introspection-review-tracker

What problem does it solve?

Reference documentation for the automated ReviewOutcomeTracker hook that persists adversarial code review findings as self_assessment memories. The hook fires automatically after every review — no manual steps required. This skill documents the mapping from severity tiers to error categories and the content format.

Core Features & Use Cases

• Tracks and persists review findings as self_assessment memories to enable auditability and learning.
• Documents severity-to-category mappings and the required memory content format for introspection workflows.
• Provides guidance for post-review verification and integration with the llmem CLI.

Quick Start

Run llmem track-review after each adversarial code review to persist findings.