Codebase Metrics Report

The problem

Engineering leads and developers often lack objective data on codebase composition. Manual line counting is inaccurate because it fails to distinguish between functional code, comments, and boilerplate.

What it does

• Generates deterministic reports on lines of code (LOC) categorized by language.
• Produces machine-readable XML and CSV files for automated metric tracking.
• Identifies maintenance hotspots by ranking files by size and cyclomatic complexity.
• Calculates language distribution ratios to inform migration or hiring decisions.
• Performs directory comparisons to quantify the impact of refactors or branch merges.

Frameworks & tools

Python, pygount, radon, and standard Unix utilities like csvcut and sort.

Why this beats prompting it yourself

Standard LLM prompts often hallucinate counts or fail to handle large directory structures. This skill provides a specific, reproducible pipeline using offline tools that correctly ignore comments and blank lines, ensuring audit-grade accuracy.

Use cases

• Quantifying technical debt by identifying oversized or overly complex modules.
• Performing due diligence on a new codebase to understand language distribution.
• Measuring the net code reduction after a major refactoring sprint.
• Generating automated reports for stakeholders during a migration project.

Known limitations

Requires Python and pygount installed on the local system. Performance may lag on massive repositories if excluding generated or vendored folders is skipped.