Claude Code 101: Concept Map
How the ideas from the course fit together: one agent, one loop, one context window, and a set of ways to shape what goes into it.
Claude Code 101 at a Glance
Claude Code is an AI agent: software that interacts with its environment and acts to reach a goal, using an LLM that runs in a loop with tools.
How Everything Plugs into the Agentic Loop
The loop is the engine. Every other concept either feeds the context, provides tools, gates actions or runs work in a separate context. Hover or tap a box, or switch to the kitchen view to see the same ideas as a restaurant kitchen.
From Prompt to Response: Under the Hood
Who talks to whom, in order, from the moment the user presses Enter to the response. This is a simplified view: solid arrows are calls, dashed arrows are replies, and boxes mark parts that repeat (loop), happen only sometimes (opt) or branch (alt). Hover or tap a step.
What Lives in the Context Window
The context window is Claude's working memory. Everything you type, every file it reads and every tool result adds to it. The proportions below are illustrative, not measured.
Main Session
- CLAUDE.mdAlways loaded, every session
- Skill descriptionsOnly name and description until a skill is used
- MCP tool definitionsAlways loaded, even when unused. Above 10%, Claude switches to tool search
- Conversation + tool resultsGrows with every prompt, file read and command
- Subagent summaryThe only thing a subagent brings back
- Free spaceWhen it runs out, auto-compaction kicks in
/context
Inspect. Shows the size and what takes the most space. Nothing changes.
/compact
Summarize. Keeps a memory of the work so far and frees space. Use it to keep going on the same feature. Details may be lost.
/clear
Start fresh. Removes the conversation, so it can't bias a new feature. Anything Claude should remember belongs in CLAUDE.md.
- 💡 Be specific: vague prompts cost more exploration
- 💡 Disable unused MCP servers (
/mcp) - 💡 Prefer a Skill or a CLI (
gh,aws) over always-loaded MCP tools - 💡 Delegate research to subagents
Explore → Plan → Code → Commit
The daily workflow, with the concepts you use at each stage.
Explore
Give Claude the relevant context.
- Plan mode
- explore subagent
- CLAUDE.md
- web search
Plan
Agree on the steps and what "correct" looks like.
- Plan mode
- plan subagent
- clarifying questions
- success criteria
Code
Approve the plan, then iterate until it works.
- permission mode
- agentic loop
- test suite
- tools / MCP
- hooks
Commit
Review the diff, get a second opinion, then ship.
/diff/code-review(clean context)/rewind- commit message
Choosing the Right Customization
| What It Is | When It Loads | Context Cost | Guaranteed? | Where It Lives | Best For | |
|---|---|---|---|---|---|---|
| CLAUDE.md | Markdown onboarding notes added to your prompt | Every session, automatically | Always present, so keep it compact | No, guidance |
| Project facts, conventions, repeated corrections |
| Skill | Folder with a SKILL.md, plus scripts and resources | When its description matches your request | Name and description only, until used | No, guidance |
| Task-specific know-how: review checklist, commit format, brand guide |
| Subagent | Separate agent with its own system prompt and context window | When Claude delegates a task | Only the summary it returns | No |
| Exploration, research, clean-context review |
| MCP | Open standard connecting external tools and data | Tool definitions load up front | High: every tool definition, even unused ones | No |
| Context outside the codebase: issue trackers, databases, apps |
| Hook | Command that runs on a lifecycle event | On its event: PreToolUse, PostToolUse, Stop, … | None | Yes, deterministic |
| Must-happen rules: format, log, block rm -rf |