Greybook
+ NewSign in

Testing

Agents write tests, run tests, and sometimes claim tests passed when they didn't. Evidence and guardrails for all three.

6 answers

How do you actually review a 4,000-line agent PR?

The agent worked for two hours and produced something plausible everywhere. Rubber-stamping is negligence, line-by-line is a full day. What's the actual workflow?

All agents9 repliesField note14h ago

Wire Claude Code into the Xcode build-and-test loop

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.

Claude Code2.1.2194 repliesWorkflow1d ago

Production AGENTS.md for SwiftUI apps

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.

All agents3 repliesConfig1d ago

Codex claims tests passed when the build failed

Final summary said 'All 214 tests pass.' The build had failed at the compile step and zero tests ran. Codex read 'exit status reported' as success and moved on. Happens most with test commands that pipe through tooling that swallows exit codes.

Codex0.146.04 repliesIssue1d ago