Claude Code

An agentic coding assistant in your terminal.

Claude Code is taught here in 13 lessons, running from Installing and configuring Claude Code through to Building your own agent with the Agent SDK. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. Installing and configuring Claude CodeGet the terminal agent running, give it project instructions it will actually follow, and set permissions before you need them.
2. A typical editing workflowExplore, plan, edit, verify: the loop that keeps an agent session short, reviewable and cheap.
3. Permissions and safety with agentsPermission modes, why deny rules matter more than instructions, and the specific risks of an agent that can run shell commands.
4. Managing the context window and session hygieneWhat loads automatically, why a long session gets worse rather than just slower, and when to compact, clear or start fresh.
5. Slash commands and reusable promptsTurn the prompts you type every day into files under .claude/commands, with arguments, allowed tools and a pinned model.
6. Scoped instructions: memory, rules and path-specific contextLayer CLAUDE.md from user to project to directory, scope rules by path, and understand why editing instructions mid-session changes nothing.
7. Subagents and context isolationDelegate a search or a review to an agent with its own context window and a restricted tool set, and get a summary back instead of a transcript.
8. Hooks and deterministic automationRun your own commands at lifecycle events, block a dangerous tool call with an exit code, and format every edited file without asking the model.
9. Connecting external tools with MCP serversAdd local and remote Model Context Protocol servers, control who can see them, and understand the context and trust cost of every tool you enable.
10. Skills, plugins and marketplacesPackage procedural knowledge as a skill that loads only when relevant, then bundle skills, agents and hooks into a plugin your team can install.
11. Headless mode, scripts and CI automationRun the agent non-interactively, parse its JSON output, gate a pipeline on exit codes, and keep CI permissions tighter than your laptop's.
12. Cost, model choice and troubleshootingPick the right model per task, see where tokens actually go, and diagnose the two failure modes that waste the most time: loops and confident bad edits.
13. Building your own agent with the Agent SDKDrive the agent loop from your own code: define tools, control permissions programmatically, and decide when building beats shelling out to the CLI.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow PyTorch Natural Language Processing LangChain Ollama OpenCV Codex OpenCode Vibe Coding Selenium Playwright

FAQ