Request an audit

Expertise

A fixed-price code audit for AI-generated and legacy code

Before anyone rebuilds anything: I review architecture, security, tests, performance and deployment, and write down what is solid, where the risks are and what to fix first.

Open for new projects

Get in touch See all references

What I bring

  • What I review

    Architecture and dependencies, authentication and permission checks, secrets, test coverage, database queries and caching, CI and the release process – in in-house software, agency code and apps built with Cursor, Claude Code or Copilot.

  • What you get

    A written report: every finding with its severity, the effort to fix it and a suggested order. The report is yours – even if you do not continue with me.

  • How it is billed

    A fixed price, agreed up front in a written proposal. An NDA and a data processing agreement under Art. 28 GDPR come as standard; I work in your repository and in the AI setup you approve.

Projects that prove it

Real projects, real numbers – the full list is on the references page.

  • Messerle Shop

    Ticket-to-PR agent pipeline

    Agent skills that take a bug from report to pull request: reproduce it from synced data, prove the root cause, create the Jira ticket, fix it with unit + Playwright E2E tests and pass the PHPUnit/PHPStan gate.

    • Claude Code
    • OpenCode
    • Agent skills
    • Playwright
    • PHPUnit
    • GitHub API
    Read the article– Messerle Shop

Toolbox

  • Agentic engineering
  • MCP servers (Model Context Protocol)
  • Embeddings & vector search
  • Tool calling & structured outputs
  • Multi-agent orchestration
  • Claude Code & agent skills
  • OpenCode · Codex
  • LLM API integration (Anthropic, OpenAI)
  • Prompt & context engineering
  • LLM evals & guardrails
  • Agent guardrails: tests & CI gates
  • WebMCP · llms.txt
  • AI-assisted code review
  • Performance
  • Accessibility (WCAG)
  • Code reviews
  • Mentoring
  • CI/CD
  • AWS
  • Platform.sh
  • Agile / Scrum

Frequently asked questions

What does a code audit cover?

Architecture, security, tests, performance and deployment. I read the code, run it and look for the usual traces of unreviewed AI code: open API endpoints, missing permission checks, secrets in the repository, N+1 queries and duplicated logic.

Do you audit code written with Cursor, Claude Code or Copilot?

Yes – that is the core of my work. I use coding agents every day myself and know their typical failure patterns.

What happens after the audit?

You decide. The findings are ordered so your own team can work through them – or I fix them step by step while the system keeps running: tests first, then CI gates, then the rebuild, module by module.

Where are you based – and do you work remotely?

In Voitsberg, west of Graz in Styria, Austria. Remote across Europe and the UK, or hybrid in Styria.

Are you available?

Open for new projects. The quickest way to reach me is e-mail or LinkedIn.

Which languages do you work in?

English and Hungarian. Project communication, tickets, documentation and code are in English – I don’t work in German.

Sounds like what you need?

Tell me about your project or role – I’d love to hear from you.

Get in touch Connect on LinkedIn(opens in a new tab)