Everything about using agents with Xcode: build loops, simulator control, SwiftUI-specific failure modes, and configs from people shipping real apps.
Claude Code can't see Xcode's build errors unless you hand them over. XcodeBuild MCP plus a formatter that strips the noise gives the agent a real edit-build-test loop for SwiftUI work — the difference between guessing and iterating.
The AGENTS.md running my shipping iOS app. Simulator names, the exact xcodebuild invocations, SwiftUI conventions the agent kept violating until they were written down, and a definition of done that includes a green test run.
Show me what actually works. Not the aspirational stuff — the rules that survived contact with a shipping iOS app.
Agent converts @StateObject to @State (or reorders wrapped properties) as part of an 'observability migration' and every preview in the file dies with 'Compiling failed: cannot preview in this file' or a XCPreviewAgent crash. Builds fine, runs fine on device — only previews break.
iOS is the acid test: Xcode builds, simulators, and API churn. With XcodeBuild MCP wired up, Claude Code pulls clearly ahead; without it, both are guessing.
Eight days migrating a legacy widget suite to WidgetKit with Claude Code and XcodeBuild MCP: timeline budgets, a haunted pbxproj, and $84 of tokens.