Claude Code Fundamentals

This path consists of a single guide that walks you through installing Claude Code, logging in, and making your first code change, so by the end you will have a working setup and a completed first edit. With only one step, there is no ordering to worry about beyond starting at the beginning.

6 steps

1. 1

   Claude Code Quickstart: Install, Log In, and Make Your First Code Change

   This guide walks through getting started with Claude Code, Anthropic's terminal-based coding tool. It covers installing Claude Code on macOS, Linux, Windows, and WSL using the native installer, Homebrew, or WinGet, then logging in with a Claude subscription, Console account, or enterprise cloud provider. From there it shows how to start a session in a project directory, ask questions about a codebase, make a first code change with permission modes, and use Git conversationally. It is based on Anthropic's official quickstart documentation.

2. 2

   Claude Code Subagents: Built-in Agents, Delegation, and Context Management

   This guide explains subagents in Claude Code: specialized AI assistants that handle side tasks like codebase search or research in their own context window, returning only a summary to your main conversation. It covers why subagents preserve context and control costs, the built-in subagents (Explore, Plan, General-purpose, and helper agents), how model inheritance works for Explore, and the options for restricting or disabling subagent delegation through permissions and environment variables.

3. 3

   How Claude Code Remembers Your Project: CLAUDE.md Files and Auto Memory

   Every Claude Code session starts with a fresh context window, so persistent knowledge has to come from somewhere. This guide explains the two mechanisms that carry knowledge across sessions: CLAUDE.md files, which you write to give Claude standing instructions, and auto memory, notes Claude writes itself based on your corrections. It covers where CLAUDE.md files can live, what to put in them, how to generate one with /init, and how to verify your files loaded.

4. 4

   How to Connect an MCP Server to Claude Code (Step by Step)

   This guide walks through connecting a Model Context Protocol (MCP) server to Claude Code using the CLI. You will register a hosted server with the claude mcp add command, verify the connection with claude mcp list, use the server inside a session, and remove it when finished. It also covers what the connection status indicators mean, where the configuration is saved on disk, and the difference between local, user, and project scopes.

5. 5

   Claude Code Permissions: Rules, Modes, and How Approvals Are Saved

   This guide explains how Claude Code's permission system works based on Anthropic's documentation. It covers the tiered approval model for read-only tools, Bash commands, and file edits; where permanent approvals are saved; how allow, ask, and deny rules are evaluated; the difference between bare tool-name deny rules and scoped pattern rules; the Ctrl+E command explanation shortcut; and the permission modes you can set with defaultMode, including default, acceptEdits, plan, and auto.

6. 6

   Connecting Claude Code to External Tools with MCP: Servers, Transports, and Configuration

   This guide explains how to connect Claude Code to external tools and data sources using the Model Context Protocol (MCP). It covers what MCP connections enable, such as working with issue trackers, databases, and monitoring tools; where to find reviewed connectors; how to scaffold your own server with the official mcp-server-dev plugin; and how to install remote HTTP, remote SSE, and local stdio servers, including transport-specific flags, JSON configuration pitfalls, and environment variables like CLAUDE_PROJECT_DIR.