More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    voice agent guard

    1

    A deterministic safety framework for AI agents to block, confirm, or allow shell commands and tool calls.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    voice agent guard

    Example session with this skill installed

    Review the command 'rm -rf /' and explain how the guard should handle it based on the guard rules.

    • Read your context and instructions
    • Compiled the voice agent guard

    The provided command rm -rf / is a critical system operation that violates multiple safety boundaries. According to the guard rules, this call must be intercepted at the PreToolUse stage and stopped immediately.

    Guard Analysis: rm -rf /

    CheckResultReason
    Commandrm -rf /Recursive force-delete of the root directory.
    TierBLOCKClassified under "deletes system folders or a whole drive".
    ResponsedenyImmediate termination of the tool call.
    Logic PathPrinciple 1 & 2Block beats confirm. Root access is strictly prohibited.

    The guard identifies the rm verb with recursive and force flags targeting the root /. Any command attempting to delete system folders, the home directory, or a volume root is hard-blocked without a confirmation prompt. The agent should be informed that the action was denied and instructed not to attempt a workaround.

    Hook Output

    {
      "hookSpecificOutput": {
        "hookEventName": "PreToolUse",
        "permissionDecision": "deny",
        "permissionDecisionReason": "deletes system folders or a whole drive"
      }
    }
    

    Next steps

    1. Ensure your PreToolUse hook handles both the alias del and the verb rm.
    2. Add a unit test specifically for root-relative paths in the block list.
    3. Configure the agent to report the specific permissionDecisionReason to the user via voice.

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

    About this skill

    Voice-driven AI agents can mishear commands or act on instructions hidden in web pages, leading to deleted files or leaked secrets. This skill provides a tested rulebook for building a PreToolUse permission layer that decides which commands run, which ask first, and which never run.

    What it does

    • Three tiers sort every tool call into Allow, Confirm or Block. Block beats Confirm, Confirm beats Allow, and anything unknown asks first.
    • Wrapper unwrapping checks commands hidden inside powershell -Command or bash -c, and checks every part of a chained or piped command.
    • Untrusted content treats text from web pages, files, emails and the clipboard as data, and asks before any change once the agent has read it.
    • Secret protection blocks reads of browser profiles and saved passwords, SSH keys, AWS and cloud credentials, keychains and system folders.
    • Permission modes offer five levels, from Manual (every change asks) to Bypass (nothing asks, but the Block list still blocks).
    • Browser rules cover clicks that submit, buy, post or delete, plus password and card fields.

    How it works

    1. Intercept the tool call as JSON from a PreToolUse hook, before it runs.
    2. Split the command on pipes, ;, &&, newlines, brackets and backticks, and unwrap shell wrappers.
    3. Check every part against the Block, Confirm and Allow lists. One risky part decides for the whole command.
    4. Answer the agent with allow, ask or deny, plus a plain reason the user sees. No answer within 30 seconds means no.

    Frameworks & tools

    Written for Claude Code and Codex hooks, with the exact JSON output format included. The rules carry over to any agent that runs shell commands. Covers bash, zsh and PowerShell on Windows, macOS and Linux. Drawn from the guard in Nova, an open-source voice assistant, where these rules are covered by tests.

    Why this beats prompting it yourself

    A system prompt that says "be safe" can be talked around, and the model can mishear or misjudge. This skill moves the decision into code that checks the real command, not the model's description of it. It also tells you to make that code fail closed: if the check crashes or nobody answers, the action is denied.

    Use cases

    • Voice interfaces for hands-free coding, where nobody is watching the terminal.
    • Browser agents that must not click Delete, Buy or Send without asking.
    • DevOps guardrails that stop an agent from pushing to git, deploying or changing infrastructure without asking.

    Known limitations

    This is a rulebook, not a ready-made hook: you build the parsing and register the hook yourself. Pattern rules can be bypassed by unusual spellings, so test them and expect to add rules over time. Database commands (for example DROP TABLE) are not covered. The browser rules assume your browser tool can inspect the real page element.

    Only covers standard shells (bash, powershell) and common CLIs. Implementation of the parsing logic and hook registration is required by the developer.

    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 5 days ago

    Requires

    jest
    Node.js
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a deterministic 'PreToolUse' documentation framework that intercepts commands at the software level, ensuring that malicious or misheard instructions are blocked regardless of how the AI is prompted.

    While optimized for Claude Code and Codex hooks, the logic is universal and can be implemented in any Python or Node.js environment where an AI agent has shell or tool-calling access.

    You will receive the complete logic architecture, the three-tier command categorization rules, and the specific segmentation strategies needed to parse complex shell commands.

    Yes, the framework includes configurable profiles ranging from 'Manual' (maximum security) to 'Bypass,' allowing you to relax restrictions for known safe environments or specific development tasks.

    The framework uses recursive parsing to break down command strings by delimiters like pipes (|) and backticks (`), ensuring that a malicious command cannot be 'hidden' inside a seemingly safe wrapper.

    New in Security