1

    Agent Tool Trace for Debug

    by Corey Jacobs

    This skill allows for focused tool trace receipts to help debug and fine tune Agents

    Updated Jul 2026
    0 installs

    Free

    Included in download

    • Downloadable skill package
    • 3 permissions declared
    • Instant install

    Media gallery

    See it in action

    You say

    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.

    Your agent does

    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

    About This Skill

    The problem

    Agent runs fail in ways that are hard to see afterward. A task drifts. A file goes missing. A model says “done” without proof. Without a trace, nobody can tell where the run broke.

    What it does

    • Logs agent actions, decisions, discoveries, and artifacts as JSONL.
    • Labels failures with 10 modes, including silent-scope-drift and artifact-evaporation.
    • Generates pass/fail/unknown release receipts backed by evidence.
    • Creates replay prompts so another agent or reviewer can retrace the run.
    • Exports SFT-shaped JSONL, including negative eval records when failures exist.

    Frameworks & tools

    Python CLI using local JSON and JSONL artifacts. Core file: afr/cli.py.

    Why this beats prompting it yourself

    Asking an agent what happened after the fact is weak. This gives the run a paper trail: logs, failure labels, receipts, replay prompts, and exportable training/eval records.

    Use cases

    • Audit a skill, prompt pack, or workflow before release.
    • Debug multi-step agent failures.
    • Create receipts for sensitive file or release operations.
    • Turn real agent runs into structured training and evaluation data.

    Known limitations

    No passive background recording. Requires CLI use, scripted integration, or post-hoc transcript analysis.

    Use Cases

    • Classify agent failures using a standardized 10-mode taxonomy
    • Generate replay prompts to reproduce agent behaviors exactly
    • Produce structured receipts to prove what an agent actually verified
    • Export SFT-ready data for model evaluation and fine-tuning

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables

    Allowed Hosts

    json-schema.org
    agensi.io

    File Scopes

    agent-tool-trace-for-debug/**

    Tags

    debugging
    audit-trail
    agent-ops
    traceability
    python
    replay
    sft

    Requires Node.js 18+. Best with Claude Code 1.2+ and compatible agents that support SKILL.md workflows.

    Creator

    Corey Jacobs

    AI Autodidact living at the edge.

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    diagnosing-rag-failure-modes

    RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

    $105 installs

    designing-hybrid-context-layers

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    $1016 installs
    Cinematic Landing Page Builder

    Cinematic Landing Page Builder

    Turn any business URL into a high-end animated landing page with 4K AI assets and GSAP animations via Cloudflare.

    $1912 installs

    Bounty Security Pattern Master Library — 399 Vulnerability Patterns

    A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.

    $7512 installs

    Free