IT course Advanced level

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

Master Claude Code: multi-file editing, git workflow, headless mode, subagents, hooks, CI/CD, MCP and security. Terminal-first course updated for 2026.

Lessons
28in 11 modules
Duration
~25 hself-paced
Quiz
382questions
Level
Advancedfor practitioners
  • In English
  • Updated on
Free preview · lesson 1 · no account needed Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game Most developers who try an AI programming assistant use it without tapping into what it can truly do: they keep it captive inside the editor, like a smarter autocomplete that proposes the next line, while they remain the ones opening files, positioning the cursor, and running commands. Claude Code proposes something radically different — an agent that lives in the terminal, takes over execution based on your intent, and closes the loop on its own between reading code, modifying it across multiple files simultaneously, and running the tests. Read the preview

What you will learn

The course’s skills. The same ones appear on your Certificate of Completion, so you can show what you covered.

  • 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

About the course

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 5.1, Opus 5.5, Sonnet 5 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 5.1, for Claude Opus 5.5, and for Claude Sonnet 5.

Who it is for

For developers, engineers and technical professionals who build or integrate AI solutions. It belongs to AI for Developers, on the IT track.

What you need

Advanced level: assumes hands-on experience with AI in the course’s field.

Course curriculum

11 modules · 28 lessons · about 25 hours · 382 quiz questions

Read a free preview of lesson 1: “Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game” No account needed. See how a lesson is written before you pay.

  1. Module 1: Claude Code Fundamentals: Installation, CLI and the Agent-First Mental Model

    3 lessons · 2 h 32 min · 43 questions
    1. Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game Free preview of the lesson “Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game” 52 min 14 questions
    2. Installation, Authentication, and Your First Run: From npm to Your First Agentic Task 50 min 15 questions
    3. CLAUDE.md as Project Memory: Instructions, Conventions, and Persistent Context 50 min 14 questions

  2. Module 2: Multi-File and Large Codebases: Plan, Edit, Review and Context Management

    3 lessons · 2 h 36 min · 43 questions
    1. The Plan / Edit / Review Loop: How the Agent Works on Multiple Files at Once 51 min 14 questions
    2. Context Management in Large Codebases: The Context Window, /compact, and Efficiency Strategies 52 min 15 questions
    3. Refactoring at Scale with Zero Regressions: Migrations, Renames, and Cross-Cutting Changes 53 min 14 questions

  3. Module 3: The Full Git Workflow: Branches, Commits, Conflicts, Code Review and PRs

    3 lessons · 2 h 32 min · 43 questions
    1. Assisted Git from the Terminal: Branches, Staging, and Quality Commit Messages 50 min 15 questions
    2. Resolving Merge Conflicts and Assisted Rebase: Strategies for a Clean History 51 min 14 questions
    3. AI-Assisted Code Review and Pull Requests: From Diff to PR with the gh CLI 51 min 14 questions

  4. Module 4: Headless Mode (claude -p) and Non-Interactive Automation

    2 lessons · 1 h 43 min · 30 questions
    1. claude -p: Programmatic Execution, Structured Output, and Script Integration 52 min 16 questions
    2. Non-Interactive Pipelines and Batch Operations: Repeatable, Safe Automation 51 min 14 questions

  5. Module 5: Subagents and Agent Teams: Orchestration, Delegation and Controlled Parallelization

    2 lessons · 1 h 44 min · 29 questions
    1. Subagents: Context Isolation, the Task Tool, and Defining Specialized Agents 52 min 14 questions
    2. Agent Teams and Controlled Parallelization: Delegation, Orchestration, and Safety Limits 52 min 15 questions

  6. Module 6: Lifecycle Hooks: Deterministic Guardrails and Custom Automations

    2 lessons · 1 h 45 min · 30 questions
    1. The Anatomy of Hooks: PreToolUse, PostToolUse, Stop, SubagentStop, and Configuration in settings.json 53 min 16 questions
    2. Hooks in Practice: Deterministic Guardrails, Automatic Formatting, and Custom Validations 52 min 14 questions

  7. Module 7: CI/CD Integration: GitHub Actions with claude-code-action and GitLab CI/CD

    2 lessons · 1 h 44 min · 30 questions
    1. claude-code-action on GitHub Actions: Setup, Triggers, and PR Automation 53 min 16 questions
    2. GitLab CI/CD and Portable Agentic Pipelines: Headless Mode on Any Runner 51 min 14 questions

  8. Module 8: MCP in Practice: Consuming External Tools with Least-Privilege Permissions

    2 lessons · 1 h 44 min · 29 questions
    1. Connecting Claude Code to MCP Servers: Configuration, Scope, and Transport 52 min 14 questions
    2. Least-Privilege MCP: Minimal Permissions, Tool Approvals, and Trusted Data Sources 52 min 15 questions

