Model Bundle Integrity Manifest

    1

    Refuses to write if the directory holds a file you did not declare, so the manifest describes the exact topology.

    $29

    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

    Model Bundle Integrity Manifest

    Example session with this skill installed

    Generate a manifest for my model directory at ./dist/llama-v3 with roles for the transformer and tokenizer, pinned to onnxruntime on cpu.

    • Read your context and instructions
    • Compiled the model bundle integrity

    Generated manifest for ./dist/llama-v3. Every file has been hashed and pinned to the specified runtime.

    Manifest Summary

    {
      "schemaVersion": "1.0.0",
      "engineVersion": "1.4.0",
      "manifestSha256": "8f3e27a1c92b45d6e81f72c9a871d3e192837465afbc9021034857261a938c42",
      "runtime": {
        "backend": "onnxruntime",
        "device": "cpu",
        "dtype": "float32"
      },
      "models": [
        {
          "role": "transformer",
          "file": "model.onnx",
          "bytes": 452083120,
          "sha256": "a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6e7f8a9b0c1d2e3f4a5b6c7d8e9f0a1b2"
        },
        {
          "role": "tokenizer",
          "file": "tokenizer.json",
          "bytes": 210432,
          "sha256": "f0e9d8c7b6a5f4e3d2c1b0a9f8e7d6c5b4a3f2e1d0c9b8a7f6e5d4c3b2a1f0e9"
        }
      ]
    }
    

    Next steps

    1. Copy the manifest.json into your ./dist/llama-v3 directory.
    2. Add const { verifyBundleDirectory } = require('./scripts/verify-bundle.mjs') to your service entry point.
    3. Record the manifestSha256 value in your deployment logs to verify consistency across your cluster.

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

    About this skill

    Model weights are the one artifact most deployments never verify after copying. A swapped file, a download truncated by a dropped connection, a weight replaced through a symbolic link or quietly updated to another quantization loads without complaint and changes every answer the service gives.

    Manifest (make-manifest.mjs): writes manifest.json from the directory you intend to ship: engine version, a runtime map (backend, device, dtype, versions), and for every model its role, plain file name, exact byte count, SHA-256, source and license. Refuses to write if the directory holds a file you did not declare, so the manifest describes the exact topology.

    Verifier (verify-bundle.mjs, library and CLI): the directory and every file must be real (lstat, realpath equal, no symbolic links or junctions); every file is stat'ed before and after it is streamed through SHA-256 and must be byte-identical and unchanged in inode, size, mode and timestamps; the directory listing must be exactly the manifest plus the listed files; roles must appear in the order your build expects; runtime fields you pin must match; unknown manifest keys fail. Returns the manifest digest so your health endpoint can prove which weights are loaded; exits 1 with MODEL_INTEGRITY: <reason> otherwise.

    6 tests: intact bundle, generator provenance fields and undeclared-file refusal, byte-count and byte-flip and extra-file and missing-file failures, role order and duplicate roles and path escapes and extension limits and runtime pins, symbolic-link redirection, and the two CLIs end to end.

    reference/manifest-format.md documents the format and each check. Node 20+, no packages, no network.

    Requires Node 20+. Cannot protect against attackers with write access to both manifest and model files. Symbolic link detection tests require specific OS privileges on Windows.

    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 17 days ago

    Requires

    Node.js 20+

    Permissions

    Read Files
    Write Files
    Listed17 days ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'silent failures' where a model might run but produce degraded results due to partial downloads, unauthorized file swaps, or unexpected quantization changes. It ensures that the exact model weights you tested in development are the ones running in production.

    Yes, it is framework-agnostic and supports any format including ONNX, safetensors, GGUF, and PyTorch. It focuses on the file-level integrity and directory topology rather than the internal model architecture.

    The bundle includes the core Node.js verification library, CLI tools for manifest generation (make-manifest.mjs) and auditing (verify-bundle.mjs), and a specialized test suite to confirm platform-specific link detection.

    While it runs on any Node.js 20+ environment, it is specifically designed for LLM-Ops and DevOps agents that manage model deployments, automated CI/CD pipelines, and health-check monitoring services.

    This skill uses advanced techniques like `lstat` checks and `realpath` equality to prevent Time-of-Check to Time-of-Use (TOCTOU) attacks, ensuring an attacker cannot swap a file in the split second between verification and loading.

    New in LLM Ops