Ran Vibe Kanban on a side repo over the weekend it’s slick, but I tripped on one thing: all the agents write into the same checkout, so parallel cards can clobber each other when they touch the same files. I’ve been spinning up a quick `git worktree` per card as a stop gap.

Outside of that, really enjoying the flow.

BTW, if anyone’s juggling multiple agents and wants a “quarantine” layer before changes hit Git, I’m hacking on SAV (Shadow VCS)open source, risk scores every commit and keeps them sandboxed until you approve. Happy to swap notes. https://github.com/AKIFQ/sav

How is the isolation layer of a shadow vcs different/better than just checking into a feature branch and not pushing?

Not saying there isn't value in the risk assessment part, but, I'm asking specifically about the change isolation.

Are you sure you're using vibe-kanban? The project spins up a worktree for each task attempt specifically to solve this problem.

In software we already let Copilot rough-draft code, run tests, then keep or toss the changes. We can do the same with hardware:

– keep the AI traces in a separate layer or revision – run basic checks for clearance and width – eyeball the diff, accept what looks right, fix the rest

The tricky part is psychological: once you charge, you implicitly promise consumer-grade polish. If the address-bar jitters after an update, people will cancel faster than they would stop donating.

Human readability isn’t going away. Most teams still debug by eyeball, so the baseline must stay “another human can scan this at 2 a.m."