Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Customs Checkpoint

    1

    You run the checkpoint on the command you are about to execute, read the verdict, and only then run it.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Coding agents often install packages that do not exist, and attackers register those exact names. This skill puts a checkpoint in front of installs, clones and skill fetches. You run the checkpoint on the command you are about to execute, read the verdict, and only then run it.

    The checkpoint is deterministic. It looks up each name in the registry, checks its age, downloads and advisories, and compares it with popular names to catch typos. Its verdicts do not depend on a model's opinion.

    Run the check before any of these, on the exact command you were going to run:

    • pip install, pip3 install, uv add, uv pip install, poetry add
    • npm install, npm i, pnpm add, yarn add
    • git clone of a repository, or an install of an agent skill (skills add ...)
    • A manifest edit that adds a dependency (requirements.txt, package.json): check the install line you are adding, not just the file

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

    Reads public registry metadata and statically scans install-time code; it does not run packages, so a clean result is not proof of safety. Git and skill sources are fully checked only on GitHub. Requirements files are not opened. The typo list covers about 75 popular package names. The optional LLM checks have not been run against the live service.

    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

    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 2 days ago

    Accounts
    GitHubOsv
    Software
    Python 3.10+Network access to PyPI, npm, OSV, GitHubGit
    Optional
    NEBIUS_API_KEY

    Permissions

    Allowed Hosts

    pypi.org
    files.pythonhosted.org
    registry.npmjs.org
    api.npmjs.org
    api.osv.dev
    api.github.com
    api.tokenfactory.nebius.com (only if NEBIUS_API_KEY is set)

    File Scopes

    requirements.txt
    /
    package.json
    (only
    when
    the
    user
    runs
    fix)

    Read-only registry lookups by default. The fix command edits a manifest and runs a test command the user supplies; the original file is restored if tests fail.

    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Checks every package install, git clone and agent-skill fetch against the real registries (PyPI, npm, OSV, GitHub) before it runs, so hallucinated or malicious names get caught. Use this whenever you are about to run pip install, npm install, uv add, poetry add, git clone, or install a skill, especi

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use customs-checkpoint on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Security