agentleFS
uvwtuvwt/agentdock-skills/skills/codex-usage/SKILL.md

codex-usage

Skill6 starsChanged 2 months agoApache-2.0View on GitHub

Use this skill when checking the current macOS user Codex CLI account state or Codex usage quota.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Codex Usage

读取当前 macOS 用户的 Codex CLI 登录状态,并查询 ChatGPT Codex 订阅额度。只提供手动查询,不创建或管理定时任务。

动作

  • status:检查 ~/.codex/auth.json 是否存在、访问令牌是否仍有效、是否能取得 account ID。所有凭据均脱敏。
  • query:查询当前套餐、session/weekly 窗口、credits、spend_control、可用重置次数、额外限额、code review 限额、promo/referral 等接口字段,并返回打码后的 raw_response_redacted。

Authentication

默认读取系统当前用户的 ~/.codex/auth.json。由于 AgentDock 的 HOME 可能指向 workspace,Skill 通过系统用户数据库定位真实用户目录。可通过 CODEX_HOME 覆盖 Codex 配置目录。

Security

  • 不接受 token 作为输入。
  • 不输出 access token、refresh token、ID token、Authorization header 或真实 account ID、真实 user ID 或真实邮箱。
  • 只读认证文件,不修改 Codex 登录状态。
  • 只访问 ChatGPT Codex usage 接口。

辅助脚本执行

Skill 本体是本说明文档。确需调用包内辅助脚本时,在 Skill 包根目录使用相对路径执行;运行宿主负责切换到包根目录并把所需变量注入当前子进程。

printf '%s' '{"skill_action":"<动作>"}' | python3 run.py

输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。

动作用途
statusCheck local Codex CLI login state without revealing credentials.
queryQuery Codex usage and expose the full redacted usage API payload plus parsed quota fields.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.