Claude Launchpad

Getting Started

Install Claude Launchpad and score your Claude Code setup in 10 seconds.

Claude Code follows your CLAUDE.md rules about 80% of the time. Hooks run at 100%. Most projects have zero hooks configured. Claude Launchpad fixes that.

Install

npx claude-launchpad

Or install globally:

npm i -g claude-launchpad
pnpm add -g claude-launchpad
yarn global add claude-launchpad

Claude Launchpad has 4 CLI commands (init, doctor, eval, memory) and 2 skills (/lp-enhance, /lp-migrate-memory). Memory is optional.

Why hooks matter: CLAUDE.md rules are ~80% reliable. Hooks are 100% enforced. A SessionStart hook that runs cat TASKS.md means Claude sees your tasks at every session start. A PostCompact hook re-surfaces tasks after context compression, keeping work on track.

New project

Scaffold

claude-launchpad init

Generates baseline config files in-project (CLAUDE.md, TASKS.md, .claude/settings.json) and creates .claudeignore, .claude/.gitignore, and .claude/rules/conventions.md when missing. It also offers /lp-enhance install (project/global/skip) when not already installed.

Diagnose + fix

claude-launchpad doctor --fix

Catches anything init missed and auto-fixes it.

Let Claude perfect it

/lp-enhance

Inside Claude Code, run the skill. Claude reads your codebase, restructures CLAUDE.md, and fills in architecture, conventions, and guardrails with real content.

Prove it works

claude-launchpad eval

15 scenarios test if Claude actually follows your rules.

Existing project

See your score

cd your-project
claude-launchpad

A typical unconfigured project scores ~42%.

Fix the structure

claude-launchpad doctor --fix

Adds missing hooks/rules/sections, security defaults, and creates /lp-enhance only when no project/global/legacy install already exists. Jumps to ~86%.

Let Claude clean it up

/lp-enhance

Inside Claude Code, type /lp-enhance. The fixer appends sections mechanically - the skill has Claude restructure and rewrite CLAUDE.md into clean, project-specific content.

Prove it works

claude-launchpad eval

Keep your config healthy

init runs once. Everything else is designed for repeat use as your project evolves.

WhenRun
Added dependencies, changed frameworks, modified hooksdoctor --fix
Major refactor, new modules, CLAUDE.md feels stale/lp-enhance
Before a release, after config changes, Claude ignoring ruleseval
You want cross-session memory with local SQLite + MCP toolsmemory

Your codebase changes. Your config should keep up. Run doctor periodically. If the score drops, --fix and /lp-enhance bring it back.

Who does what

Each tool handles one job. No overlap.

Responsibilityinitdoctor --fix/lp-enhanceevalmemory
Detect stack and framework
Generate CLAUDE.md, TASKS.md, BACKLOG.md
Generate settings.json and hooks
Generate .claudeignore
Score config 0-100
Fix missing sections, rules, permissions
Rewrite CLAUDE.md with real project content
Suggest hooks, MCP servers, path-scoped rules
Overflow conventions to .claude/rules/
Prove Claude follows your rules
Run sandbox test scenarios
Persistent cross-session memory
Memory dashboard, sync, migration

init scaffolds. doctor maintains. /lp-enhance makes it smart. eval proves it works. memory remembers.

Command reference

CommandRuns
claude-launchpad initLocally, free
claude-launchpad / doctorLocally, free
claude-launchpad doctor --fixLocally, free
claude-launchpad doctor --watchLocally, free
/lp-enhance (skill)Inside Claude Code
claude-launchpad evalVia Claude CLI
claude-launchpad memoryLocally
claude-launchpad memory --dashboardLocally
claude-launchpad memory push/pullVia GitHub API
claude-launchpad memory sync statusLocally
claude-launchpad memory sync cleanLocally

Commands marked Locally run offline with zero API calls. Commands marked Via Claude CLI require Claude Code installed and authenticated. Memory is optional.

Next Steps

On this page