🚨 Google’s former CEO revealed a secret that will reshape the world in the coming years, all because of AI.

He says that creating wealth and starting your own business has become much easier now, with just one condition: you must enter this field and truly understand the rules of the game.

If you only have 30 days to get started, act on this advice and go all out. This is the complete roadmap and all the tools you need, 100% free:

Phase One: Understanding Architecture and Fundamentals

Agent Architecture: Learn how to build an intelligent, independent AI agent that can make its own decisions and execute them. 🔗 https://code.claude.com/docs/en/how-claude-code-works… 🔗 https://langchain.com/blog

Claude Code 101 Course: Learn the basics of using Anthropic’s powerful coding tools. 🔗 https://anthropic.skilljar.com/claude-code-101

Live Demo: Tool-building for real projects, so you can see its capabilities with your own eyes. 🔗 https://anthropic.skilljar.com/claude-code-in-action…

Phase Two: Mastering Prompts and Context

Prompt Engineering Official Guide: Anthropic’s official tutorial on how to write professional-level prompts. 🔗 https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview…

Interactive Prompt Course: Hands-on training on GitHub to level up your prompting skills. 🔗 https://github.com/anthropics/prompt-eng-interactive-tutorial…

CLAUDE.md and Memory: The secret to making Claude remember the full context and rules of your project. 🔗 https://code.claude.com/docs/en/memory

Phase Three: Automation and Real-World Integration

MCP Protocol: The real revolution. Connect Claude to the tools and databases you use every day, like Slack, GitHub, and Google. 🔗 https://code.claude.com/docs/en/mcp

Skills: Teach Claude to repeat workflows and custom functions, letting it intelligently reuse them in your projects. 🔗 https://code.claude.com/docs/en/skills

Phase Four: Community Guides and Pro Tips

Complete Claude Code Guide: A massive open-source guide from the developer community, packed with tips and tricks. 🔗 https://github.com/FlorianBruniaux/claude-code-ultimate-guide…

Awesome Claude Code Collection: Curated best ready-to-use scripts, skills, and plugins. 🔗 https://github.com/hesreallyhim/awesome-claude-code…

Anthropic Academy: All 13 official courses from the company, with certificates, completely free. 🔗 https://anthropic.skilljar.com

Complete Official Docs: The ultimate reference guide for everything Claude. 🔗 https://code.claude.com/docs/en/overview…

Save this and turn on notifications for more content 🛎️

These resources are completely free, not a penny spent, but they’ll let you master a skill to do the work of an entire team solo, with the same quality.

How Claude Code works - Claude Code Docs

Source: https://code.claude.com/docs/en/how-claude-code-works Claude Code is an agentic assistant that runs in your terminal. While it excels at coding, it can help with anything you can do from the command line: writing docs, running builds, searching files, researching topics, and more.This guide covers the core architecture, built-in capabilities, andtips for working effectively. For step-by-step walkthroughs, seeCommon workflows. For extensibility features like skills, MCP, and hooks, seeExtend Claude Code.

The agentic loop

When you give Claude a task, it works through three phases:gather context,take action, andverify results. These phases blend together. Claude uses tools throughout, whether searching files to understand your code, editing to make changes, or running tests to check its work.The loop adapts to what you ask. A question about your codebase might only need context gathering. A bug fix cycles through all three phases repeatedly. A refactor might involve extensive verification. Claude decides what each step requires based on what it learned from the previous step, chaining dozens of actions together and course-correcting along the way.You’re part of this loop too. You can interrupt at any point to steer Claude in a different direction, provide additional context, or ask it to try a different approach. Claude works autonomously but stays responsive to your input.The agentic loop is powered by two components:modelsthat reason andtoolsthat act. Claude Code serves as theagentic harnessaround Claude: it provides the tools, context management, and execution environment that turn a language model into a capable coding agent.

Models

Claude Code uses Claude models to understand your code and reason about tasks. Claude can read code in any language, understand how components connect, and figure out what needs to change to accomplish your goal. For complex tasks, it breaks work into steps, executes them, and adjusts based on what it learns.Multiple modelsare available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning for complex architectural decisions. Switch with/modelduring a session or start withclaude \-\-model <name\>.When this guide says “Claude chooses” or “Claude decides,” it’s the model doing the reasoning.

