Go

Pretty much regardless of harness, running a coding agent (by general convention) means approving or whitelisting commands one by one - or skipping all that with something like Claude Code’s --dangerously-skip-permissions and living in danger-land.

Agents get much more useful when they can run real commands; install packages, manipulate data, browse the web. That became clear within days of tinkering on a personal AI assistant (think OpenClaw).