Claude Code for Developers
Professional developers using Claude Code as an engineering tool
Prerequisites: Working developer setup (terminal, git, IDE). Module 14 not required.
Last verified 2026-07-28
Learning objectives
- Run Claude Code professionally in terminal and IDE: approval modes, plan mode, context commands
- Write and maintain a CLAUDE.md operating manual that actually changes agent behaviour
- Use subagents, custom slash commands, hooks, and skills to structure work
- Connect MCP servers and wire Claude Code into git and CI/CD workflows
- Adopt the practice loop: plan, build, test, review, capture lessons
What's in this module
5 lessons · 7 exercises · ~5 min reading
Starts withThe mental model~1 minExecutive summary
You will learn how to run Claude Code as a professional engineering tool: operating manuals, subagents, hooks, skills, MCP, and git/CI workflows. End state is a CLAUDE.md committed to your most important repo, one custom command, one MCP integration, and one real backlog item shipped through the full loop. After this module you can delegate scoped engineering work with confidence, structure agent workflows your whole team can reuse, and draw the autonomy line correctly in a shared codebase.
Sources
- Anthropic, "Claude Code overview", the documentation root, on its own site at code.claude.com: https://code.claude.com/docs/en/overview
- Anthropic, "Best practices for Claude Code", the vendor's own version of the operating manual this module teaches: https://code.claude.com/docs/en/best-practices
- Anthropic, "Common workflows", subagents, plan mode, checkpointing, and the patterns worth stealing: https://code.claude.com/docs/en/common-workflows
- Anthropic Academy: Claude Code 101, Claude Code in Action: https://anthropic.skilljar.com
- Community best practices and orchestration workflows: https://github.com/shanraisshan/claude-code-best-practice
- Curated ecosystem directory (skills, hooks, commands, orchestrators): https://github.com/hesreallyhim/awesome-claude-code
- Ruben Hassid, "Claude Code" (non-coder angle, useful for mixed groups): https://ruben.substack.com/p/claude-code
Prefer the live room?
This module also runs inside our in-person bootcamps and workshops in Copenhagen.
More in Track F
Prompt Engineering Deep Dive
The complete prompting toolkit, from structure and roles to hallucination control and complex industry prompts, plus how to measure prompt quality with evaluations.
Agent Harness Engineering
How agents actually work under the hood: the model supplies intelligence, and everything else is a harness you can build.
Agentic Futures Briefing
Where agentic engineering is heading across three horizons: what's standard practice now, what arrives within a quarter, and what's forming six months out.