/checkup (Claude Code setup audit)
Reduces setup friction and misconfiguration that slow CI/CD pipelines and developer onboarding.
Native Claude Code CLI command (v2.1.205+, alias of /doctor) that audits and offers to fix your setup: cleans up unused skills/MCPs/plugins, dedupes local vs. checked-in CLAUDE.md, splits a bloated root CLAUDE.md into nested files + skills, disables slow hooks, updates the CLI, enables auto mode by default, and pre-approves frequently-denied read-only commands. Confirms every change before applying. Interactive-terminal only — not available in Cowork/desktop app sessions or non-interactive harnesses.
- Ask Claude to audit your Claude Code setup and remove duplicate or unused skill configurations.
- Generate a report of slow hooks and CLI performance issues, then disable them automatically.
- Find and reorganize bloated CLAUDE.md files into smaller, nested configuration files by skill.
Reduces setup friction and misconfiguration that slow CI/CD pipelines and developer onboarding. Prevents duplicate or stale configurations that cause silent failures in code generation workflows.
Platform engineers and DevOps leads managing Claude Code deployments across teams or CI environments.
https://github.com/anthropics/claude-code/blob/main/CHANGELO...
How to Get It
This is a methodology or approach — no installation needed. See the Source link above for the full steps, or paste the source URL into Claude and ask it to summarise the recipe and help you apply it.
After installing, paste this into Claude:
Audit my Claude Code setup and remove duplicate or unused skill configurations
Trust Signals Auto-scanned
Community Pulse Active
Discussed on Hacker News
- Claude Code is steganographically marking requests — Hacker News · 2444 pts
- Claude 3.7 Sonnet and Claude Code — Hacker News · 2127 pts
- The Claude Code Source Leak: fake tools, frustration regexes, undercover mode — Hacker News · 1376 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 137,372 GitHub stars; contributors unknown; last commit 0d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 137,372 GitHub stars; contributors unknown; last commit 0d ago; license no license.