Dependency Audit

    2

    Audit project manifests against source code to find unused, missing, and misplaced dependencies across major languages.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    dependency-audit

    Example session with this skill installed

    Audit my project's dependencies to find any unused packages or items in the wrong section, and give me the commands to fix them.

    • Read your context and instructions
    • Compiled the dependency-audit

    Findings

    Unused

    PackageLocationConfidence
    lodashprodHigh

    Misplaced

    PackageMove to
    vitestdevDependencies

    Recommendations
    Run npm uninstall lodash and npm install -D vitest.

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

    About this skill

    What it does

    The Dependency Audit skill performs a deep-tissue scan of your project to identify unused, misplaced, and missing dependencies. It works by cross-referencing your manifest files (like package.json, requirements.txt, or Cargo.toml) against the actual import and require statements found in your source code.

    How it works

    Unlike basic linters, this skill maps your entire dependency graph across various ecosystems. It categorizes issues into clear buckets: unused packages that are bloating your build, dev-dependencies that accidentally leaked into production code, and "phantom" dependencies that you're using without explicitly declaring them.

    Supported ecosystem

    • Node.js/TypeScript: npm, yarn, pnpm (handles scoped packages and test-file detection).
    • Python: pip (requirements.txt and pyproject.toml normalization).
    • Go: go.mod analysis.
    • Rust: Cargo.toml dependency and dev-dependency separation.

    Why use this skill?

    Standard dependency checkers often miss the context of where a package is used. This skill understands the difference between production source and test suites. It prevents production crashes caused by missing manifest entries and reduces your attack surface by pruning unneeded code. It delivers a comprehensive DEPENDENCY_AUDIT.md report with actionable CLI commands to fix every found issue.

    • May flag runtime-only deps (polyfills) or config-based plugins as unused
    • Cannot detect dynamic imports or string-literal requires
    • Limited to root-level audits for monorepos

    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 any payment.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    Permissions

    Terminal / Shell
    Network Access
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    The skill identifies 'phantom' dependencies (used in code but missing from manifests), identifies unused packages to reduce build size, and flags development dependencies that are incorrectly used in production code.

    The skill provides a detailed DEPENDENCY_AUDIT.md report that categorizes every issue and provides the exact CLI commands needed to add, move, or remove the packages.

    Yes, the skill is designed to distinguish between production source code and test suites, ensuring that test-only libraries aren't accidentally flagged as missing from your production environment.

    This skill is compatible with major AI agents that have filesystem access, including AutoGPT, BabyAGI, and custom OpenAI-based agents capable of running command-line tools.

    Currently, the skill supports Node.js (npm/yarn/pnpm), Python (pip/pyproject), Go (go.mod), and Rust (Cargo), with more ecosystems planned for future updates.

    Your purchase includes the full skill set, documentation for integration, and lifetime access to any future updates or additional language support modules.

    New in Code Quality & Review