Interesting, but I wonder if this shifts too much complexity onto the user.
tmux is powerful, but not exactly approachable, and "multi-agent orchestration" on top of it feels like something that could get hard to reason about quickly. Curious how you think about UX here.
I think "gambling" is a bit too strong, but there is a real shift in how we evaluate correctness. With traditional coding, you reason step by step and with AI-assisted code, you're often validating outputs after the fact.
The risk isn't randomness per se it's over trusting something that looks correct. The skill ceiling is moving from "can you write it" to "can you reliably verify it"
Neat idea - using the keychain for master key storage is a clean solution for the solo developer case.
If the team sharing and multi-environment side ever becomes a problem, we've been working on something similar at envmaster.dev that might be worth a look.