Back to courses
IT & ENGINEERING Advanced Popular

Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)

Read a free preview of the first lesson No account, no card · the opening of Lesson 1, plus the interactive platform demo and the AI Professor Start now Finish the course with a publicly verifiable Certificate of Completion See the certificate

A complete, terminal-first program for mastering the Claude Code coding agent in a professional development workflow. You learn the agent-first vs IDE-first mental model, CLAUDE.md as project memory, multi-file editing and refactoring in large codebases, the full git workflow (branches, commits, conflicts, code review and PRs), headless mode (claude -p) for scripting and non-interactive pipelines, subagents and agent teams for controlled parallelization, routing across the 2026 Anthropic model lineup (Claude Fable 5, Opus 5, Sonnet 5, Sonnet 4.6 and Haiku 4.5) as a cost and quality lever, lifecycle hooks (PreToolUse/PostToolUse/Stop/SubagentStop) as deterministic guardrails, CI/CD integration with the official claude-code-action on GitHub Actions and GitLab, consuming MCP with least-privilege permissions, plus security and sandboxing anchored in CVE-2025-59536 and the OWASP Agentic Top 10. Everything strictly anchored in official Anthropic documentation, with an end-to-end agentic capstone project on a realistic repo. Content updated for Anthropic's most capable model, Claude Fable 5, and the new Claude Sonnet 5.

11 modules
28 lessons
~25h duration
v1.0 version
AI professor An AI agent built into every lesson — ask questions and get instant answers based on the course content
Hands-on exercises Real scenarios and practical exercises directly on the platform, with instant feedback
Progress & analytics A personal dashboard with statistics, streaks, scores and structured learning paths
Interactive AI quizzes Questions generated by AI and adapted to your level, with detailed explanations
Individual course access
€99
/ month, VAT included
Get started
All lessons AI quizzes AI professor included Cancel anytime
Or read a free preview of the first lesson
or
Recommended
IT Pro bundle
€399
/ month, VAT included
See the IT Pro bundle
  • Every IT Pro courseA full library, not just this course
  • AI professor in every lessonAnswers when you need them, included in your subscription
  • Quizzes, progress, streaks & statistics
  • Content updated regularly
Cancel anytime
Secure payment
Updated regularly
Content in English
Built-in AI agent Exclusive Ask anything about the lesson and get an instant answer — the agent knows the course content
Interactive AI chat Automatic summaries Personalized quizzes

What you will learn

Practical skills you gain by completing this course

Claude Code Fundamentals: Installation, CLI and the Agent-First Mental Model
Multi-File and Large Codebases: Plan, Edit, Review and Context Management
The Full Git Workflow: Branches, Commits, Conflicts, Code Review and PRs
Headless Mode (claude -p) and Non-Interactive Automation
Subagents and Agent Teams: Orchestration, Delegation and Controlled Parallelization
Lifecycle Hooks: Deterministic Guardrails and Custom Automations
CI/CD Integration: GitHub Actions with claude-code-action and GitLab CI/CD
MCP in Practice: Consuming External Tools with Least-Privilege Permissions
Security and Sandboxing: Deny Rules, Least-Privilege and Lessons from Real 2026 CVEs
Capstone Project: An End-to-End Agentic Pipeline on a Realistic Repo
2026 Appendix: Official Resources, Updates, Learning Paths and the Agent SDK

Who it is for

Developers Software engineers Solution architects CTOs / Tech Leads Data Scientists ML Engineers DevOps Engineers

Recommended level

Advanced

Assumes hands-on experience with AI and complex scenarios.

Updates

Regular

Last update: Aug 8, 2026. Content kept up to date.

Category

IT & Engineering

A technical course for IT professionals — available with individual course access or the IT Pro / All Access bundle.

Advanced level

Hands-on experience required

Assumes practical experience with AI. Covers complex scenarios and advanced strategies.

Always up to date

Last update: Aug 8, 2026

The course is updated regularly with the latest information, tools and practices from the industry.

Practical and applied

28 lessons with real examples

Each lesson includes practical scenarios, actionable checklists and quizzes to check your understanding.

Certificate of Completion

You leave with proof anyone can check

for the course Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)

A private attestation with a unique number and a QR code. A recruiter confirms it is authentic in a second, on the public verification page — no account, no cost.

