agent-calling
Gemini cli agent 增强组件，通过路径劫持和上下文注入在 Gemini CLI 中调用 其他模型。
Open source Open in the app JSON README (API)
About
Gemini cli agent 增强组件，通过路径劫持和上下文注入在 Gemini CLI 中调用 其他模型。
Details
- Kind
- Plugins
- Topic
- AI, RAG & memory
- Publisher
- xuansheep
- Origin
- gemini
- Category
- ferramentas
- Version
- 0.1.0
- Last push
- 2026-03-10T07:13:48Z
- Repository state
- ativo
- Language
- JavaScript
- Added
- 2026-08-30 14:13:39
- Updated
- 2026-08-30 14:13:39
- Origin id
xuansheep/agent-calling-beta
README
# 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](README.md) | [简体中文](README.zh-CN.md)
- [x] Claude code
- [ ] Codex
---
## Core Architecture
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.
---
## Installation
### 1. Prerequisites
* **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.
### 2. Method 1: Gemini CLI Direct Installation
```bash
gemini extension install https://github.com/xuansheep/agent-calling
cd ~/.gemini/extensions/agent-calling
npm install
npm run build
```
### 3. Method 2: Via npm
```bash
npm install -g agent-calling
```
add Gemini setting.json
```json
{
"mcpServers": {
"claude-mcp": {
"command": "agent-calling",
"args": []
}
}
}
```
---
## Usage
### 1. Direct Command Invocation
Once installed, Gemini CLI will expose a tool named `claude`. You can send instructions directly:
```bash
gemini claude "Analyze the architecture of src/index.ts and suggest refactorings"
```
### 2. Advanced Parameter Passthrough
You can pass additional command-line options to the original Claude CLI via the `args` parameter:
```bash
gemini claude "Scan codebase" --args "--output-format json"
```
---
## Automation (GEMINI.md)
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:
### Delegation Criteria
- **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.
### Automated Execution Protocol
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.