@lawrencecchenGitHub ↗

Lawrence Chen

A superrepo-style cmux workflow for coordinating isolated AI coding tasks, parallel agents and review through Cmd+Shift+U.

How this setup has evolved

Version 1 · Latest

Initial setup: superrepo coordination, isolated worktrees and Cmd+Shift+U review loop.

Lawrence Chen's AI setup

What I build

I work on cmux, a Ghostty-based macOS terminal built for running multiple AI coding agents side by side. I use a superrepo-style control repository above the source repositories to coordinate task topology, worktrees, skills, build rules, releases and verification.

Agents & harnesses

  • Codex (current): Primary coding agent for focused tasks in isolated worktrees.
  • Claude Code (current): Parallel coding agent in cmux workspaces; teammate mode can map to native cmux panes when useful.
  • Built-in subagents (occasional): Bounded research or implementation delegation; no custom external harness.
  • cmux (current): One task per workspace, with Cmd+Shift+U jumping to the newest unread agent notification for review.

Apps & terminal

  • cmux (current): Terminal tabs, splits, browser panes, notifications and CLI/socket control.
  • zsh (current): Default shell for scripts and development commands.
  • GitHub (current): Source, issues, pull requests, checks and release coordination.
  • Browser automation (current): Isolated browser sessions for web research and UI verification.
  • Docker (available): Ephemeral container isolation for untrusted or network-facing inspection.

Machines & isolation

  • Mac workstation (current): Runs cmux, agents and local review.
  • Isolated worktrees (current): One worktree per change; shared primary checkouts remain untouched.
  • Remote build and test machines (current): Builds and verification can run on isolated remote Macs or VMs when needed.
  • Tagged dev instances (current): Unique app tags and sockets keep concurrent sessions separate.

Skills & instructions

  • Repository instructions (current): Define worktree ownership, focused tests, builds, dogfood, release gates and secret handling.
  • Reusable agent skills (current): cmux, Swift, browser, release, verification, performance, security and infrastructure workflows are selected per task.
  • cmux primitives (current): I prefer composable terminals, browsers, notifications, workspaces, splits, tabs and CLI/socket automation over a fixed orchestration product.

How I work

  1. Start one task per cmux workspace and give the agent a focused brief.
  2. Let the agent read the relevant instructions, choose the needed topology and create isolated worktree(s).
  3. Start setup and build work early, then implement with focused tests and checks.
  4. Press Cmd+Shift+U to jump through finished-agent notifications, review the diff, build, artifact or bug fix, and reply to unblock the agent.
  5. When the notification queue is clear, create another workspace and start the next task.
  6. Exercise the advertised path through the tagged app’s CLI/socket entrypoint and capture UI evidence before handoff.
  7. Dogfood the tagged build, address concrete review or CI failures, and merge only after required checks and approval.
  8. Keep secrets, credentials, private endpoints, raw configuration, private project details and device identifiers out of shared content.