A comprehensive handbook covering Claude Code, Anthropic's AI-powered software development agent. It walks through installation, VS Code setup, subscription tiers, prompt discipline, Plan Mode, feature-by-feature development, token economics, and the internal agent loop mechanics. The guide targets both experienced developers looking to multiply their output and non-technical builders wanting to create software without prior coding experience. Key practices covered include using Plan Mode for 80% of sessions, writing Product Requirements Documents, building incrementally, managing context windows, and understanding how Claude reads codebases selectively via tool calls.
Table of contents
Table of ContentsChapter 1: The Context That Made Claude Code NecessaryChapter 2: Anthropic — Background and PurposeChapter 3: The Claude Model FamilyChapter 4: What Claude Code IsChapter 5: Why the Development Community Required ThisChapter 6: Installation and Initial SetupChapter 7: VS Code and the Claude Code ExtensionChapter 8: Subscriptions, Token Costs, and UsageChapter 9: Working in Your First SessionChapter 10: Prompt Discipline — Inputs Determine OutputsChapter 11: Planning as a Core PracticeChapter 12: Building Feature by FeatureChapter 13: How Claude Code Actually WorksChapter 14: Architecting Applications Well with Claude CodeChapter 15: Plan Mode, Edit Mode, and Operational ModesChapter 16: Context Windows and Session ManagementChapter 17: MCP Servers and External IntegrationsChapter 18: Agents, Sub-Agents, and Parallel WorkflowsChapter 19: Skills, Rules, and Persistent InstructionsChapter 20: Autonomous Loops — Conditions for UseChapter 21: Code Review, Security, and VerificationChapter 22: Starter Project BlueprintsChapter 23: The Current Frontier of Claude CodeChapter 24: Software Engineering as a DisciplineChapter 25: A Structured Path ForwardAppendix A: Claude Code Command ReferenceAppendix B: Standard Prompt TemplatesAppendix C: Reference MaterialClosing1 Comment
Sort: