His setup is, in his own words, "surprisingly vanilla."
...
Boris runs 5 Claude Code instances in his terminal simultaneously, each in its own git checkout. He numbers his tabs 1-5 and uses iTerm2 system notifications so he knows when any session needs input.
He also runs 5-10 more sessions on claude.ai/code in the browser, hands work between local and web sessions using the
&command or--teleportflag, and kicks off sessions from his phone via the Claude iOS app.
I'm not sure I'd call that workflow vanilla.
I do however appreciate efforts and workflows to reduce errors and logical faults in the output.