lunaroute

🥈Silver

LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode. Get complete visibility into every LLM interaction with zero-overhead passthrough, comprehensive session recording, and powerful debugging capabilities.

127150Updated 1mo ago

Intermediate30min to implementautomation

Saves ~60 min per use

Quick InstallView Source

git clone https://github.com/erans/lunaroute.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/erans/lunaroute

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

I'm using LunaRoute to debug my AI coding assistant interactions. Here's the [CODE] I'm working with and the [ERROR] I'm encountering. Can you help me analyze the session recording and suggest fixes? I'm using [ASSISTANT_NAME] as my coding assistant.

Example Output

# LunaRoute Debugging Analysis

## Error Summary
- **Error Type**: SyntaxError
- **Location**: Line 42, Column 15
- **Context**: Missing closing parenthesis in function call

## Session Recording
```
[2023-11-15 14:32:10] User Input: 'def calculate_stats(data):'
[2023-11-15 14:32:12] Assistant Response: '    mean = sum(data) / len(data)'
[2023-11-15 14:32:15] User Input: '    return mean'
[2023-11-15 14:32:17] Assistant Response: 'print(calculate_stats([1, 2, 3, 4, 5])'
```

## Suggested Fixes
1. Add missing closing parenthesis in print statement
2. Consider adding input validation
3. Add error handling for empty lists

## Additional Recommendations
- Use LunaRoute's session replay to observe the interaction flow
- Check the assistant's temperature setting for this session (was 0.7)
- Review the model's context window size for this interaction (was 4096 tokens)