stop-hook-needs-agent-stop-intent-guard
The stop hook script must detect whether the agent actually called stop() versus merely pausing for user input. A guard condition checking for explicit stop intent (e.g., presence of a stop tool call in the transcript or a sentinel phrase) would prevent the false-positive loop. Without this guard, any waiting state in a multi-turn skill like superpowers:brainstorming triggers repeated hook evaluations for every idle cycle.
Related
- stop-hook-infinite-loop-when-brainstorming-awaits-user-input
- 2026-04-04-oracle-001-self-architecture-analysis
- stop-hook-brainstorming-infinite-loop-pattern
- stop-hook-brainstorm-workflow-infinite-block-pattern
- stop-hook-blocks-on-brainstorming-mid-flow
- stop-hook-must-guard-against-non-termination-stop-events
- stop-hook-fires-on-every-agent-turn-not-just-session-end
- stop-hook-needs-agent-stop-intent-detection-not-response-len
- stop-hook-fires-on-agent-wait-state-not-just-stop
- stop-hook-fires-false-positives-during-waiting-states