Read by section.
57 chapters grouped by what you're trying to do. Pick a section, read in order, build the muscle.
Mental models. The temp-agency frame. Five tools, not fifty. The vault that makes any model durable.
- 01 AI as an Operating System
The Day I Killed My Tabs
- 02 The Five-Tool Stack
Five Tools, Not Fifty
- 03 Why Claude Forgets You
AI Is a Temp Agency, Not a Genius
- 04 Obsidian as Working Memory
The Vault — Where AI Becomes Useful
- 05 What a Skill Is
Recipes the Chef Reads Before Cooking
- 37 Context Files — CLAUDE.md, memory, skills
Where Conventions Live, Where They Die
- 44 Dreaming — Memory That Curates Itself
The Surfacer That Proposes, Never Writes
- 17 25 Operator Tips
Hard-Won Wisdom from Hour 200
Three doors (Chat / Cowork / Code), the swarm, the modes, sessions, the cheat sheet.
- 08 Chat, Cowork, or Claude Code?
Three Doors to Claude
- 06 Parallel Subagents and Fan-Out
The Swarm
- 13 Claude Code in 10 Minutes
The 10-Minute Quickstart
- 14 Slash Commands and Settings
The Cheat Sheet
- 16 Hooks and Custom Subagents
From Autocomplete to Coworker
- 21 Which Mode Right Now?
Interactive, Plan, Auto
- 22 Resume, Replay, Fork
Session Management
- 20 tmux, Worktrees, Named Sessions
Running Six Claudes at Once
- 57 Claude Code Mods
Six Built and Tested in 32 Minutes, and the Guard That Blocked Its Author
- 11 Build a Skill in 30 Minutes
How to Build a Skill, End to End
- 12 Connectors and MCP
Types, install paths, custom servers
- 37 Context Files — CLAUDE.md, memory, skills
Where Conventions Live, Where They Die
- 38 Run Until Done
Goals, Loops, and the Evaluator That Tells the Agent to Stop
- 44 Dreaming — Memory That Curates Itself
The Surfacer That Proposes, Never Writes
- 40 Prompting, or the Knob You Probably Shouldn't Tune
Why most prompt engineering content is wrong for operators
Don't get owned. Permissions. Sandboxes. The 11-minute leak. Real failures with receipts.
The wild stuff. Rick archetypes. Browser agents. Persona agents. Frameworks beyond Claude Code.
- 10 Hosted Agents, Local Models, Frontier
The Wild Stuff
- 32 Agent Archetypes (Rick Platform)
OpenClaw, NemoClaw, Hermes
- 33 Browser Agents with Playwright
Login, Click, Scrape, Post
- 34 Persona Agents and the Four NEVERs
Writing on Your Behalf Without Becoming a Bot
- 36 When Do I Outgrow Claude Code?
Beyond CC — CrewAI, LangGraph, SDK
- 35 Codex or Claude Code — or Both?
Day Shift, Night Shift
- 42 Codex on a Loop
The Second Opinion, Proof-Checked While You Sleep
- 43 Codex as Saviour
When a Second Prior Deletes 90,000 Lines and Hardens What's Left
- 27 Voice Agents — STT, LLM, TTS
Phone Number to Production
- 39 Skills You Should Steal
A tour of the 1M-skill ecosystem, the 73% that's broken, and the gaps an operator can fill
- 56 Read Before You Install
700 Ranked Repos, 118 Read From Source and Nine Installs
From Saturday idea to deployed URL. Six stages. Cron. Headless. Vibe coding. The bill, demystified.
- 31 Six Stages from Idea to Deploy
Ideation, Foundation, Creation, Polishing, Security, Deploy
- 07 Scheduled Tasks
Make AI Work While You Sleep
- 18 Headless Claude and CI
claude --print in Production
- 19 Shipping a Product in a Saturday
How to Build Products with AI
- 23 A Saturday Build, Hour by Hour
Vibe Coding, with the Misfires Kept In
- 25 Evals — Smoke, Regression, Golden
Evals or Hope, Pick One
- 29 Why Is My Bill So High?
Token Math, Caching, Batch, Routing
- 30 When to Drop CC for the SDK
Building with the Anthropic SDK Directly
- 41 Send the Link, Not the File
Every Deliverable as a Live Artifact
- 45 The App Store Without Swift
A Native iOS App, Real Recurring Revenue, and Not One Line of Swift I Wrote
- 46 Designing with AI
A Model Can Generate Any Interface in Seconds. It Still Can't Tell You Which One Is Right.
- 47 The Measurement Layer
When the AI Output Is the Product, a Three-Line Eval Isn't Enough
- 48 The Traffic Graph That Lies
Agentic SEO Done Right vs. the Vanity Version
- 52 What Agents Can't See
Two Review Rounds That Caught the Code, and a Menu Design Nobody Rendered
- 53 The First Real Caller
A Spelled Email, a Busy Signal and a Grader That Was Too Kind
Get twelve people to use this. Rate every tool without diplomatic phrasing.
- 26 How Do I Get My Team to Adopt?
Getting Twelve People to Use This
- 24 The Tier List
Every Tool Ranked Without Mercy
- 49 GPT-6 Astra for Real Work
Performance, Use Cases, and the Cost of a Finished Job
- 50 Claude Fable 5.1 for Difficult Workflows
Best-Fit Workflows, Fallbacks, and Real Costs
- 51 Jev and the System One Layer
Typed Questions, Calibrated Confidence, and the First Receipt From My Own Radar
- 54 Claude Opus 5.5 as the Default
The Effort Dial, Early Stops, and a Week of Receipts
- 55 Claude Sonnet 5.5 for Everyday Work
Same-Task Receipts Against Opus 5.5, and When the Cheaper Model Is Enough