stop-hook-fires-on-idle-wait-not-just-stop-calls
The Stop hook fires repeatedly during active waiting states (when Claude is awaiting user input), not only when the agent explicitly calls stop(). This creates a feedback spam loop where the hook re-injects instructions into the conversation on every idle tick. The hook condition should check whether actual agent termination was initiated, not just evaluate on any pause state.
Related
- stop-hook-false-positive-during-agent-wait-states
- stop-hook-fires-on-idle-agent-not-just-stop-calls
- stop-hook-false-positive-loop-on-waiting-state
- stop-hook-false-positive-during-waiting-state
- stop-hook-false-positive-during-active-waiting-state
- stop-hook-fires-during-active-waiting-state-false-positive-l
stop-hook-fires-on-idle-wait-states-not-just-stop