Love that it follows you from terminal to terminal, super useful.
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]
Nice! I love Cal Newport. I've definitely found spinning up multiple Claude Code instances eats into your focus, and you can "lose yourself" quite quickly.
I find I use pomodoros more as nudges, and use the "beeps" to bring me back if I'm in the browser or something. but yeah... it's a trap for sure!
Opus is so slow these days what I really want is a bell sound to ring when it's done. I kick off some task and then it takes 3-12 minutes to complete. It's wrong, so I tell it to revert and try again with slightly different instructions.
Have you tried analysing all your prompts, and then telling it to "figure out" what custom skills might improve your prompts?
I do actually have another project I'm working on that does this... it's been super useful for seeing how I prompt, what Skills I use and getting them to evolve and improve (I know Hermes does some of this, but it's been interesting rolling my own - will release soon!!)
I ended up building a vs-code/IDE style workflow for claude that has a "file browser" of CC sessions in the left column, sorted by repo, and then terminal in the right column, and then I've been tacking features like this onto it
Me too. Also it’s good to get decent reports that can be used for other things. For example the logs help me fill in my time sheets. Also it forces me to take breaks
Fantastic. I think these small productivity tools embedded in harnesses is pretty powerful.
I especially like that you can get the AI to use it and also just pop into the CLI.
Also nice to generate useful web dashboards etc
I recently had a nasty accident too and snapped my collar bone, broken tibia, and 6 broken ribs, so I can absolutely relate. Claude Code was there for me in a big way as well :-)
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!
Thanks for sharing. I was stuck in a Greek hospital for 8 days with 2 fractured vertebrae, before I could get home.
It’s easy to get into a spiral, but putting your mind to build something really helps.
I do hope your ribs and collar bone is getting better?
I’ve been lucky, as it will heal but could have been really bad. Phew!
Mmm apols. You’d think I’d have learned my lesson by now, but it’s just so seductive to have it write for you.
I got burned with this very HN post for doing just that, but they kindly let me rewrite it.
Will tweak it. Thanks for the feedback!
From the title I thought it’d be a timer for the agent itself, so it doesn’t waste time on endless thinking loops, etc.
Oh that’s an idea? Could use hooks or something?
Love that it follows you from terminal to terminal, super useful.
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/#...
Nice! I love Cal Newport. I've definitely found spinning up multiple Claude Code instances eats into your focus, and you can "lose yourself" quite quickly. I find I use pomodoros more as nudges, and use the "beeps" to bring me back if I'm in the browser or something. but yeah... it's a trap for sure!
Also for tmux (which I always run claude inside)
https://github.com/olimorris/tmux-pomodoro-plus
Ooo that's cool thank you. That's really useful! My other CLI project was: https://github.com/emson/pymodoro
Opus is so slow these days what I really want is a bell sound to ring when it's done. I kick off some task and then it takes 3-12 minutes to complete. It's wrong, so I tell it to revert and try again with slightly different instructions.
You can use edit your settings.json in ~/.claude and put a hook for it like this:
That hook is also called when subagents stop which means you'll get a lot of false positives.
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 does those checks before emitting a macOS notification and then called it in each hook. Something like this:
Maybe someone has found a better solution.Have you tried analysing all your prompts, and then telling it to "figure out" what custom skills might improve your prompts? I do actually have another project I'm working on that does this... it's been super useful for seeing how I prompt, what Skills I use and getting them to evolve and improve (I know Hermes does some of this, but it's been interesting rolling my own - will release soon!!)
Cmux notifications does this too
Try superset, it does that
I like this. Small tools inside the workflow feel much more useful than separate productivity apps I have to remember to open.
I ended up building a vs-code/IDE style workflow for claude that has a "file browser" of CC sessions in the left column, sorted by repo, and then terminal in the right column, and then I've been tacking features like this onto it
Fantastic! You should open source it
Me too. Also it’s good to get decent reports that can be used for other things. For example the logs help me fill in my time sheets. Also it forces me to take breaks
Great idea! I just created one for Pi
https://github.com/mkaz/pi-modoro
Fantastic. I think these small productivity tools embedded in harnesses is pretty powerful. I especially like that you can get the AI to use it and also just pop into the CLI. Also nice to generate useful web dashboards etc
I recently had a nasty accident too and snapped my collar bone, broken tibia, and 6 broken ribs, so I can absolutely relate. Claude Code was there for me in a big way as well :-)
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!
Thanks for sharing. I was stuck in a Greek hospital for 8 days with 2 fractured vertebrae, before I could get home. It’s easy to get into a spiral, but putting your mind to build something really helps. I do hope your ribs and collar bone is getting better? I’ve been lucky, as it will heal but could have been really bad. Phew!
Great idea and I’ll definitely try it but all those flags needed to run the startup command scare me lol
It has sensible defaults just do /pomo start
It’s only if you want to customise it. Also CC will do it for you. It’s very agent friendly
Side note, many windows people still don't know about psmux https://github.com/psmux/psmux
Ah nice thanks. Love tmux, incidentally I came across this the other day as an alternative to Ghostty: https://supacode.sh/
tool is great by your readme is pure unreadable ai slop - try to naturalise it a bit
Mmm apols. You’d think I’d have learned my lesson by now, but it’s just so seductive to have it write for you. I got burned with this very HN post for doing just that, but they kindly let me rewrite it. Will tweak it. Thanks for the feedback!