Developed with Claude Code

Course Objective

This course is designed to help you progress from basic use of Claude Code to becoming a confident “agent-driven” engineer: in-depth work with context, customization for your own tech stack using MCP, hooks, and skills, building repeatable workflows for the entire team, and integration with CI/CD and issue tracking systems.

Learning Format

Online/offline/hybrid
Practical case studies, workshops, interactive sessions
Support for participants during training via a private chat

What Will Graduates Gain?

🔗 View benefits

The problem the course solves

Developers who start using Claude Code often get stuck at the “initial plateau”: they quickly solve small tasks but don’t know how to adapt the tool to their stack, don’t use MCP, hooks, and skills, and don’t know how to scale workflows to the team. The course provides a systematic transition from individual use to the engineering discipline of working with AI agents.

Prerequisites

1+ year of commercial development experience
Proficiency with Git and the CLI
Basic experience using Claude Code or another AI agent (Cursor, Copilot, Cody)
Access to your own working repository (preferably medium-sized: 50k+ lines of code)
Node.js 18+; Anthropic account

Program

Session 1. Quick Start and Core Concepts

Rapid recap: model + tools + context
Process architecture: tool use, sub-agents, side effects
Quick setup, IDE integrations, settings, OAuth, and API keys

Session 2. Context Engineering for Large Codebases

How the model indexes a project; context window limitations
CLAUDE.md across 3 levels: global / project / directory
Naming conventions and references to "sources of truth"
Using /init as a starting point, followed by manual refinement

Session 3. Permissions, Security, and Operating Modes

Plan mode, auto-edit, accept-edits
Allowlists and denylists for tools and bash commands
Working with secrets and sensitive data
Sandboxing and network access restrictions

Session 4. Slash Commands: Building a Template Library

Built-in commands: /help, /init, /review, /clear, /compact, /cost, /status
Custom slash commands: format, storage location, arguments
A template library for common team workflows

Session 5. Sub-Agents: When and Why to Use Them

Delegation concepts: explorer, planner, reviewer, tester
When sub-agents improve outcomes—and when they do not
Creating and using sub-agents

Session 6. Workflows: From Idea to Merged PR

End-to-end workflow: discover → plan → implement → test → review → merge
Working with tickets and issue trackers
Task readiness checklists

Session 7. MCP Servers: Connecting the World Around Your Code

What Model Context Protocol is and when it makes sense
Ready-to-use servers: GitHub, Jira/Linear, Slack, Postgres, Sentry
MCP configuration in Claude Code

Session 8. Hooks: Guardrails and Automation

Hook types: pre/post tool use, on stop, on session start
Use cases: linting before commits, preventing edits to specific files, Slack notifications
Best practices and anti-patterns

Session 9. Skills: Modular Agent Capabilities

The concept of skills and how they differ from slash commands and sub-agents
SKILL.md structure and automatic activation
Creating domain-specific skills (e.g., database migrations, DTO generation)

Session 10. Testing with an Agent: Beyond "Generate Unit Tests"

Coverage strategies, mutation testing, and property-based testing
Integration testing with real dependencies
Snapshot testing and E2E testing with Playwright/Cypress

Session 11. Code Review and Code Quality

Self-review templates, /review, and team checklists
Identifying security issues and language-specific review patterns
Integration with GitHub pull requests (via MCP or CI)

Session 12. CI/CD and Headless Mode

Running Claude Code in CI/CD pipelines (headless / non-interactive)
Automated fixes for Dependabot and Snyk issues
Automatic changelog and release notes generation

Session 13. Team Workflows and Impact Metrics

Distributing CLAUDE.md, slash commands, skills, and hooks through repositories
Onboarding new developers with the help of AI agents
Measuring impact: cycle time, defect rate, review time
Anti-patterns: "AI does everything", "vibe coding", and over-engineered pull requests

Session 14. Final Project: Full Integration Lifecycle

Presenting an end-to-end case: real-world problem → delivered outcome
Live coding demonstration
A 30/60/90-day adoption plan for introducing the tool into a team
Feedback and discussion

FAQ

What problem does this developer course solve?

Many developers get stuck at the basic level: they quickly solve small problems, but do not know how to adapt Claude Code to their stack. The course helps to make a systematic transition from individual use to a confident engineering discipline of working with AI agents. You will learn to distribute workflows to the whole team and use MCP, hooks and skills.

What practical Claude Code skills will I learn?

The program covers in-depth work with the context of large codebases, setting up custom slash commands and creating sub-agents. You will learn to integrate AI with CI/CD, task trackers (via MCP servers) and write your own modular skills to automate routines. The final project consolidates skills through the full cycle of integrating the tool into a real workflow.

What level of training is required to start studying?

The course is designed for specialists with 1 year or more of commercial development experience. For successful training, a confident command of Git and CLI, basic experience with AI agents (Claude Code, Cursor, Copilot), as well as access to your own working repository, preferably of medium size, are required.

How long does the training last and in what format?

Intensive training lasts 7 weeks and consists of 14 classes. The format is flexible: you can choose an online, offline or hybrid course option. The program includes practical cases, workshops, interactive sessions and constant support of participants in a closed chat. To join, just click the "Apply" button on this page.