  9. Module 9: Security and Sandboxing: Deny Rules, Least-Privilege and Lessons from Real 2026 CVEs

    3 lessons · 2 h 38 min · 45 questions
    1. The Code Agent's Threat Model: CVE-2025-59536 and CVE-2026-21852 Dissected 53 min 15 questions
    2. Deny Rules, Permissions, and Never-Run-as-Root: Defensive Configuration of Claude Code 52 min 15 questions
    3. Sandboxing, Isolation, and the OWASP Agentic Top 10: Defense in Depth for Coding Agents 53 min 15 questions

  10. Module 10: Capstone Project: An End-to-End Agentic Pipeline on a Realistic Repo

    3 lessons · 2 h 38 min · 43 questions
    1. From Issue to Code: Multi-File Implementation, Branch, and an Agent-Guided PR 53 min 14 questions
    2. Headless, Subagents, and a Generated Guide: Automating Documentation and Verification 52 min 14 questions
    3. CI, Security, and Delivery: claude-code-action, Deny Rules, and the Final Production Posture 53 min 15 questions

  11. Module 11: 2026 Appendix: Official Resources, Updates, Learning Paths and the Agent SDK

    3 lessons · 1 h 22 min · 17 questions
    1. Official Resources, 2026 Updates, and Learning Paths 34 min 6 questions
    2. Claude Design → Claude Code: The Design-to-Code Handoff (Anthropic Labs, 2026) 18 min 6 questions
    3. Agent SDK: From claude -p to Custom Agents in Production 30 min 5 questions
By email

Email me the course syllabus

Modules and lessons in order, plus the link to the preview of lesson 1 — so you can decide at your own pace.

By pressing the button you agree to receive the course syllabus by email. You confirm the address with one click in the first email. Privacy policy

How you learn

You read the lesson, ask the AI Professor right on the page and check what you remember.

Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game

Most developers who try an AI programming assistant use it without tapping into what it can truly do: they keep it captive inside the editor, like a smarter autocomplete that proposes the next line, while they remain the ones opening files, positioning the cursor, and running commands. Claude Code proposes something radically different — an agent that lives in the terminal, takes over execution based on your intent, and closes the loop on its own between reading code, modifying it across multiple files simultaneously, and running the tests.

The AI Professor bar that appears in the lesson under the selected passage, with the actions “Explain this to me”, “Give me an example”, “Why does it matter?” and “My own question”
The first lines of lesson 1 of this course. Read the free preview, no account needed.

  1. You read the lesson at your own pace

    Written lessons, with examples and exercises. Your progress is saved automatically, so you can pick up where you left off.

  2. You ask the AI Professor inside the lesson

    Select a passage and it explains it, gives you an example or tells you why it matters. You can type or talk to it, in English.

  3. You check what you remember

    Every lesson has its own quiz, with explanations for the answers: 382 questions across the course. The professor also summarizes the lesson and prepares review flashcards.

  4. You get the Certificate of Completion

    Once you complete the lessons and reach the minimum quiz score, you issue it from your account, with a unique number, publicly verifiable.

The AI Professor is included in your subscription, per-course access included, with a monthly fair-use limit. It is an AI system, not a human teacher, and its answers may contain errors; details in the Terms. See how the AI Professor works.

You leave with proof anyone can check

The Certificate of Completion for “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 on the public verification page, with no account and no cost.

Example of a Cursuri AI Certificate of Completion with sample data: the serial number and the issue date in the top-right corner, the holder’s name, the course, the tier awarded, the percentage of lessons, the average score, the study time, the course version, the issuer and the verification QR code
The real document, an A4 PDF, shown here with sample data. Yours carries your name, the course “Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)”, the serial number, the issue date and the tier you earned; the QR code in the image is decorative.

  • Anyone can verify it

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

  • You show it where it counts

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

  • It says exactly what it attests

    The course, the tier you earned (Pass, Merit or Distinction), the serial number and the issue date, plus the percentage of lessons completed.

Verify a certificate

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.

Pricing

Just this course, or more with this one included

A subscription by number of courses: 1, 3, 5, 10, 15 or 25 courses a month, or the full catalog. You pick them and can change them at every renewal; your progress and certificates stay. Billed monthly or yearly (12 months for the price of 10), in EUR. You can stop the renewal anytime from your account, and access starts right after payment. Prices are totals, with VAT included at the rate of your country.

How many courses a month?

This course goes first on your list; you pick the others in your account and can change them at every renewal.

