Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ELYRAON Repo Health Check Lite

    2

    Static repository hygiene audit to detect missing config files, exposed secrets, and structural issues.

    Free

    1 useSecurity scanned

    About this skill

    Audit your codebase for hygiene issues without the risks of runtime execution or external API calls. Many static analysis tools are too heavy or require complex environment setups just to find missing configuration files or potential security leaks. This skill performs a filename-based hygiene check and static config audit using a local Python helper. It identifies missing project standards, exposed credential paths, and malformed repository structures while keeping your data local.

    What it does

    • Structure auditing validates presence of essential project files like README, LICENSE, and config manifests.
    • Credential detection flags common file paths and naming patterns associated with leaked secrets or logs.
    • Resource inventorying scans up to 5,000 files to map repository layout and size constraints.
    • Static evidence collection extracts specific line evidence and relative paths for manual review.
    • JSON reporting generates structured audit data compatible with custom CI/CD scripts or documentation.

    How it works

    1. Point the agent to a local repository directory or a stable snapshot.
    2. The agent executes a bundled Python helper script to scan the filesystem.
    3. The tool parses the JSON output to verify scan status and inventory limits.
    4. You receive a report detailing specific finding codes, relative paths, and line-level evidence.

    Frameworks & tools

    This skill uses a bundled Python 3 standard library helper. It operates entirely via local terminal and filesystem commands without requiring Node.js, Docker, or external cloud services.

    Why this beats prompting it yourself

    Generic prompts often hallucinate file contents or miss hidden dotfiles in large directories. This skill uses a deterministic Python script to ensure every file within the 20MB limit is actually inventoried and checked against a stable schema.

    Use cases

    • Perform a quick hygiene check on a new open-source clone before exploration.
    • Audit a repository for accidentally committed .env or log files.
    • Verify that a project meets basic scaffolding requirements before a release.

    Known limitations

    Does not execute code or run tests. Maximum 5,000 files or 20MB aggregate size. Individual files over 1MB are skipped. Symlinks and non-regular files are ignored.

    Caps at 5000 files and 20MB total. No runtime execution or deep semantic code analysis. Skips files over 1MB and symlinks.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike LLMs that may hallucinate file structures, this skill uses a deterministic Python script to ensure 100% accuracy in file inventorying and secret detection within the 5,000-file limit.

    This skill is designed for agents with local filesystem access and Python 3 environments, making it compatible with most desktop-based AI assistants and development agents.

    No, all analysis is performed locally via a bundled Python helper script; your source code is never sent to external APIs or third-party servers during the audit.

    The skill is optimized for repositories up to 5,000 files or 20MB in total size, with a 1MB limit for individual file scanning to ensure fast, responsive audits.

    You receive the complete skill package, including the Python-based audit logic, the agent configuration files, and documentation for integrating the JSON output into your workflow.

    New in Code Quality & Review

    Free