{"slug": "a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github", "title": "A free book on operating AI coding tools (no signup, source on GitHub)", "summary": "Vlad Podoliako released a free, public book titled 'Vlad's Playbook: The Ultimate AI Dive Deep' with 47 chapters on operating AI coding tools, available on GitHub without signup. The book covers practical workflows, tool stacks, and agent architectures for operators, aiming to help users run AI as an operating system.", "body_md": "#\nVLAD'S\n\nPLAYBOOK\n\nThe Ultimate AI Dive Deep\n\nFor operators who want to stop juggling tabs and start running AI like an OS. 47 chapters. One operator. Belkins, Folderly, the Newsletter, and a portfolio of others.\n\nby Vlad Podoliako · Edition 10.7 · June 2026\n\n[New to AI? Start with Learn →](/learn)\n\n[Read the prologue first →](/how-to-read)\n\n[Build/share your tier list](/tier-list)\n\n[Day zero (operator path)](/day-zero)\n\n[The journey (reader path)](/journey)\n\n[Questions people ask me](/questions)\n\n## Forty-Six Chapters\n\nRead straight or jump where you need it. Each chapter stands alone.\n\n- 01 AI as an Operating System\nThe Day I Killed My Tabs\n\n- 02 The Five-Tool Stack\nFive Tools, Not Fifty\n\n- 03 Why Claude Forgets You\nAI Is a Temp Agency, Not a Genius\n\n- 04 Obsidian as Working Memory\nThe Vault — Where AI Becomes Useful\n\n- 05 What a Skill Is\nRecipes the Chef Reads Before Cooking\n\n- 06 Parallel Subagents and Fan-Out\nThe Swarm\n\n- 07 Scheduled Tasks\nMake AI Work While You Sleep\n\n- 08 Chat, Cowork, or Claude Code?\nThree Doors to Claude\n\n- 09 Blast Radius and Key Hygiene\nDon't Get Owned\n\n- 10 Hosted Agents, Local Models, Frontier\nThe Wild Stuff\n\n- 11 Build a Skill in 30 Minutes\nHow to Build a Skill, End to End\n\n- 12 Connectors and MCP\nTypes, install paths, custom servers\n\n- 13 Claude Code in 10 Minutes\nThe 10-Minute Quickstart\n\n- 14 Slash Commands and Settings\nThe Cheat Sheet\n\n- 15 When to Skip Permissions\nPermissions, Sandboxes, and Sharp Edges\n\n- 16 Hooks and Custom Subagents\nFrom Autocomplete to Coworker\n\n- 17 25 Operator Tips\nHard-Won Wisdom from Hour 200\n\n- 18 Headless Claude and CI\nclaude --print in Production\n\n- 19 Shipping a Product in a Saturday\nHow to Build Products with AI\n\n- 20 tmux, Worktrees, Named Sessions\nRunning Six Claudes at Once\n\n- 21 Which Mode Right Now?\nInteractive, Plan, Auto\n\n- 22 Resume, Replay, Fork\nSession Management\n\n- 23 A Saturday Build, Hour by Hour\nVibe Coding, with the Misfires Kept In\n\n- 24 The Tier List\nEvery Tool Ranked Without Mercy\n\n- 25 Evals — Smoke, Regression, Golden\nEvals or Hope, Pick One\n\n- 26 How Do I Get My Team to Adopt?\nGetting Twelve People to Use This\n\n- 27 Voice Agents — STT, LLM, TTS\nPhone Number to Production\n\n- 28 Six Failures, Six Bills\nThe Receipts I'd Rather Not Show You\n\n- 29 Why Is My Bill So High?\nToken Math, Caching, Batch, Routing\n\n- 30 When to Drop CC for the SDK\nBuilding with the Anthropic SDK Directly\n\n- 31 Six Stages from Idea to Deploy\nIdeation, Foundation, Creation, Polishing, Security, Deploy\n\n- 32 Agent Archetypes (Rick Platform)\nOpenClaw, NemoClaw, Hermes\n\n- 33 Browser Agents with Playwright\nLogin, Click, Scrape, Post\n\n- 34 Persona Agents and the Four NEVERs\nWriting on Your Behalf Without Becoming a Bot\n\n- 35 Codex or Claude Code — or Both?\nDay Shift, Night Shift\n\n- 36 When Do I Outgrow Claude Code?\nBeyond CC — CrewAI, LangGraph, SDK\n\n- 37 Context Files — CLAUDE.md, memory, skills\nWhere Conventions Live, Where They Die\n\n- 38 Run Until Done\nGoals, Loops, and the Evaluator That Tells the Agent to Stop\n\n- 39 Skills You Should Steal\nA tour of the 1M-skill ecosystem, the 73% that's broken, and the gaps an operator can fill\n\n- 40 Prompting, or the Knob You Probably Shouldn't Tune\nWhy most prompt engineering content is wrong for operators\n\n- 41 Send the Link, Not the File\nEvery Deliverable as a Live Artifact\n\n- 42 Codex on a Loop\nThe Second Opinion, Proof-Checked While You Sleep\n\n- 43 Codex as Saviour\nWhen a Second Prior Deletes 90,000 Lines and Hardens What's Left\n\n- 44 Dreaming — Memory That Curates Itself\nThe Surfacer That Proposes, Never Writes\n\n- 45 The App Store Without Swift\nA Native iOS App, Real Recurring Revenue, and Not One Line of Swift I Wrote\n\n- 46 Designing with AI\nA Model Can Generate Any Interface in Seconds. It Still Can't Tell You Which One Is Right.