trace

Display agent session flow traces with chronological timelines and summaries.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/lpjhelder/kronon-forge --skill trace-lpjhelder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/lpjhelder/kronon-forge/tree/main/skills/trace
Command: npx skills add https://github.com/lpjhelder/kronon-forge --skill trace-lpjhelder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps users understand how hooks, keywords, skills, agents, and tools interact during a session by providing a clear visual trace and concise summary.

Core Features & Use Cases

  • Chronological Timeline: Uses the trace_timeline MCP tool to list events in order, with optional filtering and limiting.
  • Aggregate Summary: Employs the trace_summary MCP tool to give statistics on hook fires, keyword detections, skill activations, mode changes, and tool performance.
  • Bottleneck Identification: Highlights slow tools or agents and mode transition points for performance tuning.

Quick Start

Ask the trace skill to display the current session’s flow timeline and summary.

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 flow timeline for debugging?

To visualize an agent flow timeline for debugging, use the trace_timeline MCP tool to list chronological events of hooks, keywords, skills, and tool interactions within a Kronon Forge workflow. It generates an ordered timeline with optional filtering and limiting.

What is an agent session trace summary?

An agent session trace summary provides statistics on hook fires, keyword detections, skill activations, mode changes, and tool performance. It uses the trace_summary MCP tool to aggregate session data for bottleneck identification and performance tuning.

How do I identify slow tools and bottlenecks in a workflow?

To identify slow tools and bottlenecks in a workflow, apply the trace_summary tool to highlight slow tools, agents, and mode transition points. This provides performance insights to tune agent interactions and workflow execution.

Does the trace tool require any dependencies to display mode transitions?

No dependencies are required to display mode transitions. The trace skill uses the trace_timeline and trace_summary MCP tools directly within a Kronon Forge workflow to generate mode transition points and bottleneck insights without external setup.

Can I filter specific hook fires or keyword detections in a timeline?

Yes, you can filter specific hook fires or keyword detections in a timeline by applying optional filtering and limiting parameters. The trace_timeline MCP tool lists chronological events of hooks, keywords, skills, agents, and tool interactions with configurable limits.

When should I use a chronological timeline instead of an aggregate summary?

Use a chronological timeline to inspect the exact order of hooks and tool interactions, and use an aggregate summary for statistics on hook fires, keyword detections, and tool performance. Both trace tools help visualize agent flow but serve different debugging needs.