trace

Trace agent interaction timelines with filtering by event type.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/byonk19-svg/rt-scheduler --skill trace-byonk19-svg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/byonk19-svg/rt-scheduler/tree/main/.codex/skills/trace
Command: npx skills add https://github.com/byonk19-svg/rt-scheduler --skill trace-byonk19-svg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Flow Trace helps teams visualize and understand the sequence of interactions between hooks, keywords, skills, agents, and tools within a session. This visibility accelerates debugging, performance tuning, and incident investigation.

Core Features & Use Cases

  • Timeline view of event interactions across a session.
  • Filter by event types (hooks, keywords, skills, agents, tools, modes).
  • Aggregate statistics via trace_summary, enabling performance insights and bottleneck detection.

Quick Start

Run trace_timeline with no arguments to display the latest session timeline.

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 session timeline for debugging?

To visualize an agent session timeline for debugging, run trace_timeline with no arguments to display the chronological sequence of interactions between hooks, keywords, skills, agents, and tools. This provides a single view of the session flow.

What is session agent flow tracing used for?

Session agent flow tracing is used to visualize and understand the sequence of interactions within a session. It accelerates debugging, supports performance tuning, and enables incident investigation by showing chronological interactions across events.

How do I filter session trace events by type like hooks or tools?

You filter session trace events by applying event type filters to the timeline. The trace supports filtering by specific event types including hooks, keywords, skills, agents, tools, and modes to isolate relevant interactions.

Can I get aggregate statistics for agent interactions to detect bottlenecks?

Yes, you can get aggregate statistics for agent interactions to detect bottlenecks by using the trace_summary function. It aggregates session data to provide performance insights and identify interaction bottlenecks across the session.

Does agent flow tracing work for incident analysis across multiple sessions?

Yes, agent flow tracing works for incident analysis across multiple sessions. The trace timeline and summary functions support debugging, performance reviews, and incident investigation by visualizing chronological interactions across different sessions.