Skills
Claude Code /goal Command: Define Completion Conditions and Let the Agent Work Autonomously Across Turns Until They Hold
The /goal command introduces outcome-based autonomy: instead of turn-by-turn prompting, define a success condition ('all tests pass', 'coverage above 80%') and Claude keeps working across turns until that condition holds. This shifts the developer role from directing each step to defining acceptance criteria, matching the 'goal-based agentic coding' pattern Google previewed at I/O.
Source
↳ Follow the thread