Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Agent Failure Forensics

    1

    Forensic diagnostic skill to identify root causes and first-divergence points in failed AI agent executions.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Agent Failure Forensics

    AI Agent Failure Forensics

    Example session with this skill installed

    **Analyze this log:** the agent was supposed to fetch user data and email a summary. It fetched the data but then crashed with a 'Null Pointer' error in the email tool call.

    • Read your context and instructions
    • Compiled the ai agent failure

    **Primary Failure:** Tool Input Failure (CRITICAL). **First Divergence:** The 'fetch_user' tool returned a JSON object, but the agent failed to extract the 'email' field, passing 'null' to the email tool. **Root Cause:** Output Interpretation Failure. **Remediation:** Update extraction logic in agent prompt.

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

    About this skill

    AI Agent Failure Forensics is an evidence-first diagnostic Skill for investigating why AI agents fail, behave inconsistently, produce incorrect results, misuse tools, or break during multi-step workflows. Instead of simply asking an AI to “debug the problem,” it reconstructs the execution sequence, compares expected versus observed behavior, identifies the first meaningful divergence, separates symptoms from root causes, evaluates competing hypotheses, and produces an evidence-supported diagnosis. The Skill is designed for developers, AI engineers, agent builders, QA teams, and technical teams working with agentic systems. It delivers a structured Failure Evidence Pack containing the failure classification, execution reconstruction, first divergence, evidence chain, root cause, failure cascade, recommended remediation, regression test, verification status, and residual risk. The workflow also includes explicit safeguards for untrusted logs and artifacts, prompt-injection resistance, evidence integrity, uncertainty handling, least-privilege analysis, privacy protection, and verification discipline. Use it when you need to answer: “What actually went wrong, where did the agent first diverge from the expected path, why did it happen, and how do we prove the fix works?” This is not a generic debugging chatbot or prompt generator. It is a reusable forensic workflow designed to turn ambiguous agent failures into defensible, actionable, testable, and verifiable diagnoses.

    Requires execution logs, traces, or transcripts. Cannot diagnose failures without evidence. Does not autonomously apply fixes to your codebase.

    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 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    Unlike generic chat tools, this skill uses a structured evidence-first approach to identify the 'first divergence point'—the exact moment an agent's logic veered off-course—rather than just guessing based on the final output.

    The skill is designed to analyze logs and trace data from any agentic framework (such as LangChain, AutoGPT, or CrewAI) and is compatible with any LLM-based agent regardless of the underlying model.

    You will receive the reusable forensic workflow, a guide on formatting your execution logs for analysis, and the templates for the Failure Evidence Pack used to document findings.

    Yes, the workflow includes explicit safeguards for handling untrusted logs and artifacts, including prompt-injection resistance and privacy protection protocols to ensure data integrity during the forensic process.

    This skill is ideal for complex multi-step workflows where agents might misuse tools, hallucinate logic mid-task, or experience cascading failures that are difficult to trace manually.

    New in Agents & Orchestration