More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Vetfirst: Read every file before a skill gets installed

    1

    Pins a commit, reads every file, scans for load-time shell, hooks, MCP configs, encoded payloads and credential reads, drops what is risky, logs it in a registry, and waits for your yes.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Vetfirst: Read every file before a skill gets installed

    Vetfirst: Read every file before a skill gets installed

    Example session with this skill installed

    Vetfirst: someone shared github.com/example-dev/handy-notes-skill in our chat. Is it safe to install?

    • Read your context and instructions
    • Compiled the vetfirst

    Cloned read-only into ~/scratch/vet/handy-notes-skill, pinned at 4e1a9c0. Not opened in an agent session.

    Provenance: repo 3 weeks old, 1 author, 14 commits, no security issues filed. Name is close to a popular notes skill, noted as a possible typosquat.
    Licence: MIT. Text may be copied with attribution (LICENSE kept, NOTICE.md added).
    Inventory: 6 files, all read: SKILL.md, references/format.md, references/extra.md, scripts/setup.sh, .mcp.json, LICENSE.

    Scan hits (4)

    • SKILL.md: link to project docs (benign)
    • scripts/setup.sh: curl ... | sh download and run (risky)
    • .mcp.json: starts a server from @latest with network access (risky)
    • references/extra.md: tells the agent to add a line to the user's settings file (risky)

    Verdict

    SkillSource @ commitLicenceHitsVerdictKeptOmitted
    handy-notesgithub.com/example-dev/handy-notes-skill @ 4e1a9c0MIT1 benign, 3 riskyinstall with omissionsSKILL.md, references/format.md, LICENSEscripts/setup.sh, .mcp.json, references/extra.md

    Dangling reference: SKILL.md step 2 points to references/extra.md, which is omitted.

    Nothing has been copied. Reply yes to install the kept files by hand from the pinned clone.

    Next steps

    1. Approve or reject the verdict above.
    2. On yes, append the registry entry to THIRD_PARTY_SKILLS.md.
    3. Re-run the scan on the diff when upstream changes.
    Text may be copied with attribution (LICENSE kept, NOTICE.md

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

    About this skill

    An agent skill, plugin or MCP server runs with your agent's permissions, but most get installed on the strength of a star count or a marketplace badge. The risky part is rarely in the main file: it sits in a setup command, a hook, a hidden config or a reference file nobody opened. Vetfirst treats every outside skill like code from a stranger and reads it before anything is installed.

    What it does

    • Provenance records repo, author handle and marketplace page, and checks repo age, activity, security issues and typosquat names.
    • Licence decides what may be copied: with attribution, ideas only, or not at all.
    • Pin and read clones read-only into a scratch folder, records the commit, and reads every file including hidden configs.
    • Risk scan greps for downloads, installs, load-time shell, hooks, MCP configs, eval, base64, sudo, credential reads and remote fetches, then reads each hit in context.
    • Omit, not patch keeps only trusted files and drops risky scripts and configs instead of editing them.
    • Registry logs source, commit, licence, kept and omitted files, and a scan summary.

    How it works

    1. Check provenance and licence.
    2. Clone and pin, never running the repo's installer or a curl ... | sh line.
    3. Inventory and scan every file; binary or minified files with no source are rejected.
    4. Judge each hit benign or risky. When unsure, it is risky.
    5. Show a verdict table (install, install with omissions, reject) and wait for your yes.
    6. Record and re-scan on every update against the pinned commit.

    Frameworks & tools

    git, find, wc and grep with a ready scan pattern. Works on any skill, plugin, agent config, prompt pack or MCP server.

    Why this beats prompting it yourself

    A quick prompt usually reads SKILL.md and stops. This skill reads every file, flags load-time execution as the worst class, never opens the repo in an agent session that would auto-load it, and only counts your yes, not the agent's confidence.

    Use cases

    • Before any install from a marketplace, repo, gist or chat message.
    • MCP server review of tools, write or delete actions, network hosts and token scopes.
    • Batch vetting with one table and one registry section.

    Known limitations

    Not for auditing your own app code or package dependencies. It does not fix risky third-party scripts; it drops them or rewrites the idea. Nothing is installed automatically.

    Not for auditing your own app code or package dependencies. It does not fix risky third-party scripts; it drops them or rewrites the idea. Nothing is installed automatically.

    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 29 days ago

    Requires

    git
    grep
    find
    playwright
    Node.js

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Read Files
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    The repo URL or marketplace link of the skill, plugin or MCP server, plus `git` and `grep`. It works from a scratch folder outside your projects.

    No. It never patches a third-party script. Risky files are omitted, or you rewrite the idea yourself.

    It reads every file, including hidden configs and references, scans with a fixed pattern, judges each hit in context, and waits for your explicit yes before anything is copied.

    SKILL.md, the instructions your agent follows, and LICENSE.md.

    New in Security