Guardrails for AI agents to review payment system code safely
This project provides a set of specialized skills and evaluation harnesses for AI coding agents like Claude Code and OpenAI Codex. It focuses on critical fintech failure modes such as idempotency, reconciliation, and state machine errors. By installing these guardrails, engineers ensure their AI assistants review payment logic with the rigor required for handling real money.
View on GitHub →Pablo-aps/payments-engineering-skills