The Claude Guide · 19 concepts · each with a concept film

Claude Guide

How Claude Code actually works, one concept at a time. Every concept has a short film you can scrub through, and every fact is checked against the official docs.

Start anywhere · these need nothing first

Context Slash Commands Checkpoints Claude Code in the cloud

How it works

The loop, the context window, and the tools Claude Code acts through.

Beginner · film · start here Context The context window is everything Claude can see in a session: your messages, the files it reads, tool output and auto-loaded instructions. It fills as you work, and Claude Code compacts it when it gets full. Beginner · film · 1 first Models & Effort The two dials behind every answer: which Claude model does the work, and how much effort it spends thinking and checking before it replies, trading speed and tokens for depth. Intermediate · film · 1 first Goals (/goal) Give /goal a completion condition and Claude keeps taking turns toward it, while a separate small model checks after every turn whether the condition is met. Intermediate · film · 1 first Prompt Caching Claude Code re-sends your whole conversation on every turn. Prompt caching lets the API reuse the unchanged start of it, so long sessions stay fast and cheap until something breaks that prefix.

Instructions & memory

Telling Claude Code how you work, once, so it remembers.

Beginner · film · start here Slash Commands Type / to run a command: built-ins that control the Claude Code session itself, plus prompts packaged as skills, plugin commands and MCP prompts, including ones you write yourself. Beginner · film · 1 first Memory CLAUDE.md files you write and auto memory notes Claude writes for itself: plain markdown on disk, loaded at the start of every session so Claude doesn't start from zero. Intermediate · film · 3 first Skills A SKILL.md file of instructions that Claude loads only when a task calls for it, or that you run yourself as a /command. Custom slash commands are now skills.

Extend it

New tools, automatic guardrails, and shareable bundles.

Intermediate · film · 1 first Hooks Your own commands that Claude Code runs automatically at fixed points in its loop, so a rule always holds instead of depending on the model remembering it. Intermediate · film · 1 first MCP The Model Context Protocol connects Claude Code to outside tools and data, such as an issue tracker, a database or Figma, through servers that hand Claude new tools to call. Advanced · film · 6 first Plugins A directory of skills, subagents, hooks and MCP servers that Claude Code installs and loads as one unit, usually from a marketplace, so a whole setup can be shared with one command. Advanced · film · 7 first Mods Plugins whose JavaScript or TypeScript functions run inside Claude Code on its events, so they can watch, rewrite or answer a tool call or prompt, add commands, and draw their own interface.

Delegate

Handing work to other agents with their own context.

Intermediate · film · 1 first Subagents Helpers Claude hands a side task to. Each works in its own fresh context window with its own prompt and tools, and only its summary comes back. Intermediate · film · 1 first Worktrees A separate git checkout for each Claude Code session or subagent, with its own files and branch, so parallel work never edits the same files. Advanced · film · 2 first Dynamic Workflows A JavaScript script Claude writes to orchestrate dozens of subagents at once and cross-check their results, run in the background and saved as a command you can rerun.

Stay in control

Undo, permissions, and keeping changes reviewable.

Beginner · film · start here Checkpoints Claude Code snapshots your code before every prompt, so you can rewind Claude's file edits, the conversation, or both with /rewind or a double Esc. Beginner · film · 1 first Permissions How Claude Code decides whether a tool call runs, asks you first, or is blocked: a permission mode sets the baseline, and allow, ask and deny rules carve out exceptions. Advanced · film · 2 first Sandboxing An operating-system boundary around the shell commands Claude runs: they can write only where you allow and reach only the domains you approve, so you can approve fewer commands by hand.

Where it runs

Terminal, IDE, web and the other places Claude Code works.

Beginner · film · start here Claude Code in the cloud Claude Code sessions that run in an isolated cloud VM instead of on your machine. Start one from claude.ai/code, your phone or the terminal, then review the branch it pushes. Advanced · film · 1 first Run it programmatically Run Claude Code with nobody at the keyboard: claude -p for scripts and CI, or the Agent SDK to drive the same agent loop, tools and context handling from your own Python or TypeScript code.

How this guide stays accurate

Claude Code changes quickly. Every concept cites the official documentation it was checked against, shows when it was last verified, and carries a review date: once that date passes, this site refuses to build until the concept is re-checked. Most recent verification: 2026-10-01.

Want the ideas underneath, like context windows, tool use and agents? They're in the Field Guide.