Nice idea. Using git worktrees for parallel agents is interesting, but I’ve found that coordination and debugging become the hard part pretty quickly. Curious how you’re handling visibility into what each agent is doing and why something went wrong.

Totally agreed, and that's exactly why I built harness! If you use just raw worktrees you can get lost super quickly because there's just things happening all over the place

Harness solves this by putting the status of the agent front and center (or rather on the left vertical tab bar). Each worktree is a tab, the icon shows you if the agent is working (green means working, yellow means waiting on you, red means waiting on a permission prompt). The goal is that all work for a worktree is in one mental space, so you can easily review the agent's work (reviews built in, integrated browsers sorted by worktree, etc)