Claude tests 25 Capacitor screens daily through Android CDP and iOS accessibility

• A solo developer turned Claude into an unattended QA agent for a Capacitor app, with the writeup saying it now drives web, Android, and iOS flows, checks 25 screens daily, and files bug reports.
• The implementation split cleanly by platform: the project writeup says Android WebView was reachable through Chrome DevTools Protocol, while iOS needed accessibility-based workarounds because the same control path was missing.
• Setup time was lopsided in the author's post: Android took about 90 minutes, while iOS took more than six hours because of native dialogs and weaker automation hooks.
• Hacker News discussion around the original thread framed this less as a replacement for test stacks than as a practical example of agent-driven visual regression, with commenters pointing back to Appium and WebdriverIO and calling out reliability issues in unattended runs discussion summary.

The core loop is simple: Claude drives emulators and simulators, navigates the app, captures screenshots, inspects the results, and files bugs when something looks wrong. In the writeup, the app is a Capacitor codebase spanning web, Android, and iOS, and the automated run covers 25 screens on a daily schedule.

The platform split is the main engineering detail. According to the author's post, Android was the easier path because the Capacitor WebView could be controlled through Chrome DevTools Protocol, which let Claude interact with the app much more like a browser target. iOS was harder because the same CDP-style path was unavailable, so the implementation had to lean on accessibility APIs and additional handling for native UI.

The strongest caveat is reliability under unattended execution. In the thread summary, one commenter highlighted "worktree discipline failure" as the interesting part of the experiment: when an agent runs on a schedule, mistakes surface later, not interactively. Another practitioner quoted in the discussion summary said Claude can still ignore instructions "explicitly in its memory" and then only apologize, which is a bad failure mode for hands-off QA.

The thread also pushed back on novelty. As the discussion summary notes, commenters pointed out that "WebdriverIO and Appium already exist" for this class of mobile automation and are already recommended in the Capacitor ecosystem. That leaves the writeup as a useful real-world template for layering an LLM on top of existing device-control surfaces, not evidence that classical mobile test tooling has been displaced.