hotspots

You can identify risky code files by analyzing git history for churn, evaluating complexity metrics like nesting depth, and counting file coupling to generate a ranked list of hotspots. This highlights where bugs are most likely to hide.

Code hotspot analysis pinpoints files with high change frequency, complexity, and coupling. Use it during code health reviews, pre-change impact assessments, or technical debt prioritization to find where bugs are likely to strike.

To run a hotspot analysis, ask Claude to execute the analysis on your repository. It requires access to your git history to compute change frequency and optionally uses lenskit graph data to enrich the risk scores.

Code churn analysis requires access to your git history to track file change frequency. It optionally integrates with lenskit analysis tools to compute and enrich graph data for deeper coupling and risk score insights.

Technical debt and risk scores are calculated by combining churn frequency from git history, complexity metrics like line count and function density, and coupling data counting how many other files depend on each candidate.

You can assess complexity and basic coupling without extra tools, but computing advanced risk scores is optionally enriched by lenskit graph data to provide deeper insights into how files depend on each other.