The blue pill · knowledge base
AI & Claude Code Guides
Plain-language explainers, Claude Code walkthroughs, agent deep-dives and real case studies. Built to scale to thousands — and to actually be understood.
Start with these
Claude Code Scheduled Tasks: Put Your AI on a Timer
Claude Code scheduled tasks made simple: /loop in a session, Desktop routines and cloud schedules — set up your AI alarm clock in five minutes flat.
Best Claude Model for Coding in 2026: How to Pick
Which is the best Claude model for coding? Opus, Sonnet, Haiku and opusplan explained like a gearbox — plus the /model command to switch in seconds.
Claude Code Hit a Limit? Auto-Continue Picks Up the Thread
Claude Code now waits for your usage limit to reset and resumes exactly where it stopped — automatically. How it works, and how to turn it on or off.
Mythos 5.1: What the Model Is and How to Request Access
Fable 5.1 is open to everyone, Mythos 5.1 is application-only. What differs, how to apply, and why most people don't need it.
Claude Code Fast Mode: What /fast Really Costs
Claude Code fast mode makes Opus up to 2.5x faster — for a price. How the /fast command works, what it costs, and when the speed is worth paying for.
Claude Code Dynamic Workflows: One Prompt, Dozens of Agents
Trigger a Claude Code dynamic workflow with one sentence. Dozens of agents tackle the task in parallel — you get one cited, verified answer when they're done.
Claude Code Auto Mode: What It Allows and How to Configure It
Auto mode is now the default on Pro, Max, and Team — a background classifier reviews Claude's actions. Here's what it allows, blocks, and how to configure it.
Claude Code Subagents: Your AI Team, Explained Simply
Claude Code subagents explained for non-programmers: a team of AI helpers, each with its own memory. Create your first one in 5 minutes just by asking Claude.
Claude Code Output Styles: Give Claude a Personality
Claude Code output styles rewrite the system prompt to change Claude's role and tone. Built-in styles, the /config switch, and a custom style in minutes.
Draw First, Build Later: /design in Claude Code
The /design skill generates editable UI artboards inside Claude Code. Pick one artboard, tweak it in chat, and Claude builds it. No Figma, no mockup tools needed.
Claude Code From Your Phone: Remote Control Done Right
How to run Claude Code from your phone with Remote Control: start /rc on your computer, open the Code tab in the Claude app, and steer work from anywhere.
How to Resume a Claude Code Session: --continue vs --resume
How to resume a Claude Code session: claude --continue for the last chat, --resume and the session picker for older ones, naming, forks, and session IDs.
Claude Code Sessions Now Message Each Other
Two Claude Code terminals can now exchange notes without you copy-pasting between them. Here's what cross-session messaging actually does and when to use it.
Claude Code Advisor: a Second Opinion for Your AI
What the Claude Code advisor does, how to enable it with /advisor, which model pairings work, what it costs, and when a second opinion pays off.
Claude Code Dangerously Skip Permissions: a Sane Guide
What claude code dangerously skip permissions really does, all six permission modes, how to set a default, and the safer alternatives I actually use.
Claude Code Ultraplan and Ultrareview: Cloud Power Tools
Claude Code ultraplan and ultrareview explained: plan big changes in the cloud, review them in your browser, then catch bugs with a multi-agent review.
Claude Code: Build Live Dashboards With MCP Artifacts
Claude Code artifacts pull live MCP data on every view — a dashboard you build once shows current data forever. Here's how to set one up in five minutes.
Claude Code on Your Phone: iOS & Android
Use the Claude app for iOS or Android to start cloud sessions, steer your computer remotely, or dispatch tasks — no extra app needed, it's all in the Code tab.
Claude Code Artifacts: Share Live Pages from Sessions
Claude Code artifacts turn session output into a live, shareable web page at a private URL — updated in real time as Claude keeps working. Here's how they work.
Claude Desktop Browser Pane: What It Can Do
Claude Desktop now has a built-in browser: open docs, click through pages, and read any site right next to your project — no Chrome extension needed.
Claude Code Browser Control: Chrome Extension Setup
Claude Code browser control setup, step by step: install the Chrome extension, run claude --chrome, and let AI test pages, read errors and fill forms.