What your certificate states for this course

  • Claude Code Fundamentals: Installation, CLI and the Agent-First Mental Model
  • Multi-File and Large Codebases: Plan, Edit, Review and Context Management
  • The Full Git Workflow: Branches, Commits, Conflicts, Code Review and PRs
  • Headless Mode (claude -p) and Non-Interactive Automation
  • Subagents and Agent Teams: Orchestration, Delegation and Controlled Parallelization
  • Lifecycle Hooks: Deterministic Guardrails and Custom Automations
Verify a certificate Certification policy →

A private attestation of course completion. It is NOT a diploma or a state-recognised qualification under Romanian Laws 198/2023, 199/2023 or Government Ordinance 129/2000; employers may take it into account at their own discretion. Certification policy.

Anyone can verify it

Public verification page, QR code and cryptographic fingerprint — no account and no cost for the person checking.

Useful when job hunting

Add it to your CV and LinkedIn profile; a recruiter confirms authenticity with one click.

Transparent

It shows exactly what it attests: the course, the modules covered, the assessment score and the completion date.

Curriculum

11 modules, 28 lessons — structured to learn step by step.

11 modules
28 lessons
~25h of content
Interactive quizzes
Free preview available Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game
Read the preview
1 Free preview lesson Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game
Read the preview
2 Installation, Authentication, and Your First Run: From npm to Your First Agentic Task
50 min
3 CLAUDE.md as Project Memory: Instructions, Conventions, and Persistent Context
50 min
1 The Plan / Edit / Review Loop: How the Agent Works on Multiple Files at Once
51 min
2 Context Management in Large Codebases: The Context Window, /compact, and Efficiency Strategies
52 min
3 Refactoring at Scale with Zero Regressions: Migrations, Renames, and Cross-Cutting Changes
53 min
1 Assisted Git from the Terminal: Branches, Staging, and Quality Commit Messages
50 min
2 Resolving Merge Conflicts and Assisted Rebase: Strategies for a Clean History
51 min
3 AI-Assisted Code Review and Pull Requests: From Diff to PR with the gh CLI
51 min
1 claude -p: Programmatic Execution, Structured Output, and Script Integration
52 min
2 Non-Interactive Pipelines and Batch Operations: Repeatable, Safe Automation
51 min
1 Subagents: Context Isolation, the Task Tool, and Defining Specialized Agents
52 min
2 Agent Teams and Controlled Parallelization: Delegation, Orchestration, and Safety Limits
52 min
1 The Anatomy of Hooks: PreToolUse, PostToolUse, Stop, SubagentStop, and Configuration in settings.json
53 min
2 Hooks in Practice: Deterministic Guardrails, Automatic Formatting, and Custom Validations
52 min
1 claude-code-action on GitHub Actions: Setup, Triggers, and PR Automation
53 min
2 GitLab CI/CD and Portable Agentic Pipelines: Headless Mode on Any Runner
51 min
1 Connecting Claude Code to MCP Servers: Configuration, Scope, and Transport
52 min
2 Least-Privilege MCP: Minimal Permissions, Tool Approvals, and Trusted Data Sources
52 min
1 The Code Agent's Threat Model: CVE-2025-59536 and CVE-2026-21852 Dissected
53 min
2 Deny Rules, Permissions, and Never-Run-as-Root: Defensive Configuration of Claude Code
52 min
3 Sandboxing, Isolation, and the OWASP Agentic Top 10: Defense in Depth for Coding Agents
53 min
1 From Issue to Code: Multi-File Implementation, Branch, and an Agent-Guided PR
53 min
2 Headless, Subagents, and a Generated Guide: Automating Documentation and Verification
52 min
3 CI, Security, and Delivery: claude-code-action, Deny Rules, and the Final Production Posture
53 min
1 Official Resources, 2026 Updates, and Learning Paths
34 min
2 Claude Design → Claude Code: The Design-to-Code Handoff (Anthropic Labs, 2026)
18 min
3 Agent SDK: From claude -p to Custom Agents in Production
30 min
Access this course for €99 / month, VAT included

Ready to start learning?

Create an account and choose how you want to learn — just this course, or the full IT Pro bundle.

Get started Compare plans
28 hands-on lessons Content updated regularly AI professor included in your subscription