Billing period
  1. 1 course Only this course

    €99 a course

    €99a month €990a year, 12 months of access

    Choose 1 course Choose 1 course
  2. 3 courses This one + 2 of your choice

    under €67 a course

    €199a month €1,990a year, 12 months of access

    Choose 3 courses Choose 3 courses
  3. 5 courses This one + 4 of your choice

    under €52 a course

    €259a month €2,590a year, 12 months of access

    Choose 5 courses Choose 5 courses
  4. 10 courses Recommended This one + 9 of your choice

    under €32 a course

    €319a month €3,190a year, 12 months of access

    Choose 10 courses Choose 10 courses
  5. 15 courses This one + 14 of your choice

    under €24 a course

    €359a month €3,590a year, 12 months of access

    Choose 15 courses Choose 15 courses
  6. 25 courses This one + 24 of your choice

    under €16 a course

    €399a month €3,990a year, 12 months of access

    Choose 25 courses Choose 25 courses
  7. Full catalog Nothing to pick, new courses included

    under €10 a course, across all 50

    €499a month €4,990a year, 12 months of access

    Choose full catalog Choose full catalog

Total prices, VAT included. Move up anytime and pay only the difference for the days left; move down at renewal. Renews automatically, you stop it anytime from your account; your progress and certificates stay. Digital content with immediate access: see the withdrawal terms.

Buying for a team?A team library: you pick the courses for everyone, priced per member, from €345 a month + VAT, with a company invoice and a progress report for every team member. Buying for someone else?Give one month of access to this course: a one-time payment of €99, a code by email, no subscription.

Compare all the subscriptions in detail

Before you decide

Frequently asked questions

About the course, the price, the AI Professor and the certificate.

What will I learn in “Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)”?

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 5.1, Opus 5.5, Sonnet 5 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 5.1, for Claude Opus 5.5, and for Claude Sonnet 5.

The course has 11 modules and 28 lessons, with 382 quiz questions. The full curriculum, module by module, is shown on the course page.

Do I need prior experience for this course?

Yes. The course is Advanced level and assumes hands-on experience with AI in its field.

How long does the course take?

The estimated duration is about 25 hours, across 28 lessons. You learn at your own pace, and your progress is saved automatically at every lesson, so you can pick up where you left off.

How much does it cost, and which plan do I need?

This course alone: the 1 course plan, €99 per month. The course fits into every plan of the subscription, next to other courses you choose: for example 3 courses for €199, 10 courses for €319 (recommended) or the full catalog for €499 per month.

You pick your courses after paying and can change them at every renewal; starting from here, this one is already picked. Plans are billed in EUR, monthly or yearly (pay for 10 months, get 12). Every price is a total, with VAT included at the rate of your country. See all plans.

Can I read part of the course before paying?

Yes. You can read a free preview of lesson 1, “Agent-First vs IDE-First: Why Agentic Coding from the Terminal Changes the Rules of the Game”, without an account. The preview shows you how the lesson is written; the rest of the lesson and the other lessons open after payment.

How does the AI Professor help me in this course?

The AI Professor is built into every lesson and starts from the lesson you have open: it explains the passages you select, gives you examples, summarizes the lesson, tests you with a quiz and prepares review flashcards. You can type or talk to it, in English.

It is included in every plan of your subscription, with a fair-use limit. It is an AI system, not a human teacher, and its answers may contain errors; details in the Terms.

Do I get a certificate when I finish the course?

When you meet the completion thresholds shown on the platform (lessons completed and the minimum quiz score), you can issue your Certificate of Completion for “Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)” from your account, with a unique number, publicly verifiable on the site.

It is a private attestation of course completion, issued by GALIAN SOFTWARE DEVELOPMENT SRL. 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. Details in the Certification policy.

Does the subscription renew automatically? How do I stop it?

Yes. The subscription renews automatically at the end of each monthly billing period. You can see the next renewal date in your account at any time.

You can stop the renewal at any time, from your account or by email, with no other formality. Access stays active until the end of the period already paid for, and no pro-rata refund is made for a period already started, except in the cases provided by law. Your progress stays saved in your account. Details in the Terms & Conditions, section 5.5.

Can my company buy this course for a team?

Yes. With the team library, the company admin picks 3, 5, 10, 15 or 25 courses a month, or the full catalog, for the whole team, from €49 per member per month, excl. VAT, for 5 members or more. A dashboard shows each member’s progress and manages seats centrally. Price it for your team.

From the same track

Similar courses

You can pick them together with this one in a 3, 5 or 10-course subscription (3 courses for €199 a month), and the full catalog includes them all. A single course is €99 a month.

All courses in AI for Developers Browse all 50 courses

Start the course today, at your own pace

“Claude Code Mastery: Agentic Coding from the Terminal (multi-file, git, CI, MCP)”: 28 lessons and about 25 hours of content, with your progress saved at every lesson.

  • Instant access after payment, on computer, tablet or phone.
  • AI Professor in every lesson, included in your subscription.
  • Certificate of Completion, publicly verifiable.

1-course subscription

€99/month

VAT included · stop the renewal anytime from your account

Start the course · €99/month Or 3 courses for €199/month, this one included

Still deciding?Check before you pay.

ChatGPT, OpenAI, Claude, Anthropic, Gemini, Google, Microsoft 365 Copilot, Cursor, Midjourney and the other product and company names mentioned are trademarks or trade names of their respective owners. Cursuri-AI.ro is an independent training provider and is not affiliated with, sponsored by or endorsed by any of them.