Claude Code Desktop App: a Tour for Non-Programmers
The Claude Code desktop app brings parallel sessions, visual diffs and live app preview to macOS and Windows — no terminal needed. Install guide and tour.
Claude Code Safe Mode: Fix a Broken Config Fast
claude --safe-mode launches with zero customizations active. If the problem vanishes, you know exactly which surface broke it — and this guide walks you through the fix.
Claude Code Slash Commands: 10 Hidden Gems for Beginners
The 10 Claude Code slash commands I actually use every day — /rewind, /compact, /btw and friends — explained for non-programmers, with zero jargon.
Claude Code Overloaded? Set a Fallback Model
Tired of '529 Overloaded' halting Claude Code mid-task? Set a fallback model once and it auto-switches to a backup whenever your main model is too busy.
How to Run Many AI Agents at Once with Claude Code
A power move most beginners miss: ask Claude Code to run several agents at once — to split a job, attack it in parallel, or have them challenge each other.
Can AI Agents Check Each Other's Work? Multi-Agent Setup
The single trick that raises AI quality most: don't trust one answer. Have a second agent challenge it, try to break it, and surface what the first one missed.
What Are AI Agents, and Why Is Everyone Talking About Them?
What are AI agents, and why is the news suddenly full of them? Cutting through the hype cycle to the one part that changes your next month of work.
AI Automation Case Study: 11 Hours/Week Saved in a Weekend
An AI automation case study, start to finish: how a non-technical operations lead replaced a manual reporting grind with an agent in a single weekend.
What Is an AI Agent? Agents vs Chatbots, Explained
What is an AI agent, and how is it different from a chatbot? One talks, one acts — and that single word, acts, is the whole revolution, explained simply.
How to Write an AI Prompt: Stop Asking Tiny Questions
How to write an AI prompt that does the whole job: stop feeding the AI coins like a vending machine, and hand it complete projects with rich context.
What Is an AI Hallucination (and Why AI Confidently Lies)
What is an AI hallucination, why does AI confidently make things up, and the 3-second habit that protects you. It's not a bug to fear — manage it.
How Do LLMs Work? Explained Without a Single Equation
How do LLMs work? Tokens, context windows, and next-chunk prediction — the three ideas that explain everything AI does, with zero math required.
ChatGPT vs Claude: Which Is Better in 2026 (and for What)
ChatGPT vs Claude: which is better in 2026? Wrong question — here's the right one, plus a field guide to picking the right model for each kind of task.
What Is an MCP Server? Explained With a Power Outlet
What is an MCP server, in plain English: the standard plug that lets AI agents connect to your real tools and data — with no custom wiring required.
How to Prompt Claude Code to Build a Real App
How to prompt Claude Code so it ships a finished app instead of fragments: a five-part template, plus the one line that unlocks long autonomous runs.
What Is Claude Code? (Explained for Non-Coders)
What is Claude Code, in plain English: an AI agent that reads, writes, and runs code on your computer. If ChatGPT is an advisor, this is a contractor.
Claude Code VS Code Extension: Install and First Steps
How to install the Claude Code VS Code extension and use it well: inline diffs, @-mentions, plan mode and checkpoints — right inside your editor, in minutes.
Claude Code Voice Dictation: Talk Instead of Typing
How to set up Claude Code voice dictation in two minutes: the /voice command, hold vs tap mode, 20 supported languages, and why it costs zero tokens.
Claude Code Not Working? A Checklist for Non-Coders
Claude Code not working? Walk this symptom-to-fix checklist: stuck sessions, login errors, limits, slow search — with the exact command for each case.
Claude Code Terminal Setup: Make the CLI Feel Like Home
Claude Code terminal setup explained: what /terminal-setup actually does, fixing Shift+Enter, notifications, themes, a status line and custom keybindings.
Is Claude Code Safe? An Honest Answer for Non-Coders
Is Claude Code safe to run on your computer? What it can touch, what your data does, how the sandbox works, and the real risks — explained without panic.
Claude Code Rewind: Checkpoints as Your Time Machine
How the claude code rewind checkpoint system works: undo Claude's edits with /rewind or double Esc, restore code or conversation, and what it can't undo.
