trace

Visualize agent flow timelines and aggregate session statistics.

2|2|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/chrisxue90/oh-my-qwencode --skill trace-chrisxue90
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/chrisxue90/oh-my-qwencode/tree/main/skills/trace
Command: npx skills add https://github.com/chrisxue90/oh-my-qwencode --skill trace-chrisxue90

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Show agent flow trace timeline and summary to aid debugging and auditing by exposing how hooks, keywords, skills, agents, and tools interact over a session.

Core Features & Use Cases

  • Timeline: Display a chronological sequence of events for the current or latest session.
  • Filter & Focus: Narrow output by event types (hooks, keywords, skills, agents, tools, modes) to target specific analysis.
  • Summary: Provide aggregate metrics including hook fire counts, detected keywords, activated skills, mode transitions, and tool performance.
  • Use Case: Debug complex agent workflows by tracing flow paths and identifying bottlenecks.

Quick Start

Invoke trace_timeline to view the latest session timeline, then run trace_summary to see aggregate statistics.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I trace agent workflow execution to debug performance bottlenecks?

To trace agent workflow execution, run trace_timeline to view a chronological sequence of events for the latest session. This reveals how hooks, skills, agents, and tools interact, helping you identify execution bottlenecks and debug complex workflows.

What is an agent flow timeline and when do I need it for debugging?

An agent flow timeline is a chronological visualization of session events showing interactions between hooks, keywords, skills, agents, and tools. You need it when auditing complex workflows or debugging performance issues to understand execution patterns and isolate bottlenecks.

Can I filter the agent flow timeline by specific event types like hooks or tools?

Yes, you can narrow the timeline output by filtering specific event types including hooks, keywords, skills, agents, tools, and modes. This filtering allows you to target specific analysis and focus on particular aspects of the workflow execution.

How do I get aggregate statistics for agent hooks and tool performance?

Run trace_summary to get aggregate statistics for agent sessions. This provides metrics including hook fire counts, detected keywords, activated skills, mode transitions, and tool performance, enabling focused analysis of your workflow execution.

Does this agent flow tracer require any dependencies or external components?

No, the agent flow tracer operates without any dependencies or external components. It is a standalone skill that directly analyzes session data to present timeline traces and aggregate statistics for debugging and auditing purposes.

What's the best way to audit mode transitions and skill activations across a session?

The best way to audit mode transitions and skill activations is to use trace_summary, which aggregates these metrics across a session. Pair it with trace_timeline to view the chronological context of when these transitions and activations occur.