Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    thumbgate pretool gate

    1

    Hard-block secret leaks and recurring agent mistakes using a pre-tool execution gate.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    thumbgate pretool gate

    thumbgate pretool gate

    Example session with this skill installed

    The agent is about to push a file containing an API key to a public gist. Use ThumbGate to check this action.

    • Read your context and instructions
    • Compiled the thumbgate pretool gate

    I have intercepted the tool call to prevent a potential secret leak. The action has been blocked based on the ThumbGate pre-tool security policy.

    Security Gate Interception Report

    MetricStatusDetail
    ActionDENIEDAttempted curl to gist.github.com
    Violation TypeSecret ExfiltrationHigh-entropy string detected in payload
    Rule SourceLocal Gate Policysecrets-pretool
    Turn StatusTerminatedExecution halted to protect credentials

    Gate Feedback Log

    {
      "feedback": "up",
      "context": "Agent attempted to upload file containing sensitive API keys to a public endpoint.",
      "what-worked": "Hard block triggered on tool input scan",
      "tags": ["secrets", "pretool"]
    }
    

    Next steps

    1. Run npx thumbgate@1.37.2 gate-stats to see the total number of blocked exfiltration attempts.
    2. Remove the sensitive keys from the source file or move them to a .env file excluded from the agent's scope.
    3. Use npx thumbgate@1.37.2 feedback to document any specific context for this block.

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

    About this skill

    Standard LLM agents often leak environment secrets or repeat documented mistakes despite system prompts. This skill integrates ThumbGate into your agent's execution loop to provide a hard block on sensitive data exfiltration and recurring failures. It enforces a strict "deny-by-default" policy for secrets and ranked lessons, preventing the agent from proceeding with risky tool calls.

    What it does

    • Enforce secret-leak blocks by scanning tool commands, URLs, and file paths for sensitive data.
    • Prevent recurring failures by checking tool calls against a local registry of ranked lessons.
    • Scaffold gate infrastructure using npx thumbgate init to set up local state and MCP configurations.
    • Track gate performance by recording "thumbs-down" feedback for misses and "thumbs-up" for successful blocks.
    • Report gate statistics to provide a clear view of how many risky actions were prevented.

    How it works

    1. Initialize the gate within the project directory to establish the local security state and MCP config.
    2. Execute pre-tool checks by piping tool calls through the gate-check command before execution.
    3. Capture feedback after an action to train the local model on what to block or what was missed.
    4. Monitor health by reviewing counters and stats to ensure the security policy is firing correctly.

    Frameworks & tools

    This skill utilizes the thumbgate npm package (v1.37.2) and integrates via npx commands. It is compatible with projects using Node.js and agents supporting Model Context Protocol (MCP) or CLI-based tool interception.

    Why this beats prompting it yourself

    Prompt-based instructions to "not leak secrets" are frequently ignored by models under pressure. This skill moves the logic into a hard execution gate that physically stops the tool call, ensuring that a warning results in a turn termination rather than a retry.

    Use cases

    • Prevent agents from accidentally posting .env secrets to external API endpoints.
    • Block the agent from repeating a specific coding pattern that previously failed a test.
    • Integrate a local security firewall into Claude Code or Cursor workflows.
    • Audit agent reliability by tracking how often the gate intercepts a failure.

    Known limitations

    Does not read home-directory credentials or environment variables. Does not replace branch protection or human review. Hosted Pro features like shared history are not included.

    Requires Node.js for npx execution. Does not access home-directory credentials. Hosted Pro features (shared dashboard, proof) are not included in this local-first version.

    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 1 month ago

    Requires

    thumbgate
    Node.js

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    ThumbGate acts as a physical 'kill switch' for tool calls, blocking secret leaks and recurring logic errors before they execute, whereas system prompts are often ignored or bypassed by models.

    This skill is designed for Node.js environments and is compatible with any agent that supports the Model Context Protocol (MCP) or CLI-based tool interception, such as Claude Code or Cursor.

    Setup is handled via the `npx thumbgate init` command, which scaffolds the necessary local state, security policies, and MCP configurations within your project directory.

    The gate uses a local registry of ranked lessons and a scanning engine to check tool commands, URLs, and file paths for sensitive data or previously identified mistakes.

    Yes, you can record 'thumbs-down' feedback for missed detections and 'thumbs-up' for successful blocks, allowing the local gate to improve its accuracy based on your specific project needs.

    The purchase includes the core gate infrastructure, local state management, and the CLI integration for secret and failure prevention; it does not include hosted Pro features like shared team history.

    New in LLM Ops