Phone Harness is a lightweight system that lets AI coding agents interact directly with a real iPhone through macOS iPhone Mirroring. It requires no jailbreak, Xcode project, WebDriverAgent, or custom software installed on the phone. Screenshots of the mirrored window provide visual input, while Apple's Vision framework extracts visible text and tap-ready coordinates. macOS CGEvents supply taps, long presses, drags, scrolling, keyboard input, and iPhone Mirroring shortcuts. After performing an action, the agent captures the screen again to verify the actual resulting state. The harness can be installed as an agent skill for systems such as Claude Code or Codex. Its editable helper workspace also lets an agent create missing automation functions during execution.
Features
- Real iPhone control through iPhone Mirroring
- Vision-framework OCR with screen coordinates
- Automated taps, drags, scrolling, and typing
- Screenshot-based visual state verification
- Claude Code and Codex skill integration
- Agent-editable automation helper functions