Though, if you're following Cal Newport-ian rules, watching over multiple agents doing their work is no longer a 25 minute "deep work" Pomodoro, and god knows Newport has been complaining about it [1]
[1]: https://calnewport.com/avoiding-digital-productivity-traps/#...
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "afplay ~/.claude/hooks/chime.wav",
"async": true
},Ideally you are only notified when the main agent stops, the main agent has a question, or a subagent has a question.
I created a script that figures out if any of those states apply before emitting a macOS notification and then called it in each hook:
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "script.sh",
"timeout": 10
}
]
}
],
"PreToolUse": ...
"PermissionRequest": ...
"Elicitation": ...It's a long road to recovery. I'm 5 months in and still in a lot of pain, but it does (slowly) get better. Hope you're spirits stay up!
It’s only if you want to customise it. Also CC will do it for you. It’s very agent friendly