Class Details
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 is 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. Tasks that cost you days take agents minutes, so you orchestrate workflows that reduce cost, eliminate repetition, and scale your output without scaling your team. The developers who master this move faster and do more with less, and they do it consistently.
Across 11 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 is 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 11 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.
Audience
- Software engineers who want to move from prompting an AI to designing agentic engineering systems
- Tech leads and architects introducing Claude Code across a team and setting the harness conventions
- DevOps and platform engineers automating CI, deployments and infrastructure with headless agents
- Developers preparing for the Claude Certified Architect: Foundations certification
Prerequisites
- Comfortable with at least one programming language (labs use Python, C#, Angular and React)
- Confident on the command line and with Git, including branches and worktrees
- Basic understanding of REST APIs and JSON
- Nice to have, not required: familiarity with containers and SSH for the DevOps and deployment modules
- Nice to have, not required: a Claude Code installation with an active Claude account (a GitHub Codespace / DevContainer is provided)
Curriculum
Module 1: Claude Code Fundamentals
- Introduction to Claude Code
- Setup & Installation
- Editors: Terminal, 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
- CLAUDE.md constitution
- @-mentioning files
- 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 and disallowed-tools fields
- Composite skills: scripts, references, assets
- Cross-skill references and delegation patterns
- Dynamic context injection: command preprocessing
- Forked execution: agent and background
- Testing: triggers and measurement
- Distribution: portable folder and skills API
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: Automate Claude Code from the Command Line
- 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: Scale Task Execution with Sub-Agents and Agent Teams
- 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
- 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, and self-claiming
- Messaging between lead and teammates
- Competing hypotheses: teammates disproving each other
- Plan approval and lifecycle hooks
- Team sizing, conflicts, and cost
Module 7: Optimize, Secure and Observe the Agentic Harness
- /doctor prompt-audit: dated instructions
- Caveman Compression: shorter CLAUDE.md
- Plugin Eval: graded skill experiments
- Prompt Injection: quarantine, MCP response validation
- Hook Guardrails: PreToolUse hard stops
- OpenTelemetry: tracing, cost, failure diagnosis
Module 8: Bundle and Distribute Your Config as a Plugin
- 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 9: Agentic DevOps & Automation
- 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 10: Build and Host Agents with the Agent SDK and Managed Agents
- Agent SDK: query() and sessions
- Agent SDK: parallel agents, orchestrator
- Managed Agents: Agent, Environment, Session
- Managed Agents: files, SSE stream
- Managed Agents: vaults, versions, policies
- Managed Agents: MCP servers, skills
- Human-in-the-Loop: approval gates
- Multiagent: outcomes, memory stores
Module 11: Planning & Spec-Driven Development (Optional)
- Brownfield analysis: harvesting the current state
- Plan Mode: mechanics and activation
- Stepwise context: questions and constraints
- Spec iteration via feedback loops
- Authoring specs and technical plans
- Decomposing tasks into sub-agent packages
- Defining and validating done criteria
- Why spec-driven development
- GitHub Spec Kit pipeline
- Sample case: a feature from brief to tasks
Class Logistics
AI Harness: Bring your own