菜单
Query per-model AI usage and cost data from CodexBar local cost logs. Supports current model, all models, and summary modes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Aggregate AI token usage and costs across all coding assistants (Claude Code, OpenCode, Codex) on the gateway host.
Upload files to files.shuv.me via the shuvdex MCP gateway. Accepts base64 content or a source URL.
Reusable template for packaging a local script as a module_runtime MCP tool.
Manage Make.com (Integromat) scenarios, connections, data stores, and webhooks via the full REST API.
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.
| name | model-usage |
| description | Query per-model AI usage and cost data from CodexBar local cost logs. Supports current model, all models, and summary modes. |
Get per-model usage cost summaries from CodexBar's local cost logs on the gateway host.
Input (JSON):
provider — "codex" or "claude" (default: "codex")mode — "current" (most recent model), "all" (all models), or "summary" (totals only)days — number of days to include (default: all time)model — override to query a specific model nameOutput (JSON):
provider — which provider was queriedmode — which mode was usedmodels — array of { model, cost } entries (for current/all modes)totalCost — total cost across all modelsdurationMs — execution timecodexbar CLI installed on the gateway host