ai-quota-check
Unified quota monitor and intelligent model recommender for all providers.
Output Instructions
IMPORTANT: When executing this skill, display the script output EXACTLY as-is in markdown format. Do NOT summarize or rephrase the output. The script produces a formatted dashboard that should be shown directly to the user.
Example execution:
CODEBLOCK0
Then copy the entire output and send it as your response.
Features
- 1. Provider Login Check - Detects which providers are logged in
- Unified Quota Dashboard - Antigravity + Copilot + OpenAI Codex
- Task-based Recommendations - Optimal model selection with fallback
- Reset Detection - Identifies models ready for ping (new cycle)
- Risk Level Info - Warns about weekly caps and lockout risks
Usage
CODEBLOCK1
Model Routing Rules
Coding / Debugging
| Priority | Model | Fallback Condition |
|---|
| 1st | INLINECODE0 | - |
| 2nd |
openai-codex/gpt-5.2-codex | Primary < 20% |
| 3rd |
google-antigravity/gemini-3-pro-high | All above < 20% |
Complex Reasoning / Analysis
| Priority | Model | Fallback Condition |
|---|
| 1st | INLINECODE3 | - |
| 2nd |
github-copilot/claude-4.6-opus | Primary < 20% |
| 3rd |
github-copilot/claude-3.5-opus | If 4.6 unavailable |
| 4th |
openai-codex/gpt-5.3 | All above < 20% |
| 5th |
openai-codex/gpt-5.2 | Last fallback |
Fallback Threshold
Default: 20% - Switches to fallback when primary drops below this.
Cron Integration
This skill is designed to be called periodically via Cron for:
- - Quota monitoring
- Reset detection (ping optimization)
- Automatic model switching recommendations
ai-quota-check
所有提供商的统一配额监控与智能模型推荐器。
输出说明
重要提示： 执行此技能时，请原样以Markdown格式显示脚本输出。不要对输出进行总结或改写。脚本会生成格式化的仪表盘，应直接展示给用户。
示例执行：
bash
node skills/ai-quota-check/index.js --current-model=<当前模型名称>
然后复制完整输出并作为你的回复发送。
功能特性
- 1. 提供商登录检测 - 检测哪些提供商已登录
- 统一配额仪表盘 - Antigravity + Copilot + OpenAI Codex
- 基于任务的推荐 - 最优模型选择及备用方案
- 重置检测 - 识别可进行Ping操作的模型（新周期）
- 风险等级信息 - 警告每周上限和锁定风险
使用方法
bash
完整仪表盘
node skills/ai-quota-check/index.js
特定任务推荐
node skills/ai-quota-check/index.js --task=coding
node skills/ai-quota-check/index.js --task=reasoning
模型路由规则
编码/调试
| 优先级 | 模型 | 备用条件 |
|---|
| 1 | openai-codex/gpt-5.3-codex | - |
| 2 |
openai-codex/gpt-5.2-codex | 主模型 < 20% |
| 3 | google-antigravity/gemini-3-pro-high | 以上所有 < 20% |
复杂推理/分析
| 优先级 | 模型 | 备用条件 |
|---|
| 1 | google-antigravity/claude-opus-4.6-thinking | - |
| 2 |
github-copilot/claude-4.6-opus | 主模型 < 20% |
| 3 | github-copilot/claude-3.5-opus | 若4.6不可用 |
| 4 | openai-codex/gpt-5.3 | 以上所有 < 20% |
| 5 | openai-codex/gpt-5.2 | 最后备用方案 |
备用阈值
默认值：20% - 当主模型配额低于此值时切换到备用模型。
定时任务集成
此技能设计为通过Cron定时调用，用于：
- - 配额监控
- 重置检测（Ping优化）
- 自动模型切换推荐
