Claude Code Complete Guide
A practical guide to multi-session workflows, automation, and extension patterns in Claude Code.
Claude Code is a terminal-based AI coding agent. This handbook is for advanced users who want to run it as an operating system for software work: multiple sessions, explicit plans, automated checks, project memory, subagents, hooks, MCP tools, and repeatable team workflows.
Who this is for
Engineers and AI engineering leads who already use Claude Code and want a clean operating model for real repositories. Basic prompting is intentionally skipped.
Latest Update Baseline
Baseline
This English edition uses the same operating assumptions as the Korean handbook, with a focus on Claude Code v2.1-era workflows: native launcher, fewer permission prompts, denied domain controls, recap, worktrees, hooks, MCP, and subagents.
- Use native installation paths first; treat npm installation as legacy where official tooling does.
- Keep every agent session scoped to a concrete working directory, branch, and verification target.
- Prefer worktrees for parallel implementation, review, and experiment tracks.
- Put durable project rules in
CLAUDE.md, but keep them short enough that the agent can obey them. - Use subagents for bounded parallel work, not for urgent blocking decisions.
- Use hooks and MCP only after the manual workflow is clear enough to automate.
- Make verification part of the prompt contract: tests, lint, typecheck, browser checks, or review notes.
Handbook Map
1. Plan and Environment Setup
Plans, installation, update policy, and baseline repository setup.
2. Mastering CLAUDE.md
Project memory, rule hierarchy, imports, and maintainable instruction files.
3. Multi-session Workflow
Worktree-based parallel sessions and clean handoff patterns.
4. Subagents
How to delegate bounded work without losing control of the main thread.
5. Hooks
Event-driven automation for checks, guardrails, and repository hygiene.
6. MCP Integration
Tool servers, resources, trust boundaries, and team configuration.
7. Skills and Slash Commands
Reusable workflows, custom commands, and project-specific operating recipes.
8. Plan Mode
Analysis-first work that turns ambiguity into a concrete implementation contract.
9. Context Management
Compaction, recap, project memory, and token discipline.