← Back to browse
skill

Adversarial code review using Claude Codex

From IgorGanapolsky/mcp-memory-gateway

Summary

This skill executes a skeptical, adversarial review of a codebase using Claude Codex, identifying potential regressions, unsafe assumptions, and release risks. Users can scope the review by specifying a base branch, commit SHA, or focusing on specific threat models like security or data loss.