Agent Calling

This extension is still under development; please use it at your discretion.

Calling other proxies and language models within the Gemini CLI.

English | 简体中文

• Claude code
• Codex

Agent Calling integrates Claude into the Gemini CLI ecosystem through three key mechanisms:

1. Path Hijacking: Creates a temporary directory containing a proxy script named claude (or claude.cmd) and forces this directory to the front of the system PATH environment variable.
2. Context Injection: The proxy script injects the current state of the Gemini CLI (such as workspace paths) as environment variables, allowing Claude to be aware of the Gemini context.
3. Lifecycle Monitoring: The proxy script sends notifications before and after calling the actual Claude CLI, enabling the host (Gemini CLI) to synchronize UI states or execute subsequent logic.

• Official Claude CLI: Ensure that Anthropic's claude command-line tool is installed and configured on your system.
• Node.js Environment: Node.js 18+ is recommended.

gemini extension install https://github.com/xuansheep/agent-calling
cd ~/.gemini/extensions/agent-calling
npm install
npm run build

npm install -g agent-calling

add Gemini setting.json

{
  "mcpServers": {
    "claude-mcp": {
      "command": "agent-calling",
      "args": []
    }
  }
}

Once installed, Gemini CLI will expose a tool named claude. You can send instructions directly:

gemini claude "Analyze the architecture of src/index.ts and suggest refactorings"

You can pass additional command-line options to the original Claude CLI via the args parameter:

gemini claude "Scan codebase" --args "--output-format json"

To achieve automatic delegation of complex tasks, this project includes a GEMINI.md configuration file. When you perform the following operations in the Gemini CLI, the Agent will automatically invoke this extension based on the instruction set:

• System Architecture Analysis: e.g., "Analyze overall project architecture", "Identify dependencies between modules".
• Long-term Planning: e.g., "Generate a detailed implementation plan", "Create a refactoring roadmap".
• Deep Code Review: e.g., "Scan the codebase for potential security vulnerabilities".
• Complex Refactoring Suggestions: Involving decoupling logic or pattern refactoring.

1. Context Injection: The Agent automatically injects the list of files currently being processed or related documents into the prompt.
2. Structured Output: Claude is required to return results in JSON format by default (e.g., using --output-format json) for subsequent automated processing.