More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🧭 Doc Drift Detector

    1

    Doc Drift Detector is a specialized automated auditor designed to ensure your READMEs and Markdown documentation stay in sync with your actual codebase.

    $13

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🧭 Doc Drift Detector

    🧭 Doc Drift Detector

    Example session with this skill installed

    Check if my README.md and API.md still match the current codebase. Highlight any stale environment variables or missing functions.

    • Read your context and instructions
    • Compiled the doc drift detector

    Documentation Drift Found

    • Rule ID: STALE_ENV_VAR
    • Severity: High
    • File: README.md:42
    • Message: 'API_TIMEOUT_MS' is documented but not found in source or .env.example.
    • Evidence: export API_TIMEOUT_MS=5000
    • Remediation: Update docs to 'REQUEST_TTL'.
    README.md

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

    About this skill

    What it does

    Doc Drift Detector is a specialized automated auditor designed to ensure your READMEs and Markdown documentation stay in sync with your actual codebase. It scans your project to identify "ghost" references—functions, CLI flags, environment variables, and scripts that are mentioned in your docs but have been deleted or renamed in your source code.

    Why use this skill

    Manual documentation reviews are error-prone and often skipped during fast-paced development. This skill automates the tedium of cross-referencing string literals in docs against code definitions. Unlike a generic AI prompt, it utilizes a structured scanning workflow that targets specific high-risk areas like package.json, Makefiles, and framework-specific env configurations, providing severity ratings and remediation steps for every discrepancy found.

    Supported tools

    • Languages: Python, JavaScript, TypeScript
    • Config Files: package.json, Makefile, Markdown
    • Detection Scopes: Function signatures, CLI flags, Environment variables, Import paths

    Heuristic detector. Dynamic or meta definitions can produce false positives, so it flags likely drift for review rather than asserting certainty. It cross-references Python and JS/TS source; other languages are out of scope for the code side.

    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 5 months ago

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **/*.md
    **/README*
    **/*.py
    **/*.js
    **/*.ts
    **/*.jsx
    **/*.tsx
    package.json
    Makefile

    Read-only. It reads both the docs and the source and cross-references them, then prints findings with rule id, severity, file, and line. Ignores node_modules, dist, build, and vendor. Writes nothing and reads no environment variables.

    Listed5 months ago

    What's inside

    Frequently Asked Questions

    This skill scans your Markdown files and cross-references them with your source code to find 'broken' documentation, such as functions that were renamed, CLI flags that no longer exist, or environment variables that are no longer supported.

    Doc Drift Detector is designed to work with any AI agent that has file-system access or GitHub integration, including popular coding assistants and CLI-based agents.

    Yes, the skill is optimized for monorepos and complex projects, effectively mapping references across Python, JavaScript, and TypeScript source files to ensure your project-wide READMEs are accurate.

    You will receive the complete AI skill definition, including the logic for scanning local source files (JS/TS/Python) and configuration files like package.json or Makefiles.

    Simply provide the skill with access to your repository's root directory and trigger it via your AI agent; it will automatically locate documentation and source folders to begin the audit.

    Updates are handled through the marketplace platform, and buyers receive lifetime access to any future improvements, such as support for additional programming languages or configuration file types.

    New in Technical Documentation