korta-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 landercortazarromero/korta-model-usageInstall CodexBar (brew cask):
Install CodexBar (brew cask)Requires:
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 7, 2026
A product manager at an AI-first startup needs to compare per-model usage costs for Codex and Claude to allocate budgets across squads. They run the script daily with --mode all and --format json to feed a cost dashboard. This helps justify model selection decisions and prevent overspending.
An engineering manager wants a quick, scriptable summary of the most recent model used and its cost for each team. Using --mode current, they automate Slack alerts when the current model's cost exceeds a threshold. This keeps daily burn visible without manual log inspection.
A freelance data science consultant uses the skill to pull per-model cost breakdowns from client CodexBar logs and generate monthly PDF reports. They combine --mode all with --format json to create charts showing which models drive costs. This adds transparency to AI infrastructure invoices.
A FinOps analyst at a mid-size enterprise uses the bundled Python script to analyze cost JSON from CodexBar, focusing on per-model expenses for Codex and Claude. They use --provider both iteratively and export to Excel for vendor negotiations. This helps identify cost anomalies and optimize licensing.
A DevOps engineer integrates the skill into CI/CD pipelines to enforce model usage budgets. They call the script with --mode current and --format json, parsing output to block deployments if the most recent model cost exceeds limits. This prevents runaway AI expenses in staging and production.
A subscription-based platform that ingests CodexBar cost logs and provides per-model cost analytics, alerts, and forecasting for AI teams. It uses this skill as a core data collector to normalize model usage data across providers. Customers pay monthly per seat or per monitored model.
A professional services firm that audits clients' AI model usage and recommends cost optimizations. Consultants use this skill to extract per-model cost data from CodexBar, then deliver actionable reports and implementation roadmaps. Engagements are project-based or retainer-based.
An open-source CLI tool that wraps this skill to provide a user-friendly interface for model cost summaries. The core tool is free, but enterprise support, custom integrations, and hosted dashboards are offered as paid add-ons. Revenue comes from support contracts and premium features.
💬 Integration Tip
Ensure CodexBar CLI is installed via the provided brew cask on macOS, and pipe cost JSON directly to the script using --input - for seamless automation in scripts or CI pipelines.
Scored Oct 7, 2026
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。
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。
OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI RES...