Course Overview
Great software no longer has to cost a fortune or consume every hour of your day. With Claude Code, you get an engineering partner that plans, builds, tests, and ships alongside you at a fraction of the time and cost. This isn't about prompting an AI. It's about designing systems that multiply what you can deliver.
Welcome to the new standard.
Agentic software engineering is a discipline shift, and once you experience it, there's no going back. Instead of spending days on tasks that take agents minutes, you orchestrate workflows that reduce cost, eliminate repetition, and scale your output without scaling your team. The developers who master this don't just move faster. They do more with less, and they do it consistently.
Across 14 hands-on modules, you'll go from Claude Code fundamentals to production-grade multi-agent pipelines. You'll design composable skills, build MCP tools that connect agents to real systems, extend and customize the harness with mods, architect parallel sub-agent workflows, and harden everything for real-world conditions. Every module is built around genuine engineering decisions, because the goal was never to write more code. It was always to build software that matters.
The class also covers everything required to pass the Claude Certified Architect: Foundations certification. Every exam area, from the CLAUDE.md constitution and the permission model through skills, MCP, sub-agents and security, is taught in a module and practiced in its lab. Work through the 14 modules and you are prepared for the exam without any separate study track. Still we want to point out that this is not a dedicated exam prep class.
The course price includes a 1-month Claude Max 5x membership.
Who should attend
Software Architects, Developer (All)
Prerequisites
The exercises will be conducted in Python, TypeScript, and C#. Basic knowledge of these programming languages is helpful but not required.
Course Content
Module 1: Claude Code Fundamentals
- Introduction to Claude Code
- Setup & Installation
- Editors: Console, Desktop App, VS Code
- Model Selection Strategy
- Prompt caching, cost and token awareness
- Permission Model: Tools, Bash, Network
- Checkpoints & Session Safety
- Git worktrees: isolated checkouts
- Agents view: background sessions
- Artifacts: results as shareable pages
Module 2: Claude Code Configure Harness
- Settings Hierarchy: Global, Project, Session
- CLAUDE.md constitution
- @-mentioning files and URLs
- Slash Commands
- MCP Servers & Tools
- Skill folders and their sources
- Sub-agents under `.claude/agents/`
- Hooks: PreToolUse, PostToolUse, Stop
- Mods: extend and customize the harness
- Auto-memory: MEMORY.md index, four typed files
Module 3: Creating & Managing Skills
- Skills vs. slash commands
- Invocation model, anatomy, body structure
- Authoring manually or from conversation
- Front matter fields
- Allowed-tools restrictions and metadata conventions
- Composite skills: scripts, references, assets
- Cross-skill references and delegation patterns
- Dynamic context injection: command preprocessing
- Forked execution: agent and background
- Testing: Trigger, correctness, performance
- Distribution: portable folder, skills API, hosting
Module 4: Consuming & Designing MCP Tools
- MCP architecture: servers, clients, transports
- Session lifecycle and exposed capabilities
- Remote auth: tokens, keys, OAuth
- Building a server in C#
- Inspection with the MCP Inspector
- MCP Apps: interfaces inside the host
- Artifact connectors calling MCP live
- Tool design: granularity, descriptions, resources
- Error and deferred-loading contract
Module 5: Agentic CLI & Headless Execution
- Agent harness: tools, knowledge, action interfaces
- CLI, terminal, and headless mode
- Headless mode: print, JSON, exit codes
- Least-privilege tool scoping
- CI gates: sentinels and exit codes
- GitHub Actions: scripting agentic workflows
- Parallel worktree lanes and task-queue orchestration
- PreToolUse policy gates across lanes
- Always-on goal patterns with turn limits
Module 6: Sub-Agents
- Where single-agent sequential hits a ceiling
- Frontmatter: name, model, tools, permission mode
- Restricting tools and permissions per agent
- Backend agent: .NET and Learn MCP
- Frontend agent: Angular and DevTools MCPs
- QA agent: Playwright, no implementation authority
- Evaluating performance with test cases
- Orchestration: prompt delegation, loops, workflow graphs
- Context isolation between parallel agents
Module 7: Agent Teams
- Where a team beats sub-agents
- Lead, teammates, shared task list, mailbox
- Enabling teams and session state
- Spawning teammates: names and models
- Display modes, agent panel, steering keys
- Task states, dependencies, file-locked claiming
- Messaging between lead and teammates
- Competing hypotheses: teammates disproving each other
- Plan approval and lifecycle hooks
- Team sizing, conflicts, and cost
Module 8: Optimizing the Agentic Harness & Continuous Learning
- Skills and agents as living artifacts
- Autoresearch loop: propose, evaluate, revert
- Deterministic experiments for skill quality
- Caveman skill: 60-75% output compression
- Compressing CLAUDE.md with caveman-mode
- Memory architectures: statefile and graph
- Updating harness from observed behavior
- Metrics: determinism, output structure, abort rate
Module 9: Security, Hardening & Observability
- Prompt injection: tool results and files
- Tool poisoning: validating MCP responses
- Untrusted content isolation in agent context
- Guardrails: hard stops and scope constraints
- Least privilege scoping per sub-agent
- Secrets: preventing cross-agent credential leakage
- Tracing tool chains and cost attribution
- Diagnosing stuck, runaway, hallucinating agents
- Artifact governance: toggles, retention, audit events
Module 10: Bundling & Distributing Plugins
- Plugins vs. standalone configuration: namespacing
- Plugin anatomy: manifest, skills, hooks, MCP
- Bundling skills, hooks, MCP configs
- LSP servers and background monitors
- Default agent activation via plugin settings
- Local testing: plugin directory and reload
- Converting `.claude/` configs into plugins
- Publishing to official and team marketplaces
- Plugins by Anthropic
Module 11: Agentic DevOps & Deployment
- The deployment sub-agent: allowlists, prove-it contract
- Bootstrapping and hardening Ubuntu over SSH
- Docker Compose behind a Caddy edge
- DNS before the first ACME attempt
- Core Web Vitals and SEO loops
Module 12: Claude Managed Agents
- Cloud containers with network and files
- Steering agents mid-execution via SSE
- OAuth vaults and token refresh
- Callable-agent patterns with isolated threads
- Session lifecycle: idle, running, termination
- Human-in-the-loop approval gates
- Managed Agents vs. Messages API
- Versioning agents as deployable units
Module 13: Claude Code SDK
- Spawning Claude Code via the SDK
- Sessions, context, streaming responses
- Custom tools as in-process MCP servers
- Typed output with Zod
- Parallel agents: session isolation, orchestrator pattern
- Output control: tool choice and batches
Module 14: Planning & Spec-Driven Development (Optional)
- Plan Mode: mechanics and activation
- Stepwise context: questions and constraints
- Spec iteration via feedback loops
- Extended Thinking: steering reasoning chains
- Thinking budget vs. token cost
- Authoring specs and technical plans
- Decomposing tasks into sub-agent packages
- Defining and validating done criteria
- Spec Kit and BMAD-METHOD compared
English
German
Germany