trace

Trace agent workflows with chronological timelines and type-filtered reports.

1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/1molchuan/oh-my-ccg --skill trace-1molchuan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/1molchuan/oh-my-ccg/tree/main/skills/trace
Command: npx skills add https://github.com/1molchuan/oh-my-ccg --skill trace-1molchuan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Readable, time-ordered records of how the Oh-My-CCG engine executes hooks, skills, agents, and tools, enabling quick diagnosis of workflow behavior.

Core Features & Use Cases

  • Full Timeline: Display the complete sequence of events from session start to skill activations.
  • Filtered Insights: Filter by type (hooks, skills, agents, tools) to focus on specific parts of the run.
  • Summary Analytics: Generate aggregate statistics to evaluate throughput and latency across the run.

Quick Start

Run the trace command to display the full timeline of the current session.

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 issues?

You can trace agent workflows by displaying a chronological timeline and summary of all hooks, skills, agents, and tools. This provides full timeline views and aggregated statistics to debug performance within the runtime.

What is the best way to filter agent execution logs by type?

Filtering agent execution logs by type allows you to focus on specific parts of the run. You can generate type-filtered reports for hooks, skills, agents, and tools to isolate workflow behavior and diagnose issues quickly.

Does the trace feature require a specific state file to generate accurate timelines?

Yes, the trace feature reads data from the .oh-my-ccg/state/hud-state.json file. It requires that hook scripts, agent lifecycles, and skill activations populate that file to generate accurate traces.

Can I view aggregate statistics for agent workflow latency and throughput?

Yes, you can generate summary analytics to evaluate aggregate statistics for throughput and latency across the run. This helps you assess performance bottlenecks within the agent workflow execution.

Why is my agent workflow trace not showing any events?

If your agent workflow trace is not showing events, the hook scripts, agent lifecycles, and skill activations likely did not populate the .oh-my-ccg/state/hud-state.json file. Ensure your runtime writes execution data to this file.