Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Codebase Metrics Report

    10

    Inspect a codebase with pygount: count lines of code by language, produce summary and XML/CSV reports, rank the largest files, compute language ratios, spot com

    Free

    4 usesSecurity scanned
    Codebase Metrics Report

    Codebase Metrics Report

    Example session with this skill installed

    Run a full metrics report on the current directory. Skip node_modules and dist. Give me the top 5 largest files and a language breakdown.

    • Read your context and instructions
    • Compiled the codebase metrics report
    • Generated the data export

    Analysis complete.
    Total LOC: 12,450 (TS: 65%, CSS: 20%, HTML: 15%).
    Top 5 Largest Files:

    1. src/legacy/api.ts (1,240 lines)
    2. src/store/main.ts (890 lines)
      ...
      Summary saved to summary.txt, full data in report.csv.

    report.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    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.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Requires pygount and radon to be installed via pip. Does not support proprietary languages that pygount cannot parse. Accuracy depends on correctly excluding vendored/generated folders.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    4 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    The skill uses the pygount engine to perform a deterministic analysis that ignores whitespace and comments, providing audit-grade accuracy that standard LLM prompts cannot achieve on their own.

    Yes, the skill produces machine-readable XML and CSV files, making it easy to feed data into your existing CI/CD pipelines or dashboard tools for long-term tracking.

    It works with any AI agent capable of executing Python scripts locally; ensure you have Python, pygount, and radon installed on your system for the skill to function.

    The skill is highly effective for identifying technical debt by ranking your largest, most complex files and providing language ratios to help guide refactoring or hiring decisions.

    You receive the executable skill file, a guide for local environment setup, and access to future updates that include support for new programming languages and reporting formats.

    While it handles standard repositories quickly, performance on extremely large projects (millions of lines) depends on your local hardware and whether you exclude vendored folders.

    Free