[tstrimple]

Yes. I have four devices fully managed by Claude Code at this point. My NAS and Desktop running NixOS. My MBP with nix-darwin and an M2 MBA with a dead screen that I've turned into a headless server also using nix-darwin. I've got a common flake theme and modularized setup. I've got health checks (all written by CC) coming in from all of them aggregated by another script (written by CC) which will send me alerts over various pipelines including to my Matrix server (setup and maintained by CC). I can do things like ask CC to setup radarr and make it available on my internal network and it knows where and how I host containers. It can even look at other *arr tools and pull usenet details from them to use in radarr. What my NAS is for. How to add a service in a "standards" compliant way for my setup. I can ask it to make a service available on the internet and it will configure a cloudflared tunnel exposing it. Including knowing when to make changes on my local dnsmasq instances or the Cloud Flare global DNS for external access.

I think the difference is that all of my scheduled tasks and alerting capabilities are all just normal scripts. They don't depend on CC to exist. CC could disappear tomorrow and all of my setup and config would still be valid and useful and continue to work. CC isn't a critical path for any normal operations of the system. I have explicitly instructed CC to create and use these scripts so it's not something you get "for free" but something you can architect towards. If I wanted to look at a companies job postings each day and provide alerts to me, I'd have CC build a script to scrape and process results and schedule it. At that point CC is outside of the loop and I have a repeatable pattern to use until the website changes significantly enough to justify updating it. But I could ask that CC context to stop the job search service months later and it would know or be able to find what I'm referring to.

I'm open to using more autonomous tools like OpenClaw, but I'm very resistant to building them into critical workflows. I'd happily work with their output, but I don't want them to be a core part of the normal input/output operations of the day to day running of my systems. My using AI to make changes to my system is fine. My system needing AI to run day to day is not.

[BeetleB]

I've heard people do similar stuff in CC. Do you know of any writeups on some of this (CC or OpenCode)?