\n\n- 47 The Measurement Layer\nWhen the AI Output Is the Product, a Three-Line Eval Isn't Enough\n\n[ Now · Edition 10.7 · June 2026\nRead the launch ](/launch)\n\n**Vlad's Playbook is public.** 47 chapters, 3 live embedded case studies, the source is open and is the recipe.\n\n[New · Live · Updated hourly ](/radar)\n\n### Radar — what's moving in AI, ranked by lead time\n\nA self-updating index of what's travelling through the AI ecosystem, ranked by where it sits on the gradient — papers to repos to community to analysis. The receipts are on every row. See it before the crowd does.\n\n[New here? Start here ](/learn)\n\n### Learn the basics first\n\nNew to AI, Claude, Claude Code, or Cowork? The official free courses in the right order, a five-word primer, and the learning ladder — then the book.\n\n[New · Model file ](/fable-5)\n\n### Fable 5 — the withheld model, buyable\n\nAnthropic shipped the model it said it wouldn't — split in two. Pricing, the full benchmark table read honestly, the fallback architecture, and the June 22 clock.\n\n[Dynamic Workflows ](/dynamic-workflows)\n\n### Opus 4.8 — the swarm that runs itself\n\nClaude writes a script that plans, fans out hundreds of parallel subagents, and verifies its own work. What it is, the validator loop, how to turn it on, and when not to.\n\n[New · Showcase ](/good-taste)\n\n### Good taste, on tap\n\nStop your AI from generating generic slop. A before/after of Leon Lin's public taste-skill (45k★, credited) — and the moon-base and three-design receipts I built with the discipline.\n\n[Memory ](/dreaming)\n\n### Dreaming — the loop pointed inward\n\nA local, propose-only twin of Anthropic's Dreaming: it digests your sessions, surfaces candidate memories that each cite a verbatim quote, and re-verifies every one against the raw transcript — and never writes to memory itself.\n\n[New · Method ](/self-audit)\n\n### The Self-Audit\n\nThe swarm pointed at the agent's own setup. Five auditors, an adversarial red-team, 41 findings — including two refutations that would have broken the system if executed. Your config rots faster than your code.\n\n[New · Reference ](/claude-code-pricing)\n\n### What Claude Code actually costs\n\nEvery plan and API rate, verified — then the receipts: the real monthly bill, the $1,108→$4,312 cache mistake, and the three levers that cut it.\n\n[New · Comparison ](/claude-code-vs-codex)\n\n### Claude Code vs Codex\n\nRan both in anger. Verdict per job — including the night shift Codex actually wins.\n\n[New · Reference ](/claude-code-hooks)\n\n### Hooks that can't be talked out of\n\nTen real configs with verdicts — what each caught in production, and the three hook ideas that failed expensively.\n\n[New · Setup ](/claude-code-mcp)\n\n### Claude Code + MCP\n\nThe setup guide grounded in a real roster: the servers worth wiring, what each one costs and earns, and the ones that got cut.\n\n[New · Examples ](/ai-agent-examples)\n\n### 12 agents that actually ran\n\nA receipts gallery: the book swarm, the 4 AM watcher, the $0.40/min voice agent — every example with a cost and a failure on record.\n\n[Sovereign Stack ](/sovereign-stack)\n\n### Don't get deprecated\n\nOpen-weights LLMs that survive the deprecation calendar — Ollama, the hardware ladder, the heretic question, and the nano-gpt Saturday.\n\n[Method ](/html-first)\n\n### HTML-ization\n\nStop sending dead files. Every report, pitch, and audit ships as a live interactive artifact — two real ones embedded and clickable.