Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Tool Trace: Debug Receipts

    2

    Capture tool-trace receipts, label failures, and emit replay prompts so you can debug an agent run after it finishes.

    Free

    1 useSecurity scanned
    Agent Tool Trace: Debug Receipts

    Agent Tool Trace: Debug Receipts

    Example session with this skill installed

    Trace my current session analyzing the security of the local Auth module. Use the tool watchlist. If you find gaps, classify the failures and generate a receipt.

    • Read your context and instructions
    • Compiled the agent tool trace

    ATD Run Complete

    • Run ID: auth-sec-audit-2023
    • Events captured: 14
    • Failures classified: 2 (1 stale-context-use, 1 missing-receipt)
    • Artifacts produced: trace.jsonl, failure_report.md
    • Receipt: .afr/runs/auth-sec-audit/receipt.md
    • Replay prompt: .afr/runs/auth-sec-audit/replay.md
    trace.jsonl, failure_report.md

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

    About this skill

    Logs agent actions and artifacts as JSONL, labels failures (scope drift, missing receipts, artifact evaporation), and writes a pass/fail receipt plus a replay prompt. Use it when a multi-step run failed and the chat no longer explains why.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    • No passive background recording.
    • Requires CLI or manual event logging.
    • Best results require structured post-hoc analysis.

    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

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables
    Listed4 months ago
    Updated19 days ago

    What's inside

    Frequently Asked Questions

    This skill generates structured trace receipts and logs that identify exact failure points, like file disappearances or scope drift, which are often invisible in standard agent outputs.

    The skill consists of a Python CLI tool (centered around afr/cli.py) that processes agent logs into JSONL artifacts for debugging and reporting.

    It is framework-agnostic and works with any agent capable of generating a transcript or log, provided you can pass those artifacts through the included Python CLI.

    Yes, the skill can export your trace data into SFT-shaped JSONL files, allowing you to use your real agent runs as high-quality training or evaluation data for fine-tuning.

    No, this tool does not run silently in the background; it requires active use via the CLI or integration into your existing scripts to process and label run data.

    Agent Tool Trace uses 10 distinct failure modes, such as 'artifact-evaporation' and 'silent-scope-drift,' to categorize errors more precisely than a simple pass/fail metric.

    New in LLM Ops

    Free