Truth First

    3

    Eliminate hallucinations with an evidence-first verification framework for system state, configs, and file contents.

    Free

    179 uses5.0 (3 reviews)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    truth-first

    Example session with this skill installed

    Check the current status of the database connection, Nginx configuration, and Redis service before we proceed with the deployment.

    • Read your context and instructions
    • Compiled the truth-first

    Verification Report

    • DB Connection: Verified (Source: .env/logs)
    • Nginx Config: Inferred (File exists, but syntax check skipped)
    • Redis Status: Unknown (Command timeout)
      [Evidence: 2023-10-27 14:02:11 DB_UP]
      Next check: systemctl status redis

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

    About this skill

    What it does

    The Truth-First Verification skill enforces a rigorous, evidence-based workflow for AI agents. It prevents "hallucinated certainty" by requiring real-time verification of system states, configurations, and file contents before the agent is allowed to provide an answer. Instead of assuming a service is running or a config is correct, the agent must prove it using available diagnostic tools.

    Why use this skill

    Standard LLM prompts often lead to agents making assumptions based on outdated context or training data. This skill eliminates that risk by implementing a strict classification framework (Verified, Inferred, Unknown). It is essential for developers working in environments where accuracy is non-negotiable, such as infrastructure management, debugging complex deployments, or auditing configurations. It ensures every response is backed by specific command outputs or file citations.

    Supported tools

    • Verification via ripgrep (rg) for targeted file searches.
    • System status checks (ls, stat, logs) for environment validation.
    • Connectivity and mount verification.
    • Configuration auditing through direct file reads and environment inspections.

    The Output

    The agent delivers a structured report listing every claim analyzed, its verification status, and the direct evidence (paths, log snippets, or command results) supporting the conclusion. If a state remains unknown, the agent provides the exact commands needed to find the answer.

    • Cannot verify states requiring root permissions if the shell is unprivileged.
    • Limited by the quality and freshness of available system logs.
    • High latency on deep file system scans (rg) in massive directories.

    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

    5.0
    3 reviews
    5
    3
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 179 times.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed7 months ago
    Updated22 days ago

    What's inside

    Frequently Asked Questions

    This skill forces the agent to categorize every claim as Verified, Inferred, or Unknown by performing real-time checks on your system state and file contents before responding, ensuring the agent never "guesses" about your environment.

    The skill is designed to work with most advanced LLM-based agents that have filesystem or terminal access, utilizing standard tools like ripgrep and system logs to gather evidence.

    You receive the core verification logic, instructions for the evidence-based workflow, and specific tool-call patterns that enable the agent to audit configurations and system states effectively.

    Installation is straightforward; you simply import the skill into your AI agent's environment or include the provided logic in your agent's system prompt to immediately enable the structured reporting framework.

    If the agent cannot verify a specific state or config using its current permissions, it will explicitly mark that claim as 'Unknown' and provide you with the exact terminal commands needed to retrieve that missing evidence manually.

    Yes, this skill is highly effective for auditing complex deployments, as it cross-references live log snippets and configuration files against your desired system state to ensure actual vs. expected consistency.

    New in Agents & Orchestration

    Free