trace

Reveal chronological event flows and aggregate summaries of Codex agent sessions.

20|6|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/realsigridjin/oh-my-codex --skill trace-realsigridjin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/realsigridjin/oh-my-codex/tree/main/skills/trace
Command: npx skills add https://github.com/realsigridjin/oh-my-codex --skill trace-realsigridjin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill makes complex Codex sessions easier to understand by revealing how hooks, keywords, skills, agents, modes, and tools interacted over time.

Core Features & Use Cases

  • Timeline Inspection: Display the chronological event flow for the latest session or focus on selected event types.
  • Aggregate Summaries: Review hook counts, detected keywords, activated skills, mode transitions, and tool performance.
  • Use Case: When an orchestration workflow feels slow or behaves unexpectedly, use this Skill to identify mode changes, bottlenecking tools, and keyword-to-skill-to-agent execution patterns.

Quick Start

Use the trace skill to show the latest session timeline followed by an aggregate flow summary.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I inspect agent flow and spot bottlenecks in Codex orchestration workflows?

To inspect agent flow and spot bottlenecks in Codex orchestration workflows, retrieve the chronological event timeline and aggregate session statistics to review hook counts, mode transitions, and tool performance.

What is the best way to debug unexpected execution paths in agent sessions?

Debugging unexpected execution paths in agent sessions requires analyzing the chronological event flow to identify mode changes, keyword-to-skill-to-agent execution patterns, and bottlenecking tools across the session.

How does agent tracing reveal performance bottlenecks across hooks and tools?

Agent tracing reveals performance bottlenecks by applying trace_summary and trace_timeline tools to retrieve event timelines and aggregate statistics, exposing slow tool performance and mode transitions across hooks.

Do I need specific MCP tools to investigate session timelines and aggregate behavior?

Yes, investigating session timelines and aggregate behavior requires the trace_timeline and trace_summary MCP tools to retrieve chronological event flows and session statistics for debugging orchestration workflows.

Can I review detected keywords and activated skills during an agent session?

Yes, you can review detected keywords and activated skills by generating aggregate summaries that display hook counts, mode transitions, and tool performance throughout the agent session.