The Cursor course

This is a hands-on course, not a reference. You’ll spend a week inside Cursor turning an inherited side project — budgetcli, a small self-hosted personal-finance API for tracking accounts, importing bank statements, and flagging overspend — into something you’d actually trust with your own money. Every chapter takes a problem you’ll really hit (auto-retrieval pins the wrong files on a big repo, the agent reintroduces the same money bug, a refactor is worth doing but not one-at-a-time) and shows the exact Cursor move that fixes it.

This course is editor-first. Cursor is a GUI-first fork of VS Code, built by Anysphere and shipped as its own desktop app — so the first-class surface here is the editor you already know, with the AI bolted onto it. That’s a deliberate inversion of the Codex and Claude Code courses, which start at the terminal: here the editor is the spine and the CLI is a chapter near the end, not the other way round. The arc runs from your first in-editor edit out to headless and CI — and by the time it gets there, the review habit you build in the first hour is the part that hasn’t changed.

If you want the spec-level “what is this primitive” view, that’s Foundations. This course is the other half: the muscle memory. Read it start to finish to build up from zero, or drop into any chapter when a specific problem is in front of you.

All chapters live

The full curriculum is written start to finish. Read it in order to build up from zero, or jump straight to the chapter you need. Lessons may still get sharpened over time.

The curriculum

Eleven chapters, in reading order. Each is a self-contained chapter that carries the budgetcli project one stretch further — start at the top, or pick the problem in front of you.

1 · Getting started Your first hour: install Cursor, migrate your VS Code setup, meet the Agent sidebar and Tab, watch one turn of the read-propose-review loop, and ship a first reviewed fix to the inherited repo.

2 · The daily edit loop The in-editor muscle that only exists because Cursor is an editor — Tab vs the Agent sidebar, inline edit with Cmd/Ctrl+K, the @-attaches / -runs split, accepting and rejecting diffs, checkpoints and restore, worn into your hands on real edits.

3 · Modes Switch posture deliberately — Ask for read-only Q&A, Plan to research then hand you an editable markdown plan, Agent for full execution, Debug as the fourth. One chord, Shift+Tab, cycles them; the skill is picking the right one before you start.

4 · Context Steer what the agent sees — @-tag files, folders, and @Docs — and learn when to lean on Cursor 2.0's self-gathering retrieval and when to hand-pin context instead, on a large inherited repo where auto-retrieval guesses wrong.

5 · Models Spend where it pays. Use the per-chat picker, let Auto route everyday work from the discounted pool, reach for a frontier model only when it earns it, and understand the billing split — the Auto+Composer pool versus the per-token API pool — before MAX Mode moves a request between them.

6 · Rules Stop Cursor reintroducing the same bugs by writing the project's standing facts down once. The four rule layers, the .mdc frontmatter and rule types, AGENTS.md as the portable plain-markdown path Cursor reads natively, the legacy .cursorrules file, and the 'globbed rule only attaches when the file enters context' sharp edge.

7 · Permissions, auto-run & the sandbox Set the blast radius deliberately. Pick an auto-run mode, lean on the Agent Sandbox as the load-bearing control, and treat the allowlist and denylist as superseded-by-design — not guarantees — once you know what replaced them.

8 · Parallel & remote agents Some work is worth doing but not one agent at a time. Fan a single prompt out to parallel agents, each walled off in its own git worktree, then review the competing results and merge the one that wins — then meet the delegated and remote flavours and when each fits.

9 · Extending: MCP, skills, commands & hooks Give the agent reach and structure — MCP servers to query systems it can't see, Agent Skills and custom slash commands to package the procedures you keep retyping — then a deterministic gate: Hooks that enforce policy whether or not the model cooperates.

10 · The CLI, headless & CI Take Cursor out of the editor. Install the CLI (the agent command; cursor-agent is the legacy alias), drive it interactively or headless with -p and the text/json/stream-json formats, authenticate with CURSOR_API_KEY, wire a budgetcli check into CI, spawn Cloud Agents over REST, and let Bugbot review every PR.

11 · Daily workflow You've learned every move Cursor makes on budgetcli. This last chapter isn't a new primitive — it's wearing them so lightly you stop reaching for them on purpose: Shift+Tab by instinct, Auto as a habit, the right surface picked before you type, and an honest look back across the editor-first to headless arc.

How to read it

Each chapter carries one running project — you’ll follow budgetcli across a week of real work — and the chapters build on each other: each one picks up a problem the last one left you with, adds a move to your repertoire, and hands off to the next. The order is deliberately editor-first: you start in the GUI where Cursor’s whole pitch lives, and only walk out to the terminal and CI once the in-editor habits are reflex.

So you get the most out of a chapter by reading it in order. But each one still stands on its own if you drop in from a search with one specific problem in front of you — you’ll just miss the running story.

What you won’t find is a fixed template stamped onto every chapter. Some need a long worked transcript, some a single setting and a warning, some a digression into why Cursor behaves the way it does. The shape follows the content, the way a good book varies its chapters.