A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.
production-skeleton
by hallikkristjan-code
Two skills for coding agents such as Claude Code and Codex. One checks whether a new app has the basics in place for production (backups, rollback, health checks, timeouts), and the other audits a running app, accepting only evidence that points to a file and line.
Proof level: ReadNew and promisingMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Code generation only works for one stack (Next.js, Supabase and Vercel); other stacks get the scorecard only.
Things to check
- Code generation only works for one stack (Next.js, Supabase and Vercel); other stacks get the scorecard only
- Optional live checks send requests to a URL, and the CSRF option sends a POST, so use it only on apps you own
- Small, young project with limited track record
- Needs an AI coding agent, which may require a paid subscription or API key
Can you use production-skeleton commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with production-skeleton?
- Run a read-only 13-point scorecard on a repository to see which production basics are missing, with file and line evidence
- Generate missing files such as CI workflows and health routes for a Next.js, Supabase and Vercel project, without overwriting existing files
- Audit a running app across 13 areas including payments, data protection, monitoring and business continuity, and get a top-3 risks summary
How do you get production-skeleton running?
Install with `npx skills add hallikkristjan-code/production-skeleton`, then run `/skeleton` in Claude Code, or run the probe script directly with Node.
Follow the official instructions in the project README.
Make money with it
A freelancer could sell production-readiness audits of vibe-coded apps, using the evidence-based reports as the deliverable.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Check an AI-built client app before launch to catch missing backups, rollback plans and timeouts, avoiding costly failures later
- Offer a production-readiness review to clients as a paid service, using the scorecard and audit report as the basis
Who's talking about it
Checked 11 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in Agent skills and plugins
A skill for Claude Code and Codex that reviews a screen built with AI tools, finds the generic "AI look" such as purple gradients, glows and uneven spacing, and fixes it step by step. It is for making dashboards, apps and landing pages look designed rather than auto-generated.
A small collection of agent skills, each a folder with a SKILL.md file of instructions for an AI agent. At present it holds one skill, a Socratic tutor that teaches a topic through questions, a skill map and spaced review.