# Cursor quick start: from install to a verified first feature

URL: https://developertoolkit.ai/en/cursor-ide/quick-start/
Description: The Cursor quick start: install, a verify command, run modes, project rules, MCP and Plan Mode, then a first feature proved by tests, not by reading the diff.

The Cursor quick start is ten short guides, about two hours in total, that take a developer from a fresh install to a first feature proved by evidence. It sets up a verify command, a run mode, project rules, and MCP, then builds a feature in Plan Mode where tests, not a line-by-line read, decide when it is done.

It is for the **developer** setting up Cursor on a real repository and the **tech lead** who commits the result for the team. In a first session the agent often edits several files, says it is done, and only your checks can tell you whether it is.

**What this hub checked**

Covers the Cursor 3.x line; the current release on 2026-10-12 is Cursor 3.24 (2026-10-09, Cursor's release notes). Cursor's docs list four agent modes (Agent, Ask, Plan and Debug) and three run modes (Auto-review, Allowlist and Run Everything), and Cursor names no single default model, all checked on 2026-10-12. Other feature names come from Cursor's docs as fetched on 2026-08-28. Every rollback works with git alone.

## What the Cursor quick start gives you

- A `verify` script (type check, lint, tests) that the agent, a hook, and CI all call.
- A run mode that runs that script unprompted and keeps `git push` behind approval, plus `.cursorignore` so the agent cannot read secrets.
- Project rules in git that every teammate's agent follows.
- One feature merged with evidence: criteria, a test per criterion, a green gate, a scoped diff.

## In what order should you set up Cursor?

Do steps 1–8 in order; take 9 and 10 when you need them.

| # | Guide | Time | Done when |
| - | ----- | ---- | --------- |
| 1 | [Install Cursor](/en/cursor-ide/quick-start/installation-setup/) | 10 min | Cursor opens your repository and the agent answers in chat |
| 2 | [Configure the agent's gate](/en/cursor-ide/quick-start/essential-configuration/) | 15 min | The agent runs `npm run verify` without an approval prompt and cannot read `.env` |
| 3 | [Choose a model](/en/cursor-ide/quick-start/model-selection/) | 10 min | You know which model runs, and change it only on evidence |
| 4 | [Write project rules](/en/cursor-ide/quick-start/project-rules/) | 10 min | Asked which rules apply, the agent names yours |
| 5 | [Plan from a PRD](/en/cursor-ide/quick-start/prd-workflow/) | 15 min | You approved a plan's acceptance criteria in Plan Mode |
| 6 | [Connect MCP servers](/en/cursor-ide/quick-start/mcp-setup/) | 10 min | The agent calls one tool from one MCP server |
| 7 | [Manage context](/en/cursor-ide/quick-start/context-management/) | 10 min | The agent reuses your canonical example |
| 8 | [Build your first feature](/en/cursor-ide/quick-start/first-feature/) | 20 min | Each criterion maps to a test that fails when the code is broken |
| 9 | [Recover from agent mistakes](/en/cursor-ide/quick-start/error-handling/) | 10 min | You have rolled back one agent change on purpose |
| 10 | [Work with git and your team](/en/cursor-ide/quick-start/collaboration/) | 15 min | Your pull request carries an evidence summary |

Step 2 comes this early on purpose: every later layer points at the verify command. For the model, start on one strong default (Cursor names no single default model, checked 2026-10-12) and switch only when your own tests show the work falls short; current names and prices are in the [models hub](/en/ecosystem/models/).

