Claude Launchpad

doctor

Scan your Claude Code config, score it 0-100, and auto-fix issues.

The core of the tool. Runs 7 analyzers against your .claude/ directory and CLAUDE.md. An 8th (Memory) is added automatically when agentic-memory is detected.

claude-launchpad doctor

Flags

FlagDescription
--fixAuto-fix: hooks, CLAUDE.md sections, rules, .claudeignore, credentials, sandbox
--fix --dry-runPreview what --fix would change without applying
--watchRe-runs every second when config files change
--min-score <n>Exit code 1 if below threshold (for CI)
--jsonPure JSON, no banner
-p, --path <dir>Run on a different directory

Analyzers

AnalyzerWhat it catches
Instruction BudgetToo many instructions — Claude starts ignoring rules past ~150
CLAUDE.md QualityMissing sections, vague instructions, hardcoded secrets
SettingsNo hooks, deprecated attribution, hook timeouts, auto-memory disabled
HooksMissing auto-format, .env protection, PostCompact, SessionStart
RulesDead rule files, stale references, empty configs
PermissionsCredential exposure, blanket Bash, bypass mode, sandbox disabled, .env gap
MCP ServersInvalid transport configs, missing commands/URLs
Memory (optional)MCP server config, hooks, autoMemory setting, CLAUDE.md guidance, tool permissions

What --fix applies

Use --fix --dry-run to preview changes before applying. This is recommended for projects with existing configurations.

After --fix, use /lp-enhance inside Claude Code to restructure your CLAUDE.md. The fixer appends sections mechanically - the skill rewrites them into clean, project-specific content.

When to re-run

Doctor isn't a one-time setup tool. It's a health check. Re-run it when:

  • You add or remove dependencies
  • You change frameworks or build tools
  • You modify hooks, permissions, or settings manually
  • Your score drops after an enhance or manual CLAUDE.md edit
  • Before a release, to catch config drift

Use --watch during active config editing to see your score update in real-time.

Next

On this page