"Review Before Review" — the paradox of fixing code before it hits review

LLMs keep getting better with every release but code reliability is still an issue. Coding agents dont reliably enforce user defined guardrails and/or completely bypass instructions. (Wrote about it here - https://hasaber8.github.io/agents-and-me-experiments-with-ai-workflows-in-production/)

After months of experimenting with AI workflows in production, I’ve found a way to make Claude actually follow the rules. ATX (Agent Nexus) seamlessly connects to ClaudeCode, and OpenCode provides real-time feedback, enforcing rules and standards before they ever reach code review.