Claude Code Prompts: Copy-Paste Formulas That Work
Claude Code prompts work best as formulas: goal, context, check. I break down Anthropic's official prompt library and the templates worth reusing daily.
Claude Code Plugins: an App Store in Your Terminal
Claude Code plugins bundle skills, agents and integrations you install with one command. How marketplaces work, what to install first, how to stay safe.
Is Claude Code Free? The Honest Answer for 2026
Is Claude Code free? No — the free claude.ai plan doesn't include it. Here's the cheapest legitimate way in, plus what the 'free' hacks really hide.
How to Install Claude Code: Mac, Windows, VS Code (2026)
How to install Claude Code on Mac, Windows and inside VS Code — one command per platform, zero programming required, plus the fix for 'command not found'.
How Does Claude Code Work? A Look Under the Hood
How does Claude Code work inside? The agentic loop, tools, permissions and checkpoints — explained for non-programmers, no computer science required.
Claude Code Goal Mode: the /goal Command for Beginners
Claude Code goal mode explained simply: set a finish line with /goal and Claude keeps working, turn after turn, until an independent checker says done.
Claude Code Glossary: 20+ Terms in Plain Human English
A Claude Code glossary of terms for non-programmers: tokens, context window, skills, hooks, MCP, subagents — each in one sentence plus a simple analogy.
Claude Code Context Window: Your AI's Working Desk
What is the Claude Code context window, how big is it, what eats the space, and what /context, /compact and /clear really do — explained with a desk.
Claude Code MCP Server Setup: First Server in 5 Minutes
Claude Code MCP server setup in plain English: one command, one check, and your AI gets real tools — docs search, databases, even a browser it can drive.
Claude Code Workflows: Examples & Recipes for Beginners
Real Claude Code workflows examples for non-programmers: explore any project, fix bugs, resume sessions, plan before edits, run parallel tasks safely.
What Is CLAUDE.md? The File That Stops Claude Forgetting
What is a CLAUDE.md file? A plain text note Claude Code reads at the start of every session — so your rules and preferences finally survive between chats.
Claude Code Directory: Settings, Files & Folder Structure
Where are Claude settings stored? A plain tour of the .claude directory files: CLAUDE.md, settings.json, skills, memory — and what is safe to touch.
Claude Code on the Web: Code From a Browser, Zero Install
Claude Code on the web runs coding tasks in Anthropic's cloud at claude.ai/code: connect GitHub, describe a task, review the ready PR — no install needed.
Claude Code vs Cursor: Which Is Better in 2026?
Claude Code vs Cursor compared for non-programmers: pricing, limits, how each works — and which to pick if you build personal tools, not software.
Claude Code Slack: Delegate Coding Right From the Chat
Claude Code Slack integration explained simply: mention @Claude in a channel, it fixes the bug in a cloud session and comes back with a ready pull request.
Claude Code Skills: Teach Claude Your Playbooks
Claude Code skills are saved playbooks Claude loads on demand. How to create your first SKILL.md, when skills trigger, and which skills to add first.
Does Claude Code Work in Russian? Setup & Languages
Using Claude Code in Russian works out of the box: write prompts in Russian, get answers in Russian, build real software. Here's my exact bilingual setup.
Claude Code Pricing in 2026: Plans, Limits, What I Pay
Claude Code pricing without the fog: what the $20 Pro plan really includes, when Max is worth $100 a month, and how to keep token costs from surprising you.
Claude Code Plan Mode: Think First, Build Second
Claude Code plan mode explained for non-programmers: what it does, the Shift+Tab shortcut, how to exit, plan mode vs accept edits, and when to use it.
Claude Code Usage Limits: Check Them, Then Stretch Them
How Claude Code usage limits work on Pro and Max, how to check yours with /usage in ten seconds, and the token-diet habits that make any plan last longer.
Claude Code Best Practices: 7 Habits That Save Hours
Claude Code best practices boil down to one rule: protect the context window. Plan mode, verification loops, CLAUDE.md hygiene and /clear habits, explained.
Built from the feed
Every post becomes a guide.
This library grows from real experiments, videos and threads — each one cross-linked, tagged and searchable. The course is the transformation; the guides are the map you keep coming back to.
Prefer to be transformed? Take the course →