Claude Code is easy to take for a smart autocomplete in the terminal and stop there. But it is not a suggester - it is an agentic runtime: it receives context, chooses a tool, checks permission, performs an action and continues the loop until the task is solved or stopped. The difference is fundamental. Once you understand that it is a controllable environment with its own trust boundaries, configuration and precedence, it turns from a tool for quick edits into a reliable part of the engineering process - from the first run to CI and corporate policy.

This book takes Claude Code from installation to fine-tuning. First - a checkable foundation: a map of surfaces (terminal, IDE, Desktop, web, remote), installation and updates, the billing model, the first run and the agentic loop itself. Then - daily work: interactive mode, the task contract, plan mode, implementation with verification, git sessions, checkpoints and worktrees, models and context control. Next - trust: permission modes and rules, the sandbox, prompt injection and secrets. After that - configuration and extension: scopes and precedence, CLAUDE.md and memory, settings.json, skills, subagents, teams, hooks, MCP, plugins. Then - interfaces and automation: IDE and web, headless, GitHub and GitLab CI, monorepos. And finally - production: the enterprise profile, diagnostics and a ready baseline, plus five references to the official interface.

The material rests on one distinction. Where a fact, a command name, a key, a path or a precedence order is directly described by Anthropic, the book marks it as official and cites the primary source. Where a technique follows from documented behavior but is not a product requirement, it is an engineering conclusion - useful but not passed off as a rule. This split matters more than convenient generalizations: a setting becomes useful only when you understand its source, its allowed value and the cost of a mistake.