Tools

Tools are what make Claude Code agentic. Without tools, Claude can only respond with text. With tools, Claude can act: read your code, edit files, run commands, search the web, and interact with external services. Each tool use returns information that feeds back into the loop, informing Claude’s next decision.The built-in tools generally fall into five categories, each representing a different kind of agency.

These are the primary capabilities. Claude also has tools for spawning subagents, asking you questions, and other orchestration tasks. SeeTools available to Claudefor the complete list.Claude chooses which tools to use based on your prompt and what it learns along the way. When you say “fix the failing tests,” Claude might:

1. Run the test suite to see what’s failing
2. Read the error output
3. Search for the relevant source files
4. Read those files to understand the code
5. Edit the files to fix the issue
6. Run the tests again to verify

Each tool use gives Claude new information that informs the next step. This is the agentic loop in action.**Extending the base capabilities:**The built-in tools are the foundation. You can extend what Claude knows withskills, connect to external services withMCP, automate workflows withhooks, and offload tasks tosubagents. These extensions form a layer on top of the core agentic loop. SeeExtend Claude Codefor guidance on choosing the right extension for your needs.

What Claude can access

When you runclaudein a directory, Claude Code gains access to:

• **Your project.**Files in your directory and subdirectories, plus files elsewhere with your permission.
• **Your terminal.**Any command you could run: build tools, git, package managers, system utilities, scripts. If you can do it from the command line, Claude can too.
• **Your git state.**Current branch, uncommitted changes, and recent commit history.
• **YourCLAUDE.md.**A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session.
• **Auto memory.**Learnings Claude saves automatically as you work, like your preferences. The first 200 lines or 25KB of MEMORY.md, whichever comes first, load at the start of each session.
• Extensions you configure.MCP serversfor external services,skillsfor workflows,subagentsfor delegated work, andClaude in Chromefor browser interaction.

Because Claude sees your whole project, it can work across it. When you ask Claude to “fix the authentication bug,” it searches for relevant files, reads multiple files to understand context, makes coordinated edits across them, runs tests to verify the fix, and commits the changes if you ask. This is different from inline code assistants that only see the current file.

Environments and interfaces

Theagentic loop,tools, and capabilities are the same everywhere you use Claude Code. What changes is where the code executes and how you interact with it.

Execution environments

Claude Code runs in three environments, each with different tradeoffs for where your code executes.

Interfaces

You can access Claude Code through the terminal, thedesktop app,IDE extensions,claude.ai/code,Remote Control,Slack, andCI/CD pipelines. The interface determines how you see and interact with Claude, but the underlying agentic loop is identical. SeeUse Claude Code everywherefor the full list.

Work with sessions

Claude Code saves your conversation locally as you work. Each message, tool use, and result is written to a plaintext JSONL file under~/\.claude/projects/, which enablesrewinding,resuming, and forkingsessions. Before Claude makes code changes, it also snapshots the affected files so you can revert if needed. For paths, retention, and how to clear this data, seeapplication data in~/\.claude.**Sessions are independent.**Each new session starts with a fresh context window, without the conversation history from previous sessions. Claude can persist learnings across sessions usingauto memory, and you can add your own persistent instructions inCLAUDE.md.

Work across branches

Each Claude Code conversation is a session tied to your current directory. The/resumepicker shows sessions from the current worktree by default, with keyboard shortcuts to widen the list to other worktrees or projects. SeeManage sessionsfor the full list of picker shortcuts and how name resolution works.Claude sees your current branch’s files. When you switch branches, Claude sees the new branch’s files, but your conversation history stays the same. Claude remembers what you discussed even after switching.Since sessions are tied to directories, you can run parallel Claude sessions by usinggit worktrees, which create separate directories for individual branches.

Resume or fork sessions

Resuming a session withclaude \-\-continueorclaude \-\-resumereopens it under the same session ID and appends new messages to the existing conversation. Forking with\-\-fork\-sessionor/branchcopies the history into a new session ID, leaving the original unchanged.For the resume flags, the/resumepicker, naming, and what happens when the same session is open in two terminals, seeManage sessions.

The context window

Claude’s context window holds your conversation history, file contents, command outputs,CLAUDE.md,auto memory, loaded skills, and system instructions. As you work, context fills up. Claude compacts automatically, but instructions from early in the conversation can get lost. Put persistent rules in CLAUDE.md, and run/contextto see what’s using space.For an interactive walkthrough of what loads and when, seeExplore the context window.

