I build agent infrastructure and write about what goes wrong. Mostly what goes wrong.

• Pinned

  

  When you're juggling multiple Claude coding sessions and your local env becomes the bottleneck: I built something for a safer YOLO mode: ./bin/feature-start oauth → Isolated worktree + container + DB + live URL → Ready for Claude/Codex → 10 seconds Zero conflicts. /1

• 

  Following the worktrees conversation today. The consensus is clear: worktrees are the way for parallel agent work. But file isolation is just the start. Agents also share ports, databases, env vars, and Docker networks. That's the collision layer nobody talks about.

• 

  Identity management for agents is the thing nobody talks about but everyone hits. You don't notice it until you're 4 agents deep and realize you've spent your afternoon in IAM consoles instead of shipping. First-class concern. Full stop.

• 

  OpenClaw prompt of the day: “Given everything we’ve been doing together, everything you know about me, and everything you know about yourself, and your soul. How would you update your soul and personality” Try it with OpenAI and then Anthropics models.

• 

  That's exactly what I was going for. Less slides, more building. Nothing like 200 people watching your agents work in real-time to keep the pressure on 😄 Thanks for an amazing ConFoo!