hive-debugger

Diagnose Hive agent runtime issues through multi-stage L1/L3 analysis and MCP log reviews.

10.9k|5.7k|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/adenhq/hive --skill hive-debugger
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hive-debugger
Source: https://github.com/adenhq/hive/tree/main/.claude/skills/hive-debugger
Command: npx skills add https://github.com/adenhq/hive --skill hive-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Hive Debugger provides an interactive companion to help developers identify runtime issues in Hive agents, triage logs, and guide fixes with structured diagnosis and actionable recommendations.

Core Features & Use Cases

  • Real-time and post-mortem analysis of agent runs
  • Stage-by-stage debugging workflow including L1/L2/L3 analyses
  • Step-by-step guidance to diagnose, fix, and verify agent issues with templates and verification support

Quick Start

Launch the debugger against a running Hive agent using the MCP tooling, respond to prompts to gather context, mode, and triage results.

Frequently Asked Questions about hive-debugger

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

FAQPage Schema
How do I troubleshoot Hive agent runtime issues using logs and MCP?

Hive agent debugging uses MCP queries and runtime log reviews to guide multi-stage analysis, diagnose root causes, and provide actionable remediation for completed failures and active runs.

What is the best way to diagnose a failed Hive agent run?

The best way to diagnose a failed Hive agent run is to use a stage-by-stage debugging workflow that applies L1, L2, and L3 analyses to identify the root cause and guide step-by-step fixes with verification support.

Can I analyze completed Hive agent failures, or does debugging only work on active runs?

You can analyze both active agent runs and completed failures, as the debugging workflow supports real-time triage and post-mortem analysis to diagnose runtime issues and historical patterns across L1 and L3 levels.

Do I need MCP tooling access to debug Hive agents?

Yes, you need access to MCP tooling and agent logs, because the debugging process requires integrating MCP queries and log reviews to perform runtime triage, root-cause analysis, and structured diagnosis.

How does multi-stage analysis work for Hive agent triage?

Multi-stage analysis works by guiding diagnosis through L1, L2, and L3 levels, using mode selection and verification workflows to structure the troubleshooting process and confirm actionable fixes for runtime issues.