trace

Render agent flow trace timelines and compute aggregate interaction statistics.

1|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/Linnanli/xClaw --skill trace-linnanli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/Linnanli/xClaw/tree/main/.codex/skills/trace
Command: npx skills add https://github.com/Linnanli/xClaw --skill trace-linnanli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Show agent flow trace timeline and summary.

Core Features & Use Cases

  • Timeline visualization of how hooks, keywords, skills, agents, and tools interacted during a session.
  • Summary of interactions, including counts and mode transitions.
  • Use Case: Debug complex agent workflows by inspecting the trace and aggregated statistics.

Quick Start

Run trace_timeline to display the latest session trace, then run trace_summary to view the aggregated statistics.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I visualize an agent workflow timeline for debugging?

To visualize an agent workflow timeline for debugging, run trace_timeline to display a chronological view of how hooks, keywords, skills, agents, and tools interacted during your latest session.

Can I get aggregated statistics on agent interactions and mode transitions?

Yes, you can get aggregated statistics on agent interactions and mode transitions by running trace_summary, which computes aggregate counts and transitions from your session data.

What is the best way to audit prompts during an agent session?

The best way to audit prompts during an agent session is to inspect the trace timeline, which shows chronological interaction flows across hooks, keywords, skills, agents, and tools for debugging and auditing purposes.

How do I debug complex agent workflows when tools and hooks interact unexpectedly?

To debug complex agent workflows with unexpected tool and hook interactions, run trace_timeline to inspect the chronological event flow, then use trace_summary to review aggregated statistics and identify anomalous mode transitions.

Do I need any dependencies to track agent flow and render a trace timeline?

No dependencies are required to track agent flow and render a trace timeline; the skill operates independently to process session data and output chronological timelines and aggregated statistics.