When context fills up

Claude Code manages context automatically as you approach the limit. It clears older tool outputs first, then summarizes the conversation if needed. Your requests and key code snippets are preserved; detailed instructions from early in the conversation may be lost. Put persistent rules in CLAUDE.md rather than relying on conversation history.To control what’s preserved during compaction, add a “Compact Instructions” section to CLAUDE.md or run/compactwith a focus (like/compact focus on the API changes).If a single file or tool output is so large that context refills immediately after each summary, Claude Code stops auto-compacting after a few attempts and shows an error instead of looping. SeeAuto-compaction stops with a thrashing errorfor recovery steps.Run/contextto see what’s using space. MCP tool definitions are deferred by default and loaded on demand viatool search, so only tool names and server instructions consume context until Claude uses a specific tool.

Manage context with skills and subagents

Beyond compaction, you can use other features to control what loads into context.Skillsload on demand. Claude sees skill descriptions at session start, but the full content only loads when a skill is used. For skills you invoke manually, setdisable\-model\-invocation: trueto keep descriptions out of context until you need them. For skills you didn’t write, useskillOverridesto do the same from settings.Subagentswork in their own context window. A subagent starts fresh unless it’s afork, which starts with a copy of your conversation so far. Either way, the subagent’s tool calls stay out of your context, and Claude gets back a summary when the subagent finishes.Seecontext costsfor what each feature costs, andreduce token usagefor tips on managing context.

Stay safe with checkpoints and permissions

Claude has two safety mechanisms: checkpoints let you undo file changes, and permissions control what Claude can do without asking.

Undo changes with checkpoints

**File edits are reversible.**Before Claude edits a file, it snapshots the current contents. If something goes wrong, pressEsctwice to rewind to a previous state, or ask Claude to undo.Checkpoints are separate from git and remain available when you resume a conversation. They only cover file changes, and a restoreskips symlinked and hard-linked files. Actions that affect remote systems (databases, APIs, deployments) can’t be checkpointed. You control those with your permission mode and permission rules.

Control what Claude can do

Choose a permission mode to set what Claude can do without asking you. PressShift\+Tabto cycle through the permission modes:

• Auto: a classifier reviews most actions in the background and blocks the risky ones instead of asking you. On Pro, Max, and Team plans, it’s thebuilt-in starting permission modefor interactive terminal and VS Code sessions
• Manual: Claude asks before file edits and shell commands
• Accept edits: Claude edits files and runs common filesystem commands likemkdirandmvwithout asking, still asks for other commands
• Plan: Claude explores and proposes a plan without editing your source files

You can also allow specific commands in\.claude/settings\.jsonso Claude doesn’t ask each time. This is useful for trusted commands likenpm testorgit status. Settings can be scoped from organization-wide policies down to personal preferences. SeePermissionsfor details.

Work effectively with Claude Code

These tips help you get better results from Claude Code. For more on specific prompts, verification, and planning, seeBest practices.

Ask Claude Code for help

Claude Code can teach you how to use it. Ask questions like “how do I set up hooks?” or “what’s the best way to structure my CLAUDE.md?” and Claude will explain.Built-in commands also guide you through setup:

• /initgenerates a starter CLAUDE.md for your project
• /doctorruns a setup checkup that diagnoses installation and configuration issues and can fix them

It’s a conversation

Claude Code is conversational. You don’t need perfect prompts. Start with what you want, then refine:

[Claude investigates, tries something]

[Claude adjusts approach]When the first attempt isn’t right, you don’t start over. You iterate.

Interrupt and steer

You can redirect Claude at any point without waiting for the turn to finish or starting over:

• **PressEsc**to stop Claude immediately. The running tool call is canceled and Claude waits for your next instruction. If you have messages queued, Claude Codesends them next.
• **Type a correction and pressEnter**to send it without stopping the running tool. Claude reads it as soon as the current action completes and adjusts before deciding its next step.

Delegate, don’t dictate

Think of delegating to a capable colleague. Give context and direction, then trust Claude to figure out the details:

You don’t need to specify which files to read or what commands to run. Claude figures that out.

What’s next