agent-tracing

Community

Debug agent execution with ease.

Authordodevproject
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a command-line interface to inspect and debug the execution of AI agents, allowing developers to understand LLM calls, context engine data, and agent steps.

Core Features & Use Cases

  • Inspect Execution Snapshots: View detailed logs of agent operations, including LLM interactions and tool calls.
  • Analyze Agent Steps: Drill down into specific steps of an agent's execution to understand its decision-making process.
  • Use Case: When an agent's behavior is unexpected, use this Skill to trace its execution, examine the exact prompts sent to the LLM, and review the data it processed to identify the root cause.

Quick Start

Use the agent-tracing CLI to view the latest agent execution trace.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-tracing
Download link: https://github.com/dodevproject/lobe-chat/archive/main.zip#agent-tracing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.