuming, and what would show you wrong. The rules run as hooks, so once you have started it in a repo the build stays shut until the answers are there. Purpose, strategy, opportunities, then delivery and market feedback. It adds skills and hooks, keeps its own state in a .claude/ folder, and won't edit the files already in your repo unless you ask it to.
Accessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app / video_audio / document / headless, then applies only the criteria that bind. WCAG 2.1 AA in full for web; not at all for headless.
Pinned to revision d44421b0667b, so it is the text this page describes rather than whatever the author pushed since.
Every link opens the file at its source, pinned to the revision this page describes.
