by aqua5230 · Codex Skill · ★ 285
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is usage safe to install? View the security audit →
usage 繁體中文 · English 是一個 macOS menu bar（螢幕右上角的選單列）小工具，把 Claude Code 跟 Codex 的用量釘在你的螢幕右上角。點開可以看到 Session、Weekly、各專案用量（今日 / 7 日 / 月），以及今日 token 用量與成本估算。 不呼叫 Anthropic / OpenAI 的 API（接口）、也不讀 Keychain（macOS 內建的密碼保險箱），所以不會發生「自己每分鐘 ping 一次也算用量」這種事。 它怎麼拿到你的用量數字 用量數字來自 Claude Code 跟 Codex 在你本機留下的檔案，不呼叫 Anthropic / OpenAI 的 API。唯一的例外：估算 Codex 成本時需要 token 單價表，如果本機沒有快取（），會嘗試從公開的 LiteLLM 價格表 下載一次並存起來，7 天後過期再抓。下載失敗的話會用內建的 fallback 價格，不影響用量百分比的顯示。首次啟動若沒快取會同步抓一次，網路慢時可能要等 10 秒。 Claude Code 用量 usage 會幫你裝一個小腳本，這個小腳本叫做 statusLine hook（hook 就是「事件觸發點」，每次 Claude Code 刷新狀態列就會自動跑一次的小程式）。流程是這樣： Claude Code 每次更新狀態列時，會把「這 5 小時用了百分之幾、這 7 天用了百分之幾」這類資訊整理成 JSON 透過標準輸入（stdin）餵給 hook hook 把 JSON 寫進 這個檔 usage 主程式去讀這個檔
| Stars | 285 |
| Forks | 45 |
| Language | Python |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 68.108263423977/100 |
| Last Updated | 2026-08-08 |
| Created | 2026-05-17 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
Looking for a usage alternative? If you're comparing usage with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts
Explore other popular codex skill tools:
usage is macOS menu bar & Windows tray app pinning Claude Code, Codex & Antigravity quota, burn rate, and cost to your screen. Local-first, no LLM API calls. HTML reports, 10 themes.. It is categorized as a Codex Skill with 285 GitHub stars.
usage is primarily written in Python. It covers topics such as agpl, ai-tools, anthropic.
You can find installation instructions and usage details in the usage GitHub repository at github.com/aqua5230/usage. The project has 285 stars and 45 forks, indicating an active community.
usage is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to usage on Agent Skills Hub include toktrack, headroom, agent-sessions. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.