agent-tracing

Capture and inspect agent execution snapshots with a CLI viewer.

1|Updated May 20, 2026
One-click install
npx skills add https://github.com/mDevsLabs/mAI --skill agent-tracing-mdevslabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-tracing
Source: https://github.com/mDevsLabs/mAI/tree/main/.agents/skills/agent-tracing
Command: npx skills add https://github.com/mDevsLabs/mAI --skill agent-tracing-mdevslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Debugging complex agent workflows by recording and inspecting per-step execution snapshots, traces, and context data to diagnose failures and understand behavior.

Core Features & Use Cases

  • Deterministic snapshot recording to disk during development
  • CLI viewer to inspect partial and complete snapshots
  • Context engine data capture separated from Redis pipeline for safety

Quick Start

Run agent-tracing from the repository root to view the latest trace.

Frequently Asked Questions about agent-tracing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I debug agent workflows by inspecting per-step execution traces?

Debug agent workflows by capturing deterministic execution snapshots to disk during development, allowing you to inspect per-step traces and context engine data to diagnose failures and understand behavior.

What is the best way to capture and view agent execution snapshots during development?

Capture agent execution snapshots deterministically to disk, then use a CLI viewer interface to inspect partial and complete snapshots, organizing per-step traces for debugging and auditing runs.

How do I record context engine data separately from my Redis pipeline for debugging?

Record context engine data by separating the capture process from the Redis pipeline for safety, ensuring deterministic data recording of agent steps and context without affecting live data flows.

Can I inspect partial agent execution traces if a workflow fails before completion?

Inspect partial agent execution traces by running the CLI viewer from the repository root, which displays both partial and complete snapshots to help diagnose failures and validate agent steps.

When do I need to record execution snapshots for agent debugging?

Record execution snapshots when you need to debug complex agent workflows, validate agent steps, or audit deterministic data across runs to diagnose failures and understand runtime behavior.

Does agent-tracing require any external dependencies to inspect execution traces?

Inspecting execution traces requires no external dependencies, as the skill operates standalone to capture deterministic snapshots to disk and provides a built-in CLI viewer for auditing agent runs.