It guesses instead of asking
You ask for a login and it builds an entire auth framework. Vanilla agents assume what you meant and run with it, so you get the wrong thing fast.
A drop-in kit for Claude Code, Codex & AntigravityThe AI coding starter kit
The AI coding starter kit
that asks before it builds.
Vanilla agents guess and over-build. kitstarter makes Claude Code, Codex, and Antigravity ask the right questions, build lean, and ship a real product that doesn't look AI-made. You learn the whole workflow, from planning to deployment.
Get the kit · CA$39One-time. Installs in a minute. Works in your terminal.
voice
›
kitstarter is reading your request…
Tired of wrestling with your AI agent?
Claude Code is powerful. Getting consistent, production-quality work out of it is the frustrating part. Run it vanilla, and this is what you fight.
It forgets your project
Context runs out and the agent loses the plot. Every new session it reinvents your conventions and contradicts last week's code.
It over-builds everything
A one-line fix turns into a new dependency and forty files. You inherit code you never asked for and now have to maintain it.
It ships AI slop
Gradient buttons, emoji headings, generic copy. The output screams AI made this, and your users can tell.
You redo the same setup
Copy-pasting prompts between projects and rebuilding the same patterns, with no system that actually sticks.
It says done without checking
It calls the work finished without running the tests. You find out it is broken when your users do.
Same AI. Two completely different outcomes.
The kit doesn't swap your model. It changes how it behaves, from guessing and over-building to asking and shipping clean.
Guesses, then over-builds
- Assumes what you meant and builds the wrong thing, fast
- 40-file diffs; a library for what a line would do
- Violet gradients, generic font, looks obviously AI-made
- Says “done” without ever running it
✦ With kitstarter
Asks first, stays lean, ships clean
- ✓ Asks the right questions before it touches code
- ✓ Smallest change that actually works, no bloat
- ✓ Catches the AI-slop tells, looks intentional
- ✓ Proves it runs before it calls it done
One workflow, planning to deployment.
Your agent follows a method that ships an actual product and teaches you how it works along the way.
01
Understand
It asks the questions that matter before it writes a single line.
02
Plan
A short, real plan you approve, not a 40-file guess.
03
Build lean
One step at a time: the smallest change that actually works.
04
Prove it
Runs the tests and shows you green before it moves on.
05
Ship & deploy
Catches leaked keys, gets it live, and recovers when it breaks.
Just got Claude Code? You're building in minutes.
kitstarter doesn't hand you a manual. It asks, in plain multiple choice, and sets up the tools you actually need. You pick, it installs, you start building. No blank page, no guessing where to begin.
Which tools should I set up? Pick any, or all four.
It asks. You pick. It installs.
It wires up the essentials, all opt-in:
- exaopt-in
search the live web and pull a library's current docs.
- context7opt-in
drop a library's newest official docs straight into the agent.
- geminiopt-in
let it look at your screenshots and say whether they look right.
- crawl4aiopt-in
point it at a site and it reads the whole thing into clean text.
Add what you want, skip the rest. Each one explained as it goes in.
What's inside. Few skills, each deep.
Not 108 commands you'll never learn. The core is always on; the rest installs with one flag when you want it.
always on
The core
Ask first, be direct. The always-on rule, plus the setup wizard.
- /start
- /tour
- the AGENTS.md rule
- session greeting
Build cleanly
One step at a time, prove it works, cut the over-built code.
- /step
- /check
- /fix
- /review
- /lean
the method
Loop engineering
Tight build → run → fix loops that converge on working code, instead of one giant guess.
- /ks-loop
- /ks-iterate
- the build-prove cycle
Ship & survive
Get it live, catch leaked keys, and recover when it breaks.
- /ship
- /secrets
- /recover
- /explain
37-tell detector
Don't look AI-made
A real detector for the tells that scream “AI generated this”, and the skills to fix them.
- /design-intake
- /design-check
- /polish
Reach further
Web, search, and live docs (crawl4ai + exa), plus the Claude Code you're not using.
- /connect-mcp
- /claude-tips
opt-in
Voices
Switch to a teaching or buddy tone when you want it. Default stays direct.
- teaching
- buddy
18 skills.
One that matters most: it asks.
One that matters most: it asks.
Drop it into Claude Code, Codex, or Antigravity. The rule works everywhere; the skills + hooks run in Claude Code today.
Get the kit · CA$39If you build with AI, this is for you.
Whether you're just starting, leveling up, or building for your business, kitstarter meets you where you are.
You're new to code, vibe-coding your way in
New to building with AI? The kit makes the agent ask what you don't know to ask, and the 1:1 coaching gets you up to speed fast.
Get 1:1 coaching
You code the traditional way
You write code by hand and want to level up with AI agents. The kit shows you how to direct one well, and how the modern build workflow actually works.
Level up your skills
You run a business, not a codebase
You're a non-technical founder or owner who wants to build for your business. The kit keeps the agent on rails so what you ship actually works.
Build for your businessOne-time. Yours forever.
The guides are free. The kit is a single payment, no subscription.
The kit
CA$39once
Everything you need to make your agent ask first and build clean.
- ✓ All 18 skills plus the 37-tell slop detector
- ✓ Auto hooks: anti-slop, safety, the greeting
- ✓ Teaching, simple, and technical voices
- ✓ Lifetime updates as Claude Code moves
Full refund if it doesn't calm your builds.
✦ Get unstuck faster
The kit + coaching
CA$79once
The kit, plus a human in your corner when you get stuck.
- ✓ Everything in the kit
- ✓ A 1:1 AI coaching session, tailored to you
- ✓ Premium priority support
- ✓ Early access to new skills
Best if you want help going from zero to shipping.
Prices shown in your region's currency. You are charged in your local currency at checkout.
Questions, answered.
What is kitstarter?
kitstarter is a one-time kit of Claude Code skills that makes your AI coding agent ask clarifying questions before it builds, stay lean, and stop looking AI-made. It works with Claude Code, Codex, and Antigravity, and installs with one command: npx kitstarter-cli.
How do I make Claude Code ask questions before it writes code?
Install kitstarter with npx kitstarter-cli. Its always-on rule makes the agent ask the questions that matter before it touches code, instead of guessing what you meant and over-building.
Does kitstarter work with Codex, Cursor, or Antigravity?
The ask-first rule works in any agent that reads AGENTS.md, including Codex and Antigravity. The full skills, the slop detector, and the hooks run in Claude Code today.
How much does kitstarter cost?
It is a one-time payment, no subscription: CA$39 for the kit (all skills, the slop detector, hooks, voices, and lifetime updates), or CA$79 for the kit plus a 1:1 AI coaching session and premium support.
How do I install kitstarter?
One command in any project: npx kitstarter-cli. Use npx kitstarter-cli --full for everything, or npx kitstarter-cli -g --full to install it globally for every project.
What is AI slop, and how does kitstarter stop it?
AI slop is output that screams that AI made it: gradient buttons, emoji headings, generic copy, over-built code. kitstarter ships a 37-tell detector and design skills that catch those patterns so your work looks intentional.
How is kitstarter different from other AI agent kits?
Those kits sell more agents and skills. kitstarter changes how your agent behaves: it asks before it builds, writes the smallest thing that works, proves it runs, and stops the output looking AI-made. It is about behavior and craft, not volume.