Claude Code /goal asks too many questions mid-run

Summary

Long-horizon agent tasks fail not from capability gaps but from model behavior: Claude Code breaks autonomy by asking for direction mid-task, forcing manual monitoring. Codex demonstrates that stubborn, delegation-averse execution actually scales better than orchestrated subagents.

Why it matters

Long-horizon agent tasks fail not from capability gaps but from model behavior: Claude Code breaks autonomy by asking for direction mid-task, forcing manual monitoring. Codex demonstrates that stubborn, delegation-averse execution actually scales better than orchestrated subagents.

Sources

1. 1.Claude Code added the feature in its May 12 2.1.139 release—straight to stable, not experimental
2. 2.Codex almost never calls subagents; it works inline unless I explicitly tell it to delegate
3. 3.Most importantly, it's stubborn. It almost never tells me a goal is unachievable
4. 4.it kept popping up to ask me to make choices. And the questions are usually on point. But under /goal, this is a bug, not a feature
5. 5.it proactively tells me it can't achieve the goal. Then it actually fails the goal. Sometimes after just a few dozen minutes
6. 6.After each compaction, Claude Code often seems to have forgotten everything that came before
7. 7.on April 16 they had added a 'reduce verbosity' instruction to the system prompt
8. 8.You can't fix that by tweaking a system prompt
9. 9.In extended continuous operation like /goal, this laziness gets amplified