Update to Autonom

{
  "description": "Build, launch, attach to, inspect, and debug Flutter applications on explicit devices using Flutter machine output, Dart VM service evidence, adb, screenshots, logs, and repeatable user flows.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 220
    }
  ],
  "name": "flutter-debugger-agent",
  "skill_md_contents": "---\nname: flutter-debugger-agent\ndescription: Build, launch, attach to, inspect, and debug Flutter applications on explicit devices using Flutter machine output, Dart VM service evidence, adb, screenshots, logs, and repeatable user flows.\n---\n\n# Flutter Debugger Agent\n\nDebug a Flutter app on one explicit device with machine-readable Flutter output\nplus Android evidence when needed.\n\n## Resolve the tool chain\n\n```bash\npython3 <marketplace-root>/scripts/flutter_exec.py --root . -- --version\npython3 <marketplace-root>/scripts/flutter_exec.py --root . -- devices\n```\n\nNever silently fall back to a system Flutter when the repo is FVM-pinned.\n\n## Run / attach\n\n```bash\npython3 <marketplace-root>/scripts/flutter_exec.py --root . -- \\\n  run -d <device-id> --target <target> --machine\n```\n\nCapture VM service URI from machine events when you need DevTools or custom\ninspectors. Prefer Autonom session + `ui` / `screenshot` / `logs` once the app\nis up.\n\n## Evidence ladder\n\n1. Reproduce on a single pinned device/mode.\n2. Screenshot + accessibility / UI tree (Autonom or adb).\n3. Dart logs / VM service errors.\n4. `adb logcat` filtered to the app process for platform issues.\n5. After a patch, replay the same flow end-to-end.\n\n## Rules\n\n- One device id on every command when multiple are present.\n- Debug mode is fine for functional bugs; profile mode for performance claims.\n- Do not treat a green build as a green UX path — observe the screen.\n"
}