From the terminal

Anthropic shipped a post in January 2026 that explains why your iOS agent setup feels broken. They didn’t mention iOS. They didn’t have to.

iOS development requires Apple’s CLI tools. xcodebuild compiles. simctl manages simulators. devicectl handles devices. Every build system for Apple platforms calls them eventually.

Apple ships xcrun simctl with Xcode. It works. It’s also a museum piece.

Running iOS tests from the command line shouldn’t require memorizing xcodebuild’s destination strings, SDK flags, and test filtering syntax. This post covers why xcodebuild test is hostile to automation and how FlowDeck replaces it with one command, structured NDJSON output, and live progress.

Claude Code or Codex can build your iOS app. They call xcodebuild, pass the scheme, pick a simulator, compile. On a good run, it works.

Every iOS developer who has tried Claude Code for testing hits the same wall. Claude can write XCTest cases. It can reason about your UI logic. But actually running your app, tapping through screens, and verifying what happens requires tools that Claude Code doesn’t have by default.

Every guide on using Claude Code or Codex for iOS development hits the same wall. The agent writes code. Now it needs to build, run, see errors, check the screen, read the logs. On the web, that loop is trivial. On iOS, it’s an archaeological dig through Apple’s fragmented CLI tools.