glm

🥈Silver

CLI tool for switching between GLM-4.7/4.6 and Claude Code. Manage API tokens and set up AI-powered dev environments with one command. Ideal for ops teams automating AI workflows.

2710Updated 1mo ago

Intermediate30min to implementautomation

Saves ~30 min per use

Quick InstallView Source

git clone https://github.com/xqsit94/glm.git

Works with:

Claude

Overview

About This Skill

GLM CLI is a command-line interface that enables Claude Code to use GLM models (glm-5, glm-4.7, glm-4.6, and others) through BigModel API without persistent configuration changes. It works by setting temporary environment variables for each Claude session, allowing you to switch between models at launch time while keeping your system configuration clean. The tool includes secure token management, automatic Claude Code installation, flag passthrough to the claude CLI, and a YOLO mode to skip permission prompts for faster workflows. Built for development teams and ops engineers who need to integrate multiple AI models into automated workflows without managing complex persistent configs.

How to Use

Install via the quick installer: `curl -fsSL https://raw.githubusercontent.com/xqsit94/glm/main/install.sh | bash`. Run `glm token set` to securely store your BigModel API token. Launch Claude with GLM using `glm` (default glm-5 model) or `glm --model glm-4.5-air` for a specific model. Use `glm --yolo` to skip permission prompts, or pass any claude flags directly: `glm --allowedTools "Bash,Read"`.

Use Cases

Switch between GLM and Claude models per-session without system-wide config changes

Automate AI-powered development environments with model selection at launch time

Manage authentication tokens securely across multiple AI models

Bypass permission prompts in automated CI/CD pipelines using YOLO mode

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/xqsit94/glm

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 need to switch my AI model from GLM-4.6 to Claude Code for a [PROJECT] in the [INDUSTRY] sector. Can you guide me through the process using the GLM CLI tool? Also, I need to manage my API tokens for [COMPANY] securely.

Example Output

# Switching AI Models with GLM CLI Tool

## Step 1: Install GLM CLI

First, ensure you have the GLM CLI tool installed. You can download it from the official repository or use the following command:

```bash
pip install glm-cli
```

## Step 2: Configure API Tokens

Before switching models, you need to configure your API tokens. Use the following command to set up your tokens:

```bash
glm config set --api-token YOUR_API_TOKEN
```

## Step 3: Switch to Claude Code

To switch from GLM-4.6 to Claude Code, run the following command:

```bash
glm switch --model claudecode
```

## Step 4: Verify the Switch

Finally, verify that the switch was successful by checking the current model:

```bash
glm status
```

This should display the current model as Claude Code.