codebase-inspection

Analyze repositories with pygount for lines of code, language distribution, and code-to-comment ratios.

Updated Jun 17, 2026

Search Tags:#codebase #analysis #metrics #repository #loc #pygount

Ready to run

npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill codebase-inspection-cxnaive

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codebase-inspection
Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/skills/github/codebase-inspection
Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill codebase-inspection-cxnaive

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pygount.

What problem does it solve?

This skill solves the difficulty of manually auditing large repositories to understand their size, language distribution, and code-to-comment ratios.

Core Features & Use Cases

Language Breakdown: Automatically identifies the programming languages present and their respective file counts.
Metric Analysis: Calculates lines of code (LOC) and comment density to assess project maturity or documentation quality.
Use Case: Quickly determine the primary languages and total volume of a new repository before starting a code review or migration project.

Quick Start

Use the codebase-inspection skill to analyze the current directory and provide a summary of the language breakdown and lines of code.

Frequently Asked Questions about codebase-inspection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I calculate lines of code and language distribution for a repository?▼

To calculate lines of code and language distribution, scan the software repository using the pygount utility to automatically identify programming languages, file counts, and total volume across the directory.

Can I exclude dependency and build folders when analyzing codebase metrics?▼

Yes, you can exclude dependency and build folders during codebase analysis by applying configurable exclusion patterns, ensuring the metrics reflect only your source code.

What is the best way to assess code-to-comment ratios for technical debt assessment?▼

Assessing code-to-comment ratios for technical debt involves scanning the directory to calculate comment density alongside lines of code, evaluating project maturity and documentation quality.

Does pygount support directory-level scanning for codebase size reporting?▼

Yes, pygount supports directory-level scanning for codebase size reporting, calculating lines of code and language breakdowns to satisfy repository auditing requirements.

When do I need to analyze codebase composition and metrics?▼

You need to analyze codebase composition and metrics before starting a code review or migration project, allowing you to quickly determine the primary languages and total volume of a new repository.

What are the limitations of using pygount for repository auditing?▼

Pygount focuses on calculating lines of code, language distribution, and comment density, meaning it provides quantitative codebase metrics but does not perform qualitative static analysis or detect functional code smells.