Claude Code

Instructor-led workshop Claude Code, Deep-Dive, hands-on

Over deze training

In deze 2 daagse hands-on workshop Claude Code worden zowel de basis principes als de advanced features van Claude Code behandeld zoals bijv. custom skills, automated agents (subagents), lifecycle hooks, en plugins.

In deze training leer je hoe je Claude Code effectief kan inzetten voor agentic workflows en hoe je code quality en security aspecten kan bewaken. Daarnaast ligt de nadruk op best practices om het meeste uit Claude Code te halen.

Duur: 2 dagen Vorm: Instructor-led, hands-on labs Taal: Nederlands of Engels Niveau: Beginner/Intermediate

Doelgroep

  • Full-stack, Frontend en Backend Developers
  • Technical Leads, Executives, CTO’s en Software Architects

Modules

Module 1. Introduction to Claude Code

  • What is Claude Code
  • System requirements
  • Installation
  • Account types
  • Starting your first session
  • The agentic loop
  • Platforms and IDE integrations
  • Keyboard shortcuts and controls
  • Built-in commands and tools
  • Configuration hierarchy

Module 2. Commands, Context Window and Memory

  • Essential slash commands
  • The context window
  • Compact and Auto-compaction
  • CLAUDE.md
  • Memory hierarchy and locations
  • Modular rules
  • Auto memory across sessions
  • Path Imports
  • Session management and checkpoints
  • Effective CLAUDE.md files

Module 3. Plan Mode and Specs

  • What is Plan Mode
  • Entering and exiting Plan Mode
  • Explore, plan, implement, commit
  • Editing plans in a text editor
  • Extended thinking mode
  • Headless Plan Mode
  • Creating specs and plans
  • Common workflows

Module 4. Skills and Hooks

  • What are skills
  • Creating SKILL.md files
  • Skill invocation and arguments
  • What are hooks
  • Hook lifecycle and events
  • Hook configuration in settings
  • Matcher patterns and filtering
  • Command hooks and exit codes
  • Prompt-based and agent-based hooks
  • Async hooks and background execution

Module 5. Tooling with MCP Servers

  • What is the Model Context Protocol (MCP)
  • Purpose and benefits of MCP
  • Clients and servers in MCP
  • Structure of MCP messages
  • MCP endpoints
  • Adding context with MCP
  • Creating a custom MCP Server
  • MCP configuration
  • Integrate a MCP server with Claude Code
  • MCP security

Module 6. Agents, Subagents and Orchestrating Agent Teams

  • Built-in subagents
  • Creating custom subagents
  • Subagent tools and permissions
  • Preloading skills and memory
  • Foreground vs. background execution
  • Resuming subagent context
  • Introduction to agent teams
  • Orchestrating an agent team
  • Display modes: in-process vs. tmux
  • Quality gates and best practices

Module 7. Plugins

  • What are plugins
  • Plugin structure and manifest
  • Creating your first plugin
  • Adding skills to a plugin
  • Adding agents and hooks
  • Testing plugins
  • Converting configs to plugins
  • Installing plugins from marketplaces
  • Distributing a plugin marketplace

Module 8. Best Practices, Security and Control

  • Verification options
  • Course-correcting and rewinding
  • Managing context aggressively
  • Permission modes
  • Permission rules syntax
  • Sandboxing
  • Prompt injection protection
  • Cost and token management
  • Managed settings and policies
  • Scaling: headless and parallel sessions

Appendix A: Effective prompt engineering

Appendix B: Large Language Models fundamentals

Voorkennis

  • Software development ervaring
  • Basiskennis van Large Language Models (LLMs) en AI agents is een pré, maar niet vereist

Interesse?

Neem contact op voor meer informatie, beschikbaarheid of een offerte op maat.