Hybrid-CLI-Agent
🥈SilverHybrid-CLI-Agent is a multi-agent CLI orchestrator that combines Claude Code, Gemini CLI, and OpenRouter to automate operations tasks. It enables operations teams to cut costs by ~90% without sacrificing quality. The skill integrates with existing CLI tools and workflows, providing a flexible and cost-effective solution for AI engineering.
1610Updated 2mo ago
Intermediate30min to implementautomation
Saves ~120 min per use
Quick InstallView Source
git clone https://github.com/SneezeGUI/Hybrid-CLI-Agent.gitWorks with:
Claude
Overview
About This Skill
Hybrid-CLI-Agent is a multi-agent orchestrator that routes tasks to the most cost-effective AI model: Gemini (free tier) for reading and summarizing large volumes of logs and documentation, Claude for complex reasoning and code review, and OpenRouter for specialized models and second opinions. It works as both a standalone CLI tool and integrates with Claude Code via MCP, allowing natural language task delegation. The system uses a supervisor pattern where Gemini handles heavy context processing at no cost while Claude performs high-value decision-making, reducing overall AI API spending by approximately 90% without sacrificing output quality. Operations teams, developers, and engineering managers benefit from dramatically lower costs while maintaining access to precise reasoning and comprehensive codebase analysis.
How to Use
Install via npm and run the interactive setup wizard with 'npm run setup' to authenticate Gemini (free OAuth) and Claude. Use CLI commands like 'hybrid ask', 'hybrid research', and 'hybrid draft' for direct orchestration, or integrate with Claude Code to delegate tasks naturally through MCP. Verify status with 'hybrid status' to check authentication and usage tier.
Use Cases
Analyze large error logs and documentation using free Gemini tier, then have Claude identify root causes
Draft code implementations with Gemini review-supervised by Claude before deployment
Research deprecated API usage across codebases using Gemini's free heavy-reading capacity
Perform security-focused code reviews with multi-model consensus between Claude, Gemini, and OpenRouter models
Tags
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/SneezeGUI/Hybrid-CLI-AgentRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Act as a Hybrid-CLI-Agent. Use Claude Code for precise reasoning, Gemini CLI for large context, and OpenRouter to orchestrate the following task: [TASK]. Use the following existing CLI tools: [TOOLS]. Provide a step-by-step plan to automate this task, explaining how each tool will be used and how they integrate together.
Example Output
# Hybrid-CLI-Agent Task Automation Plan ## Task: Automate Server Monitoring and Alerting ### Step 1: Data Collection - **Tool**: `server-monitor-cli` - **Action**: Use Gemini CLI to process large log files and extract relevant metrics. - **Output**: Generate a summary of server health metrics over the last 24 hours. ### Step 2: Anomaly Detection - **Tool**: `anomaly-detector-cli` - **Action**: Use Claude Code to analyze the extracted metrics and identify anomalies. - **Output**: List of detected anomalies with severity levels. ### Step 3: Alert Generation - **Tool**: `alert-cli` - **Action**: Use OpenRouter to orchestrate the alerting process, sending alerts to the appropriate team members based on severity. - **Output**: Alerts sent to Slack channels and emails for critical issues. ### Step 4: Reporting - **Tool**: `report-cli` - **Action**: Generate a daily report summarizing server health, anomalies, and actions taken. - **Output**: PDF report sent to the operations team. ## Integration - **Data Flow**: `server-monitor-cli` → `anomaly-detector-cli` → `alert-cli` → `report-cli` - **Cost Savings**: Estimated 90% reduction in manual monitoring tasks.
Apply to these tools
Browse all tools
Gemini
Google's multimodal AI model and assistant
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan