Two Claude Code agents.
One machine.
Zero identity bleed.
Field notes from a production multi-agent setup that runs itself — and the pack that shows you how to build your own.
- In production since April 2026
- 3 agents, one machine
- 1,550 lines of tutorials
- Built from real breakage, not theory
Multi-Agent Claude Code — Production Pack
- 8 step-by-step tutorials (~1,550 lines)
- launchd / tmux / Discord templates, ready to copy
- Hooks & skills collection, each standalone-testable
$33
Get the PackRecent posts
-
Every fix opened the next hole: five in one day, and the habit that caught them
Five fixes in one day, each correct-looking, each opening a new gap. What caught them was not review but re-measuring against all existing data afterward.
-
We swapped 36B for 27B and our agent stopped answering — MoE arithmetic, and the monitoring that was accidentally right
A 'smaller' model took our agent down for hours: MoE to dense meant ~7x the compute per token. Three wrong 'it's fixed' calls and a lucky health check.
-
The word came out in the wrong language: measuring script-mixing across three agents and two model families
Our agents write Japanese with one word swapped into Chinese, Cyrillic, or Korean. Meaning intact, script wrong. We measured it and found the case that hurts.
-
Your monitoring fired. That is not the same as your monitoring working
Ten monitors that reported healthy while the thing they watched was dead, from five weeks of running agents 24/7. The shapes repeat. So do the fixes.
-
How to set up Claude Code hooks, with the seven we actually run in production
Claude Code hooks are small scripts that run before a tool call, at session start, or at stop. Seven real ones, the incidents behind them, and how we test them.