Agent Receipts Gate

    1

    Deterministic pre-send linting to catch agent hallucinations, missing receipts, and filler chatter.

    $9

    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 CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Receipts Gate

    Example session with this skill installed

    Analyze this draft: 'I have finished the code review for the auth module. Everything looks good, consider it handled.' Context: { 'hasTools': true, 'lastSentAgoSec': 300 }

    • Read your context and instructions
    • Compiled the agent receipts gate

    The agent reply was analyzed. The gate flagged a fabrication because the claim of a completed review lacked a receipt (file path, PR #, or link) and used a premature closure phrase.

    Validation Results

    MetricScoreStatusDetails
    Grounding10/100FAILNo file path, PR #, or URL provided for 'auth module'.
    Action20/100FAILClaimed 'handled' without specific tool output.
    Honesty90/100PASSNo false tool denials detected.
    Noise100/100PASSNot a duplicate; sent 300s after last message.
    VerdictREPAIR2Block sending until evidence is added.

    Suggested Repair

    "I have finished the code review for src/auth/middleware.ts in PR #42. The changes meet our security standards."

    Next steps

    • Append the specific file path or PR number to the draft.
    • Rerun the gate to confirm the send action (Exit Code 0).
    • Check the reason field in the JSON output to identify other missing receipts.

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

    About this skill

    Agent communication often suffers from "lazy hallucinations" where models claim a task is complete without performing the action or deny access to tools they actually possess. This skill provides a deterministic, pattern-based linting gate to validate agent replies before they reach the end user. It enforces the inclusion of "receipts"—tangible evidence like file paths, commit SHAs, or URLs—while suppressing redundant duplicates and filler chatter.

    What it does

    • Evidence verification identifies claims of completion or review that lack specific identifiers like URLs, file paths, or PR numbers.
    • Action validation flags instances where an agent claims a task is "handled" before any tool execution has occurred.
    • Honesty checking detects "self-denials" where an agent incorrectly claims it cannot perform a task despite having the necessary tools.
    • Noise suppression blocks duplicate messages sent within short windows or messages containing only filler chatter.
    • Reply scoring generates a 0-100 metric across grounding, action, honesty, voice, noise, and closure.

    How it works

    1. Pass the draft reply along with JSON context containing tool availability and message history.
    2. Evaluate the action code returned by the gate: send, repair, or suppress.
    3. Parse the verdict to identify specific failure modes like fabrication or promised-done.
    4. Automate the response by using exit codes (0, 2, or 3) to trigger pipeline blocks or rewrite logic.

    Frameworks & tools

    This is a deterministic, offline Node.js script (gate.cjs) that uses regex pattern matching rather than LLM calls for low-latency validation.

    Why this beats prompting it yourself

    Prompting an LLM to check its own honesty often results in recursive hallucinations. This skill uses hard-coded rules and pattern matching to provide an objective, offline second opinion that doesn't add to your token costs.

    Use cases

    • CI/CD bots that must provide a commit hash or log path when claiming a build passed.
    • Support agents to prevent "I'll look into that" filler when no ticket was actually opened.
    • Coding assistants to ensure file modifications are accompanied by specific line numbers or file names.

    Known limitations

    The tool is pattern-based and supports English only. It may flag benign conversational sentences as fabrications if they lack hard links, and it currently lacks a comprehensive list of all external websites.

    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.

    Pattern-based, English only. May flag benign claims lacking hard links as fabrications. Does not recognize all external URLs. Requires node environment.

    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 today

    Software
    Node.js

    Permissions

    Terminal / Shell
    Network Access
    Listedtoday

    What's inside

    Frequently Asked Questions

    This skill acts as a deterministic firewall that catches 'lazy hallucinations' by scanning agent replies for tangible evidence (like URLs or file paths) and flagging responses that claim completion without actual tool execution.

    Because this is a Node.js script using regex-based pattern matching rather than LLM calls, it provides objective validation with near-zero latency and no additional token costs.

    You will receive the 'gate.cjs' Node.js script, documentation on the JSON schema for context inputs, and a guide for integrating the send/repair/suppress exit codes into your existing pipeline.

    Yes, since the gate functions as an offline script, it is compatible with any LLM (GPT-4, Claude, Llama, etc.) as long as you can pass the agent's draft reply and tool history to the script.

    The gate is currently optimized for English-language patterns and requires a specific JSON format for tool history to accurately score 'honesty' and 'action' metrics.

    The skill uses a scoring system (0-100) across six categories, allowing you to set custom thresholds for when a message should be automatically blocked, sent for a rewrite, or allowed through.

    New in Security