Free playbooks in your inbox
Hands-on tutorials for people who want to build with AI.
Cover of Ship While You Sleep
From the youcanbuildthings catalog · ▸ Build-tested

Ship While You Sleep

5 Claude Code Agents in 30 Days

eBook: $12.99 252 pages

You left five agents running overnight. One failed silently. One retried 47 times and burned $50. You shipped nothing. In 30 days you turn one babysat agent into a fleet of five that survives a hard kill, refuses a collision, and hands you finished work by morning.

Twenty-eight books on this shelf teach you to configure one agent inside one session. Not one of them survives process death. None ship a schema. None get you a second agent working safely.

The finished fleet package ships as a free companion repo: a runnable drill for all twelve chapters, and one command that kills a live agent and resumes it. No key, no account, no install.

What You'll Build

01
Agent C Retried 47 Times and Burned $50

The three failures that kill every overnight run: silent failure, retry storms, and collisions.

02
The Half of the Harness Nobody Builds

Configuring one agent is the easy half. The operational half is what survives process death.

03
Your Agents Need a Database, Not More Markdown

Build agent.db with three contracts: control state, an append-only event ledger, derived knowledge with provenance.

04
Kill It Mid-Run and Watch It Come Back

A resumable session wrapper. Kill it at step 4 of 6, restart, and it finishes at step 5 without redoing a thing.

05
Receipts, Not Retries

An idempotent execution layer so the third retry never repeats the side effect.

06
Two Agents, One Repo

A claim registry with leases. Two agents work the same repo all night and never touch the same file.

07
The Scheduler: Five Agents, One Work Queue

Five agents pull from one shared queue, with heartbeats and a dead-letter queue you can inspect.

08
Where Did It Actually Break?

Trace the failure to the exact step instead of reading 400 lines of log at 8 a.m.

09
The Cost Governor: Stop the $50 Burn

A hard budget ceiling plus a routing split that buys more parallel agents from the same monthly spend.

10
Proof on Paper: Replay, Eval, and Numbers You Can Defend

A replay-driven regression suite seeded from your own production failures.

11
Where This Breaks at 3 A.M.

The honest chapter. What still fails, and the guardrail that catches it before you do.

12
Leave It Running

The 30-day operating plan: close the laptop, read the trace in the morning.