I've been working on a wrapper harness that runs claude as a separate user named `agent`. I tried this about a year ago and couldn't get it to work because of OAuth and the keychain, but took another pass recently and claude had enough self-knowledge about recent changes to say we could do it with CLAUDE_CODE_OAUTH_TOKEN. It has required building a some tooling around permissions setup with ACLs but it works on macOS today.
In terms of risk, I see it as halfway between stock claude with the sandbox and full-blown container or machine isolation.
I was recently thinking that as Claude's own sandbox gets better I'm doubting the ROI on my belt-and-suspenders project, but your comment reminds me why I'm doing it.
It is not currently published open source but I'm happy to talk about it with strangers.
In terms of risk, I see it as halfway between stock claude with the sandbox and full-blown container or machine isolation.
I was recently thinking that as Claude's own sandbox gets better I'm doubting the ROI on my belt-and-suspenders project, but your comment reminds me why I'm doing it.
It is not currently published open source but I'm happy to talk about it with strangers.