ag-model-usageUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trig...
Install via ClawdBot CLI:
clawdbot install t-atlas/ag-model-usageGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:loadCodeAssist`Calls external URL not in known-safe list
https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:fetchAvailableModelUses known external API (expected, informational)
googleapis.comAI Analysis
The skill interacts with Google's internal sandbox APIs (sandbox.googleapis.com) which appear to be legitimate endpoints for querying model usage data, consistent with its stated purpose of checking quotas for Google Cloud Code Assist. While the external calls are not to standard public APIs, they target Google's own infrastructure and the skill description explicitly mentions using OAuth tokens from a Google auth profile, indicating an intended internal tool rather than credential harvesting or data exfiltration to unauthorized servers.
Generated Mar 20, 2026
Development teams using AI models like Codex or Claude for coding assistance can track real-time usage quotas to avoid hitting limits during critical sprints. This ensures uninterrupted access to AI tools, optimizing productivity and project timelines.
Large organizations with multiple teams using AI models can monitor per-model usage to allocate budgets effectively and prevent overspending. It helps in forecasting costs and ensuring compliance with internal financial policies.
Independent developers or freelancers relying on AI models for client projects can check remaining quotas to plan their work and avoid disruptions. This aids in managing limited resources efficiently across different tasks.
Universities or training centers offering AI tools to students can use this skill to track usage across models, ensuring fair access and preventing abuse. It supports educational goals by maintaining reliable AI resource availability.
Companies offering AI model access via subscriptions can integrate this skill to provide customers with transparent usage dashboards. This enhances customer satisfaction by allowing users to monitor their consumption and plan upgrades.
Consulting firms that help clients optimize AI tool usage can leverage this skill to offer detailed usage reports and recommendations. This adds value by enabling proactive cost management and efficiency improvements.
SaaS providers incorporating AI features into their platforms can use this skill to give users insights into model usage. This drives engagement by helping users maximize their AI investments within the platform.
💬 Integration Tip
Ensure the system has Python3 installed and valid OAuth tokens from Google Antigravity for seamless API access.
Scored Jun 17, 2026
Audited Apr 16, 2026 · audit v1.0
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the...