Blog

Notes on running Claude Code, Codex and other coding agents. The posts cover agent orchestration, handoffs, review loops and usage limits.

  1. Claude Code and Codex on Windows: native, WSL or Git Bash

    Install Claude Code and Codex on Windows, natively in PowerShell or in WSL 2: the commands, when Git Bash matters, sandboxing, updates and uninstalls.

  2. Claude Code agent teams: how to set them up and when to use them

    Claude Code agent teams, step by step: turn them on, start a team, give each teammate a pane, and when subagents or a team across vendors fit better.

  3. Why I built a canvas to see all my Claude Code agents at a glance

    Running several Claude Code and Codex agents turned my job into checking on them. Why I built a canvas where every agent's state reads at a glance.

  4. Claude Code plan mode: how to use it and when to skip it

    Claude Code plan mode, step by step: how to turn it on, why Claude enters it by itself, approving or editing the plan, opusplan, and when to skip it.

  5. The best terminal for Claude Code on Mac and Windows

    The best terminal for Claude Code on a Mac or a Windows PC, compared on Shift+Enter, notifications and split panes: Ghostty, iTerm2, Windows Terminal, VS Code.

  6. Claude Code notifications: know when it finishes or needs you

    Claude Code notifications on a Mac: what each terminal does by default, a sound when Claude finishes, hooks for approval prompts, and Codex alerts too.

  7. How to run Claude Code in tmux on a Mac

    Claude Code tmux setup for a Mac: the config lines it needs, mouse scrolling, notifications, agent team panes, and when claude --bg replaces tmux.

  8. Excalidraw MCP: draw diagrams from Claude Code and Codex

    Excalidraw MCP servers compared: the official app, the live canvas server with Claude Code and Codex install commands, and diagrams built into Starkomand.

  9. Port 3000 already in use on Mac? How to find and kill the process

    Kill port 3000 on a Mac: find what holds it with lsof, stop it safely, and free any other port. Plus how to stop dev servers your AI agents left running.

  10. What to do when Claude Code hits its usage limit

    Claude Code usage limit reached mid-task? Continue in Codex: it opens on the same files with Claude's edits in place, plus the recorded conversation.

  11. How to run Claude Code and Codex side by side on a Mac

    Run Claude Code and Codex side by side on a Mac without edit collisions: split the roles, isolate writers in Git worktrees, and see who finished.

  12. Claude Code voice mode and on-device Parakeet dictation

    How Claude Code voice mode works, and how to dictate to Claude Code and Codex by name with NVIDIA Parakeet on your Mac or OpenAI dictation.

  13. Hand off a task from Claude Code to Codex without losing the plan

    How to hand off a task from Claude Code to Codex: plan a CSV export, then pass the objective, acceptance criteria and brief to Codex in Starkomand.

  14. How to keep track of multiple AI coding agent sessions

    Back from a break with agents still running? Keep track of multiple AI coding agent sessions with window states, spoken notices and live window backs.

  15. Have a second AI agent review code changes: a search race fix

    Have a second AI agent review code changes: hand a Claude Code fix to a Codex reviewer with a factual brief, then make the final call yourself.

  16. Why I put AI coding agents on an infinite canvas

    An infinite canvas for AI coding agents keeps the issue, diagram, preview and reviewer beside the terminal. Why I built Starkomand that way.