Credentials. The agent works inside your logged-in iPhone apps, so it can see and use saved accounts and payment details on the phone.
Who it is forAn iPhone owner with a Mac who wants an agent to finish a repetitive app task, such as booking a ride or placing a food order, while they stay at the desk.
The problemDoing a multi-screen app errand by hand takes attention for each tap and every confirmation screen.
The outcomeThe agent completes the errand in the iPhone app and reports the confirmed details from the final screen.
What you need first
- uv installed, with Python 3.12 available
- A coding agent such as Claude Code or Codex
- Either a Mac with iPhone Mirroring, an Android phone with adb and developer options on, or a Phone Harness Cloud account
- Your own hands to pair the phone, grant Accessibility and Screen Recording, or approve adb
Steps
- Install Phone Harness with uv using Python 3.12, for example
uv tool install phone-harness. (inferred, check the README) - Pair iPhone Mirroring on the Mac and grant Accessibility and Screen Recording, as the setup prompt in the README describes.
- Run
phone-harness skilland thenphone-harness doctorto confirm the mirrored phone is found. - Ask the agent to find the app and step through the errand, keeping the iPhone unlocked because unlocking pauses mirroring.
- Review the confirmation screen the agent reports before any final payment step.
Prompt for your agent
Using the phone-harness repo at https://github.com/ShawnPana/phone-harness, use the iPhone Mirroring window on this Mac to complete the errand <errand description>. Stop before the final payment confirmation and report the screen text, then verify the order details match the request before approving the last step.
Caveat. Unlocking the iPhone pauses mirroring, so the phone must stay unlocked while the agent works.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page