跳到技能内容
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
词映 AI导航
工具库Skills 技能
我的收藏
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
Skills directory/tirakula07/codex-usage-dashboard/metrics-quality

Codex usage metrics and cost estimates

Design reproducible usage aggregation and tests, handle absent model pricing, and label local usage estimates.

中文

Install in Codex

Codex and a synthetic usage record. The record has no model pricing.

  1. Review `.agents/skills/metrics-quality/SKILL.md` and its requirements at the pinned GitHub commit.
  2. Create `.agents/skills/metrics-quality/` in your project and save the reviewed file as `.agents/skills/metrics-quality/SKILL.md`.
  3. Start Codex from that project's root, then type `$metrics-quality` and select the matching skill.

Example task

Use this synthetic record in the usage dashboard and check the aggregate and cost label.
model="unknown-demo"; inputTokens=300; outputTokens=120; pricing=null; billingSource="local subscription"

What to check

Total usage is 420 tokens. Cost is unknown with no amount. Local subscription usage is labeled estimated. Processing the same record again produces the same results.

Original SKILL.md on GitHub · Updated 2026-11-14

Frequently asked question

How should a Codex usage dashboard handle unknown model costs?

Keep the input and output token totals available and mark the cost unknown when pricing is absent. Label local usage estimated and test that repeated inputs yield identical results.

Related skills from this repository

  • Codex JSONL Usage Parsing with Malformed Records
  • Codex local-first apps and idempotent imports
Browse Codex skills in the Chinese directory
词映 AI 导航Skills 技能
工具分类全部工具已本地化技能选型指南AI 快讯