trace

Trace chronological agent interaction flows with timeline and summary outputs.

24|2|Updated Mar 12, 2025
One-click install
npx skills add https://github.com/Orinks/AccessiWeather --skill trace-orinks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/Orinks/AccessiWeather/tree/main/.codex/skills/trace
Command: npx skills add https://github.com/Orinks/AccessiWeather --skill trace-orinks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This trace capability helps developers visualize and audit the runtime flow of agent interactions, showing how hooks, keywords, skills, agents, and tools interact during a session.

Core Features & Use Cases

  • Timeline tracing: display chronological sequence of events for debugging and optimization.
  • Summary statistics: expose hook fire counts, detected keywords, activated skills, and mode transitions.
  • Insightful flows: identify bottlenecks and flow patterns (keyword → skill → agent chains) to improve performance.

Quick Start

Invoke trace_timeline to view the latest session, or trace_summary to generate an aggregate report for debugging agent flows.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I debug multi-agent flow interactions during a session?

To debug multi-agent flow, you can trace the chronological sequence of agent interactions to visualize how hooks, keywords, skills, agents, and tools connect. This exposes runtime events for structured analysis and optimization.

How does timeline tracing work for optimizing agent performance?

Timeline tracing works by displaying a chronological sequence of runtime events, allowing you to identify bottlenecks and flow patterns like keyword to skill to agent chains. This helps improve overall agent performance.

Can I get summary statistics for detected keywords and activated skills?

Yes, you can generate an aggregate summary report that exposes hook fire counts, detected keywords, activated skills, and mode transitions. This provides structured statistics for debugging agent flows across sessions.

What is the best way to audit runtime interactions across multiple sessions?

The best way to audit runtime interactions is to generate a trace summary that aggregates flow patterns and statistics across sessions and runs. This exposes how tools and agents interact for comprehensive review.

How do I view the chronological sequence of events in a debugging session?

You view the chronological sequence of events by invoking the timeline trace function, which displays the latest session flow. This exposes the exact order of hooks, skills, and tools firing during runtime.