Getting Started
Install Claude Launchpad and score your coding-agent setup in seconds. Doctor diagnoses Claude Code or Cursor Agent config; eval proves the agent follows your rules; memory persists decisions across sessions and machines.
Claude Code follows CLAUDE.md rules about 80% of the time. Hooks run at 100%. Most projects have zero hooks configured. Claude Launchpad scores and repairs that setup — and does the same for local Cursor Agent projects.
Install
npx claude-launchpadOr install globally:
npm i -g claude-launchpadpnpm add -g claude-launchpadyarn global add claude-launchpadClaude Launchpad has 4 CLI commands (init, doctor, eval, memory) and 2 skills (/lp-enhance, /lp-migrate-memory). Memory is optional. The npm package name stays claude-launchpad.
Two local harnesses share the same workflow files (TASKS.md, BACKLOG.md) and the same memory store. Scores are never averaged.
| Command | Claude Code | Local Cursor Agent |
|---|---|---|
init | default (CLAUDE.md, .claude/) | --harness cursor (AGENTS.md, .cursor/) |
doctor / --fix | yes | yes (--harness auto detects either) |
eval | yes | --harness cursor |
memory install | yes | --harness cursor (same SQLite + MCP) |
/lp-enhance | .claude/skills/lp-enhance/ | .cursor/skills/lp-enhance/ |
--harness both scaffolds or diagnoses both surfaces in one run. --min-score gates each harness separately. Cursor Cloud Agents cannot use the local memory MCP server.
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 SessionStart hook with the compact matcher re-surfaces tasks after context compression, keeping work on track.
Recommended Flow
New project
Scaffold
claude-launchpad initGenerates baseline config for the selected harness. Default is Claude Code (CLAUDE.md, .claude/). init --harness cursor writes AGENTS.md and .cursor/. Shared TASKS.md and BACKLOG.md are written once.
Let the agent perfect it
/lp-enhanceInside Claude Code or Cursor Agent, run the skill. It reads your codebase and fills in architecture, conventions, and guardrails on CLAUDE.md or AGENTS.md.
Prove it works
claude-launchpad eval17 scenarios test whether the selected agent actually follows your rules. Use --harness cursor for Cursor Agent.
Existing project
Fix the structure
claude-launchpad doctor --fixAdds missing hooks/rules/sections, security defaults, and creates /lp-enhance only when no project/global/legacy install already exists. Jumps to ~86%.
Let the agent clean it up
/lp-enhanceType /lp-enhance in Claude Code or Cursor Agent. The fixer appends sections mechanically — the skill rewrites the instruction file with project-specific content.
Prove it works
claude-launchpad evalKeep your config healthy
init runs once. Everything else is designed for repeat use as your project evolves.
| When | Run |
|---|---|
| Added dependencies, changed frameworks, modified hooks | doctor --fix |
| Major refactor, new modules, CLAUDE.md or AGENTS.md feels stale | /lp-enhance |
| Before a release, after config changes, the agent ignoring rules | eval |
| You want cross-session memory with local SQLite + MCP tools | memory |
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.
| Responsibility | init | doctor --fix | /lp-enhance | eval | memory |
|---|---|---|---|---|---|
| Detect stack and framework | ✓ | ||||
| Generate CLAUDE.md / AGENTS.md, TASKS.md, BACKLOG.md | ✓ | ||||
| Generate settings or hooks.json | ✓ | ✓ | |||
| Generate .claudeignore / .cursorignore | ✓ | ✓ | |||
| Score config 0-100 | ✓ | ||||
| Fix missing sections, rules, permissions | ✓ | ||||
| Rewrite CLAUDE.md / AGENTS.md with real project content | ✓ | ||||
| Suggest hooks, MCP servers, path-scoped rules | ✓ | ||||
| Overflow conventions to rules files | ✓ | ||||
| Prove the agent 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
| Command | Runs |
|---|---|
claude-launchpad init | Locally, free |
claude-launchpad / doctor | Locally, free |
claude-launchpad doctor --fix | Locally, free |
claude-launchpad doctor --watch | Locally, free |
/lp-enhance (skill) | Inside Claude Code or Cursor Agent |
claude-launchpad eval | Via Claude CLI or Cursor Agent |
claude-launchpad memory | Locally |
claude-launchpad memory --dashboard | Locally |
claude-launchpad memory push/pull | Via GitHub API |
claude-launchpad memory sync status | Locally |
claude-launchpad memory sync clean | Locally |
Commands marked Locally run offline with zero API calls. Eval requires the selected harness CLI or SDK (Claude Code or Cursor Agent) and authentication. Memory is optional.