AI for developers
Claude Code in practice: the terminal code assistant
Install, configure and integrate a terminal code assistant into your daily developer work.
- Duration
- 14 h · 2 days
- Level
- Intermediate
- Format
- On site · Remote · Blended
- Max. group size
- 12 participants
Overview
This program teaches how to work with a command-line code assistant. Participants install and configure it (project instructions file, permissions), use it to navigate code, work with Git and run commands, then exploit its advanced features: hooks, custom commands, plan mode, sub-agents and MCP servers. They adopt an explore-plan-code-verify cycle to debug, refactor, test and document.
Who this program is for
- Experienced developers
- Tech leads equipping their team
- DevOps and quality engineers
Prerequisites
- Significant experience in a programming language
- Practice of Git and the terminal
- Ability to formulate requests to a generative AI
Learning objectives
- Install and configure the assistant in a project
- Write an effective instructions file and manage permissions
- Navigate code, use Git and shell commands
- Manage a session's context
- Configure hooks, custom commands and sub-agents
- Connect MCP servers
- Apply a safe workflow: explore, plan, code, verify
Detailed curriculum
4 modules · 14 h · 2 days
Day 1
Installation and configuration
30% theory · 70% practice
- How it works and first uses
- Installation and authentication
- Project instructions file
- Permissions and execution modes
- First sessions
🛠 Hands-on workshops
Configured project1 h
Configure the tool on a real project.
✅ Deliverable : A working instructions file
Everyday use
50% theory · 50% practice
- Exploring and explaining a codebase
- Modifying code and reviewing changes
- Git: commits, branches, merge requests
- Shell commands and scripts
- Managing context and consumption
Day 2
Advanced features
30% theory · 70% practice
- Hooks: automating checks
- Custom commands
- Plan mode
- Sub-agents
- MCP servers and external tools
🛠 Hands-on workshops
Automate your workflow2 h
Write hooks and commands for the project.
✅ Deliverable : A set of hooks and commands
Explore, plan, code, verify workflow
30% theory · 70% practice
- Recommended work cycle
- Debugging, refactoring and tests
- Documentation
- IDE integration
- Costs, security and limits
🛠 Hands-on workshops
End-to-end feature2 h
Deliver a feature following the work cycle.
✅ Deliverable : A tested, documented feature
Tools and technologies
Claude CodeGitMCPVisual Studio Code
Teaching methods
- Alternating short lectures and hands-on work
- Live demonstrations by the trainer
- Capstone project built throughout the modules
- Group corrections and discussion of best practices
Assessment
- Hands-on exercises corrected in each module
- Mini-project completed at the end of the course
- Knowledge-check quiz
Required equipment
- A computer with an internet connection
- Node.js, Git, a terminal and an account with access to the tool
- A code project to work on
Resources provided
- Course materials and repository of corrected exercises
- Project instructions file template
- Catalog of hooks and custom commands
Career outcomes
- A project configured for assisted development
- A documented team workflow
- Security reflexes and cost control
Related video courses
My video courses that go with this program, to get ready for the training or to review afterwards. Free with an account.
