quickstart

An interactive first-run walkthrough for setting up and using the Claude Code Starter Kit. It checks whether the shared configuration is installed before asking about the project and preferred profile.

In plain words
What is it for?
Use it to check global configuration, choose a project name and profile, and start the starter kit setup.
Why use it?
It helps new users complete the initial setup in the right order and gives next steps based on the current state.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/thedecipherist/claude-code-mastery-project-starter-kit/quickstart
Clone the repo
git clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kit

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.01024
Opus 5 $0.00003 $0.00512
Sonnet 5 $0.00001 $0.00205
Haiku 4.5 $0.00001 $0.00102

Measured 2d ago against content hash 603947858303, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quickstart scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/quickstart.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quickstart — First-Run Walkthrough

Guide the user through their first experience with the Claude Code Starter Kit. This is an interactive walkthrough — ask questions, check state, and give personalized next steps.

Step 1 — Check Global Config

ls ~/.claude/CLAUDE.md 2>/dev/null && echo "GLOBAL_CONFIG=installed" || echo "GLOBAL_CONFIG=missing"

If GLOBAL_CONFIG=missing:

Tell the user:

Your global Claude config isn't installed yet. This is a one-time setup that adds
security rules and hooks across ALL your projects.

Run: /install-global

This smart-merges into your existing ~/.claude/ config — it never overwrites.
Come back to /quickstart after it's done.

Stop here if global config is missing. Don't proceed until they install it.

If GLOBAL_CONFIG=installed, continue to Step 2.

Step 2 — Ask Project Details

Ask the user:

Question 1: "What do you want to name your project?"

Validate: lowercase letters, numbers, and hyphens only. No spaces, no uppercase. Show an example: my-awesome-app

Question 2: "Which profile do you want to use?"

Options:

  • clean — All Claude AI tools (commands, hooks, skills) with zero coding opinions. You pick your own language, framework, and structure. Best for: experienced developers who want Claude's tooling without opinionated scaffolding.
  • default — Full opinionated stack: Next.js, TypeScript, MongoDB, Tailwind, Docker, CI, Rybbit analytics, Playwright tests. Best for: new projects that want everything pre-configured.
  • go — Go project with standard layout (cmd/internal/), Gin router, golangci-lint, Makefile builds, and multi-stage Docker. Best for: developers who prefer Go over Node.js.
  • vue — Vue 3 SPA with Composition API, Tailwind, Vite. Best for: Vue developers building SPAs.
  • nuxt — Nuxt full-stack with auto-imports, SSR, MongoDB, Docker. Best for: Vue developers who need SSR.
  • svelte — Svelte SPA with Tailwind, Vite. Best for: developers who prefer compiled frameworks.
  • sveltekit — SvelteKit full-stack with SSR, MongoDB, Docker. Best for: Svelte developers who need SSR + API routes.
  • angular — Angular standalone components with Tailwind. Best for: enterprise Angular teams.
  • python-api — FastAPI with PostgreSQL, Docker. Best for: Python API developers.
  • django — Django full-stack with PostgreSQL, Docker. Best for: Python web developers.
  • flask — Flask API with PostgreSQL, Docker. Best for: lightweight Python APIs.

Read the full file on GitHub · 106 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 106 lines · 7 tokens per session scan A 603947858303

Subscribe to this mod's changes

quickstart is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 1,024 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.