The 15-minute Claude Code setup

Four files. Five of the fifteen minutes are one step, and skipping it is the difference between a setup and a template.

Last updated: 2026-09-21 · checked against Claude Code 2.1.278

The clock

Four files, fifteen minutes, and one of those steps is the whole job. The other three are typing.

MinStepSkippable?
0–2npm install -g @anthropic-ai/claude-code, then run claude once in your repo to sign inNo
2–5Copy CLAUDE.md, .claude/ and .mcp.json.example into your repo rootNo
5–10Fill in your four commands and your never-do list in CLAUDE.mdThis is the step. Skip it and you have a template, not a setup
10–12Edit permissions.allow to match your real test and lint commandsYes, but the prompts continue
12–15Run claude, then your ship-check skill. It should run tests and lint and report PASS/FAILNo — this is the only proof the rest worked

Minute 5 to 10: the only step that matters

Claude Code starts every session knowing nothing about your repo. CLAUDE.md is what it reads first, every time. Most people write an essay here; the essay is what makes it useless.

Four commands and a short list of things not to do beats three paragraphs of architecture:

# My Project

## Commands
- install: `pnpm install`
- dev: `pnpm dev`
- test: `pnpm test`
- lint: `pnpm lint --fix`

## Layout
- `src/` app code · `src/db/` migrations, hand-written · `e2e/` Playwright

## Never
- Never edit anything in `src/generated/`
- Never commit to `main`; branch first
- Migrations are forward-only. No editing an applied one

If you only ever do one thing from this page, write the four commands. Everything downstream — the allowlist, the skills, the checks — is about commands Claude already knows how to run.

Minute 10 to 12: why it stops asking

Approving a command approves that run. It is not remembered, which is why you can approve npm test forty times and be asked a forty-first. The allowlist is what makes it stop:

{
  "permissions": {
    "allow": [
      "Bash(git status)",
      "Bash(git diff:*)",
      "Bash(npm test:*)",
      "Bash(npm run lint:*)"
    ],
    "deny": [
      "Bash(rm -rf:*)",
      "Bash(git push --force:*)",
      "Read(./.env*)"
    ]
  }
}

The detail that catches everyone: Bash(npm test) matches that exact string, so npm test -- --watch still prompts. Bash(npm test:*) covers the arguments too.

Do not allow everything. The point of an allowlist is that you can stop reading the prompts, and that is only safe while the prompts you would want to read still appear. Allow the boring repeated read-only things. Leave deletes, force-pushes and anything that reads .env out.

More detail, including the three reasons a rule silently does not match: Claude Code keeps asking permission.

What you do not need in the first fifteen minutes

Four words get treated as one thing. They are not, and three of them can wait:

ThingDay one?Why
A skillYes, oneIt is a SKILL.md and it is also the slash command. Start with a ship-check
HooksNot yetUseful once you know what should be enforced rather than requested. They also fail quietly
An MCP serverOnly if neededOnly for reaching something outside your machine. Words cannot query your database
A pluginNoPlugins are about handing a setup to other people. Nothing to package on day one

Which is which, and the one question that picks between each pair: plugin, skill, subagent, hook or MCP server.

Two things that will waste your afternoon

1. You do not need to restart

Claude Code watches the settings files, so an edit to permissions or hooks is picked up without restarting the session. If a change seems not to have landed, the configuration is usually wrong rather than stale. claude --debug hooks will tell you which.

2. A hook that fails tells you nothing

Hook stderr goes to the debug log and never to the transcript, so a hook that crashes on line one looks exactly like a hook that was never wired up. And it takes exit 2 to block a tool call — exit 1 is a non-blocking error, so the Unix reflex produces a hook that complains and then allows the thing anyway. Full list: hooks are configured but never run.

Copy a working one

All four files, filled in, MIT, nothing held back — kit-claude-code-starter. Clone it, copy three paths, and you are at minute 5 with the only step that matters left to do.

git clone https://github.com/sdvsignal/kit-claude-code-starter
cp -r kit-claude-code-starter/{CLAUDE.md,.claude,.mcp.json.example} your-repo/
cd your-repo && claude
Free starter repo

There is no paid tier of that repo and nothing is withheld from it. If you already know your build commands, this page plus that clone is the whole job. Fifteen minutes gets it installed; proving it actually fires is a separate sitting.

What does it cost to have someone set this up?

Flat prices, written scope, stop at any rung. No call to book, no retainer.

RungWhat you getClock
Free — starter repoA real setup you copy yourselfnow
$29 — Setup LiteOne project: CLAUDE.md, allowlist, one skill, as a pull request you review24 hours
$99 — Setup Sprint3–5 skills, hooks, up to 3 MCP servers, plus a runbook48 hours
$79 — Surface AuditAlready set up and still fighting it: contradictions and an exact fix list48 hours
Setup Lite $29 Surface Audit $79 Setup Sprint $99 Or start free

Hooks and MCP servers are in Sprint, not Lite — which one you actually need. Clocks run from a complete intake, not from the Stripe receipt.