Claude Code in Practice
Use Claude Code effectively on real projects: project memory, permissions and plan mode, context management, custom commands, hooks, MCP servers, subagents and git workflows.
11 lessons in 4 modules.
Lessons
Module 1: Setup
- CLAUDE.md: What Actually Belongs in Your Project Memory File
- Claude Code Permission Modes: Balancing Speed and Safety
- Plan Mode in Claude Code: When It's Worth the Extra Step
Module 2: Working in sessions
- Claude Code Context Window: Managing Compaction Without Losing the Thread
- Custom Slash Commands in Claude Code: Turning Repeated Prompts Into Workflows
- Claude Code Hooks: Automating Guardrails Without Slowing Yourself Down
Module 3: Extending Claude Code
- Claude Code MCP Servers: Connecting Tools Without Custom Integrations
- Claude Code Subagents: When to Delegate vs. Handle It Inline
- Claude Code Background Tasks: Running Long Jobs Without Blocking Your Session
Module 4: Team workflows
- Git Workflows With Claude Code: Letting an Agent Commit Without Losing Control
- Using Claude Code for Code Review: What It Catches That a Linter Doesn't
Final project
Set up a repository with a CLAUDE.md, a permission configuration, one hook that runs your tests before commits, and one custom slash command; use plan mode to implement a small feature and review the result.
Next: AI Agents: From Concepts to Production