\n\n[The launch ](/launch)\n\n### Edition 10.7 is public\n\nTypewriter hero, animated stat odometer, three live embedded artifacts, all 47 chapters as a click-anywhere mosaic, a post-credit scene.\n\n[Live diary ](/launch-week)\n\n### Launch week\n\nThe launch as its own experiment in the thesis. Four surfaces, seven days, receipts accruing — honest, even the embarrassing ones.\n\n[Resources ](/resources)\n\n### Vault library\n\nCLAUDE.md skeletons, .mcp.json examples, hook scripts, SKILL templates, the five reusable prompts. Copy, paste, ship.\n\n[Reference ](/cheat-sheet)\n\n### Cheat sheet\n\nSlash commands, settings, env vars, file paths, keyboard shortcuts. Print it. Tape it next to your monitor.\n\n[Vocabulary ](/glossary)\n\n### Glossary\n\nFifty-plus terms you'll need, grouped A–Z. Linked inline throughout the book. Hover any underlined term to read it.\n\n[Tier list ](/tier-list)\n\n### Rank without mercy\n\nDrag-and-drop your own tier list across AI tools, connectors, and infra. The live LMArena leaderboard for reference.\n\n[Orchestration ](/swarms)\n\n### Swarms\n\nMulti-agent orchestration — the four-pattern visualizer, ten swarm skills shipped, seven patterns I use, the orchestration prompts to steal. Three real multi-session screenshots.\n\n[GitHub ](/github-playbook)\n\n### GitHub for non-developers\n\nFive non-code uses, eight gh commands you actually need, what you can safely ignore. Six worked examples — Vlad's Playbook, AFC, Karpathy, Simon Willison ×2, profile READMEs.\n\n[The stack ](/showcase)\n\n### 66 skills · 32 agents · 12 plugins\n\nVlad's full Claude Code setup. Every skill folder, every custom subagent, every plugin — sanitized and shareable. Freshly pruned by the Self-Audit.\n\n[Research ](/research-notes)\n\n### What shifted this week\n\nExternal findings that move what an operator does Monday — model releases, deprecations, benchmark shifts. Dated, sourced, signal-not-receipt discipline.\n\n## More from the shelf\n\nDecisions, setups, and reference — the rest of the Playbook.\n\n[Decision ](/build-vs-buy)\n\n### Build vs Buy\n\nSequencing wedge, cost ladder, and a 5-question matrix for what to make vs buy.\n\n[The case ](/cfo-case)\n\n### For your CFO\n\n600 words to defend the spend — Claude as a labor line, not a SaaS line.\n\n[Rules ](/claude-md-rules)\n\n### The 12-rule CLAUDE.md\n\nKarpathy's template at 11% mistakes; the operator overlay gets it to 3%.\n\n[Setup ](/cowork-setup)\n\n### Cowork setup\n\nVlad's Cowork connectors and scheduled tasks — sanitized and cloneable.\n\n[Vault ](/vault-starter)\n\n### Vault starter\n\nPARA vs 7 other systems, project-as-entity, and a working vault to clone.\n\n[Recipes ](/weekend-builds)\n\n### Weekend builds\n\nEight Saturday-ship recipes — plus the one that's a trap.\n\n[Skills ](/starter-skills)\n\n### Starter skills\n\nSix drop-in SKILL.md files to paste into ~/.claude and run today.\n\n[Roadmap ](/thirty-day-plan)\n\n### 30-day plan\n\nA day-by-day roadmap from clean machine to operator in a month.\n\n[Index ](/sections)\n\n### Sections\n\nEvery chapter grouped by theme — the table of contents, by topic.\n\n[About ](/about)\n\n### About\n\nVlad, the portfolio, and the newsletter behind the Playbook.", "url": "https://wpnews.pro/news/a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github", "canonical_source": "https://dive.vladyslavpodoliako.com/", "published_at": "2026-06-19 20:52:12+00:00", "updated_at": "2026-06-19 21:08:06.066833+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-agents", "large-language-models", "generative-ai"], "entities": ["Vlad Podoliako", "Claude", "Anthropic", "Obsidian", "Playwright", "CrewAI", "LangGraph", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github", "markdown": "https://wpnews.pro/news/a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github.md", "text": "https://wpnews.pro/news/a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github.txt", "jsonld": "https://wpnews.pro/news/a-free-book-on-operating-ai-coding-tools-no-signup-source-on-github.jsonld"}}