## How do you check that the Cursor setup works?

Commit a clean baseline first, so any uncommitted agent change is one `git restore .` away, plus `git clean -nd` to review new files and `git clean -fd` to delete them (or `git stash -u` to keep it all). Then run the gate yourself in a terminal at the repository root:

```bash
git status --short     # empty: nothing uncommitted before the agent starts
npm run verify         # your type check, lint and tests; must exit 0 on main
```

Fix or record a red `verify` first, or the agent "fixes" failures it did not cause. Then paste this into Cursor's agent chat:

**Copy-paste prompt: audit a fresh Cursor setup**

```text
Audit this Cursor setup before I start real work. Do not edit any file.
1. List every project rule that applies to this repository and quote the
   line in each that names a build, test, lint or type-check command.
2. Run `npm run verify` once and report the exit code and the first error
   line of any failing check.
3. Tell me whether you needed my approval to run it.
4. List the MCP servers and tools you can call.
5. Try to read .env and report exactly what happened.
Finish with `git status --short`, which must be empty.
```

The setup passes when `verify` ran unprompted, `.env` was refused, the quoted rules are yours, and `git status --short` is empty.

## How do you trust the first feature without reading every line?

The agent proves its work, and you check the proof. Write acceptance criteria before any code, paste them into Plan Mode, and approve the plan. Build one step per prompt with a commit after each, while a [Cursor hook](/en/cursor-ide/quick-start/essential-configuration/) that re-runs `verify` when the agent finishes sends failures back to it.

You sign off on the criteria, a criterion-to-test table, and the scope from `git diff --stat`; CI re-runs `verify` on the pull request. [Build your first feature](/en/cursor-ide/quick-start/first-feature/) walks through it, and [evidence, not diffs](/en/ladder/evidence-not-diffs/) explains why it scales.

**Copy-paste prompt: evidence summary for the first pull request**

```text
Write the evidence summary for this branch's pull request. Do not change code.
- Each acceptance criterion mapped to its test, and whether that test
  failed when you broke the behaviour.
- The final pass/fail line of each check in `npm run verify`.
- `git diff --stat main...HEAD`, with a reason for every file outside
  the feature and its tests.
- Anything no test covers that a reviewer must check by hand.
```

## What breaks in a first Cursor setup?

| Symptom | Likely cause | Recovery |
| ------- | ------------ | -------- |
| The agent asks before every test run | The run mode still asks for that command | Set a run mode that lets `npm run verify` run without approval ([essential configuration](/en/cursor-ide/quick-start/essential-configuration/)) |
| The agent ignores your conventions | No rule, or it never loads | Fix it with [project rules](/en/cursor-ide/quick-start/project-rules/) |
| The agent writes a new helper instead of yours | It never saw yours | `@`-mention one canonical example ([context management](/en/cursor-ide/quick-start/context-management/)) |
| Tests pass, but the feature is broken | The tests mock the broken part | Test through the real entry point ([first feature](/en/cursor-ide/quick-start/first-feature/)) |
| The agent turns a test green by editing it | Nothing forbade it | Check `git diff --stat main...HEAD -- '*.test.*' '*.spec.*'` for committed steps (drop `main...HEAD` for uncommitted edits), revert, and forbid it in a rule |
| One prompt broke many files | The step was too large | `git restore .`, then `git clean -nd` to review new files and `git clean -fd` to delete them (or `git reset --hard <last good commit>` for committed steps), then ask for a smaller step ([error recovery](/en/cursor-ide/quick-start/error-handling/)) |
| A tutorial says "YOLO mode", "Auto-Run", `.cursorrules`, or Background Agents | It predates Cursor's renames | Use Run modes (Auto-review, Allowlist, Run Everything), Rules or AGENTS.md, and Cloud Agents instead |

## Where to go next after the Cursor quick start

For the wider path, follow the [developer track](/en/start/developer/) and the [Cursor overview](/en/cursor-ide/); for other agents, see the [Claude Code](/en/claude-code/quick-start/) and [Codex](/en/codex/quick-start/) quick starts.

- [Essential configuration](/en/cursor-ide/quick-start/essential-configuration/) — Verify command, run mode, rules, hook and secret exclusions
- [Build your first feature](/en/cursor-ide/quick-start/first-feature/) — Acceptance criteria, Plan Mode, small steps and proof it works
- [Testing patterns in Cursor](/en/cursor-ide/test/testing-patterns/) — Make the tests strong enough to replace line-by-line reading
