Claude Code 101

Claude Code 101

Learning notes for the Claude Code 101 course from Claude Academy.

The course introduces coding agents, setup and prompting, everyday development workflows, and project-specific customization.

Course Outline

12 lessons across four modules.

Summary

AI agent: Software that can interact with its environment and perform actions to complete a defined goal.

The agentic loop:

Diagram of the agentic loop: Your prompt flows into the loop of Gather context, Take action, and Verify results, with the ability to interrupt, steer, or add context at any point

Daily workflow: Explore → Plan → Code → Commit

  1. Explore (use explore subagent to get a general summary) and plan: use the plan mode
  2. Code
  3. Commit: Run a /code-review subagent before committing

Context management

  • Context window = the amount of space Claude can hold in its memory
  • Commands
    • Use /context to check the context state
    • Use /compact to compacts everything up to that point
    • Use /clear to removes everything
  • Save context space
    • Be specific
    • Manage MCP servers
    • Use subagents

Customization

  • CLAUDE.md: A Markdown file you add to the root of your project, and Claude Code reads it automatically every time you start a session
  • Subagent: Runs autonomously in parallel with a separate context window
  • Skill: A markdown file that teaches Claude how to do something once, and Claude applies that knowledge automatically whenever its relevant - automatic and task specific
  • Model Context Protocol (MCP): an open standard that lets Claude Code connect to external tools and data sources
  • Hooks: Give you deterministic control over Claude Code’s behavior
docs