debug

Diagnose container-runner issues blocking agent execution across host and container.

5|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/thmtz/nanoclaw-fleet --skill debug-thmtz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug
Source: https://github.com/thmtz/nanoclaw-fleet/tree/main/.claude/skills/debug
Command: npx skills add https://github.com/thmtz/nanoclaw-fleet --skill debug-thmtz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Debug container agent issues and misbehaving container runtimes to keep NanoClaw Fleet running smoothly.

Core Features & Use Cases

  • Diagnose container-spawn and log propagation problems across host and container
  • Validate session resume paths and environment variable passing to the container
  • Troubleshoot MCP startup, Claude Code integration, and IPC workflows

Quick Start

Begin by checking the main logs, environment mounts, and session directories to identify the root cause and guide corrective actions.

Frequently Asked Questions about debug

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

FAQPage Schema
How do I debug container agent issues blocking execution?

To debug container agent issues, check the main logs, environment mounts, and session directories to identify the root cause. This skill diagnoses container-spawn and log propagation problems across both host and container to guide corrective actions.

Why does session resume fail in my container runner?

Session resume fails when container runner paths and environment variable passing are misconfigured. You can validate session resume paths and troubleshoot environment variable passing to the container to fix the execution block.

How do I troubleshoot MCP startup failures with Claude Code integration?

To troubleshoot MCP startup and Claude Code integration failures, diagnose the IPC workflows and container environment. This involves checking environment variable mounts and validating the IPC communication channels between the host and container.

What is the best way to fix container log propagation problems?

The best way to fix container log propagation problems is to diagnose log paths across both the host and container. This skill helps trace where logs fail to propagate and validates the environment mounts required for proper log output.

Can I use this debugging approach for any container runtime or just specific agents?

This debugging approach targets container-runner issues that specifically block agent execution, such as NanoClaw Fleet. It is suited for diagnosing MCP startup, session resume failures, and IPC workflows within that environment.

What should I check first when container spawn is not working?

When container spawn is not working, first check the main logs, environment mounts, and session directories. Identifying the root cause in these areas helps resolve container-spawn failures and environment variable passing issues.