LaunchReadyKit

How it works

From checkout to SHIP, step by step.

Pay once, install with one command, then three commands to use. Here is what you type, what happens, and every file that ends up in your project.

  1. 01

    Buy

    On this site

    Pay once: $9, no subscription. The payment is handled by Dodo Payments, which emails you a receipt with a link to your order.

    Open that link and connect your GitHub account. You are then invited to the private repository that holds the kit.

    GitHub sends the invitation by email. Accept it before you install. See the price →

  2. 02

    Install

    In your terminal

    Open your project folder and run one command. It needs Claude Code and Node 18 or newer. Then restart Claude Code.

    $ npx -y github:launchreadykit/LaunchReadyKit setup

    The repository is private, so this works once you have accepted the invitation and your terminal is signed in to GitHub.

    What it adds to your project

    • .claude/agents/41 agents, one file each
    • .claude/skills/72 skills: the checks and how to run them
    • .claude/commands/63 commands you can type

    All of them are plain markdown files you can open and edit. Nothing else in your project is touched. Add --global to install for all your projects instead.

  3. 03

    Check

    In Claude Code

    Type the launch check. It maps your project, sends the specialists your project needs, and verifies what they find. It takes several minutes and changes nothing in your code.

    > /launch-check

    What it writes

    • .launchreadykit/report.mdThe report, in plain language
    • .launchreadykit/findings.jsonEvery problem, for the fix command to use
    • .launchreadykit/history.jsonYour score over time
    • .launchreadykit/raw/What each checker found, one file per checker

    The kit adds .launchreadykit/ to your .gitignore, so reports are not committed. Short on time? /launch-check quick checks only security, database and payments.

  4. 04

    Read the report

    In Claude Code

    You get a score from 0 to 100, a verdict (SHIP, FIX THEN SHIP or DON'T SHIP) and a list of what to fix first. Each problem says where it is, why it matters and how to fix it.

    > /launch-report

    /launch-report html saves one page you can share, at .launchreadykit/report.html. See an example report →

  5. 05

    Fix

    In Claude Code

    This is the only step that changes your code. Problems that can be fixed in code are fixed, worst first, and you review every change. You also get a short list of what only you can do, such as changing a leaked key.

    > /launch-fix

    To choose what gets fixed, add all, a severity such as critical, or check IDs such as KEY-01.

  6. 06

    Check again

    In Claude Code

    Run the check again. You get the new score, and what is fixed, what is new and what is still open. Repeat the fix and the check until the verdict is SHIP.

    > /launch-check

    /launch-score shows the current score and its history.

In your project

Two folders. Nothing hidden.

The kit lives in .claude/ and its results go to .launchreadykit/. Everything runs inside your own Claude Code session. There is no server and nothing is sent to us.

your-project/
├─ .claude/                 added by setup
│  ├─ agents/               41 agents
│  ├─ skills/               72 skills
│  └─ commands/             63 commands
├─ .launchreadykit/         written by the check, ignored by git
│  ├─ report.md
│  ├─ findings.json
│  ├─ history.json
│  ├─ raw/
│  └─ launch/               drafts for launch day
└─ your code                changed only by /launch-fix

Updating and removing

Run these in your terminal, from the project folder.

  • npx -y github:launchreadykit/LaunchReadyKit update

    New files are added. Files you edited are kept.

  • npx -y github:launchreadykit/LaunchReadyKit doctor

    Verifies the install.

  • npx -y github:launchreadykit/LaunchReadyKit uninstall

    Removes the kit. Files you edited are kept.

  • A command missing or not working? Type /launch-doctor. Not sure which command to use? Type /launch-help and say what you want in your own words.

/launch-check

Find the problems before your users do.

Install the kit into Claude Code, type one command, and get a score and a list of what to fix. Pay once, use it on every project you own.

Get the kitSee a sample report

41 agents · 440 checks · read-only audit · one-time payment