/SKILL.md
统一监控 MiniMax、Codex (ChatGPT Plus) Coding Plan 用量。支持双限制显示(7天+5小时)、10格 Emoji 进度条、北京时间重置时间显示,支持 Verbose 模式查看各账号独立用量。当需要查询或监控各平台 Coding Plan 剩余额度时触发此技能。
npx skillsauth add shiquda/coding-plan-monitor-skill coding-plan-monitorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
统一监控多个 Coding Plan 平台的用量情况。
| 平台 | 限制类型 | |------|----------| | MiniMax | 5小时 | | Codex (ChatGPT Plus) | 7天 + 5小时(多账号平均) | | Kimi Coding Plan | 7天 + 5小时(同一池额度的双重限制) | | Webshare Proxy | 流量上限(GB) |
# 1. 复制配置
cp .env.example .env
# 2. 编辑 .env 填入 Token(详见 references/)
# 3. 运行(默认简洁模式)
./scripts/check_all_usage.sh
# 4. Verbose 模式 - 显示每个账号的独立用量
./scripts/check_all_usage.sh -v
Codex 支持多账号,Verbose 模式下会先输出每个账号的 7d/5h 用量,再输出综合平均值:
📊 Coding Plan 用量汇总 - Verbose 模式 (2026-04-16)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[🔴] [email protected] (7d: 73%, 5h: 93%)
7d → 剩余 27 | 11h 9m 后刷新
5h → 剩余 7 | 1h 8m 后刷新
[✅] [email protected] (7d: 1%, 5h: 6%)
7d → 剩余 99 | 6d 23h 后刷新
5h → 剩余 94 | 4h 33m 后刷新
---
✅ Codex-7d ███░░░░░░░
📈 37/100 (37%) | 💰 剩余 63 | 3d 17h 后刷新
✅ Codex-5h █████░░░░░
📈 49/100 (49%) | 💰 剩余 51 | 2h 56m 后刷新
...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
平均规则:所有账号的用量取平均值(而非最大值),更好地反映总体剩余能力。
各平台 Token 获取方式:
Codex 通过 CLIProxyAPI 的 Management API 自动发现所有已登录账号,无需手动配置每个账号:
# .env 中配置
CODEX_CLI_PROXY_URL=http://100.88.53.43:8317
CODEX_MANAGEMENT_KEY=your-management-key
CLIProxyAPI 服务器需要开启 allow-remote-management: true 才能远程访问。
📊 Coding Plan 用量汇总 (2026-03-10)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ Kimi Coding Plan-7d ███░░░░░░░
📈 30/100 (30%) | 💰 剩余 70 | 17:44
✅ Kimi Coding Plan-5h ░░░░░░░░░░
📈 0/100 (0%) | 💰 剩余 100 | 19:44
✅ MiniMax ░░░░░░░░░░
📈 10/600 (2%) | 💰 剩余 590 | 4h38m
✅ Codex-7d ███░░░░░░░
📈 37/100 (37%) | 💰 剩余 63 | 3d 17h 后刷新
✅ Codex-5h ████░░░░░░
📈 49/100 (49%) | 💰 剩余 51 | 2h 56m 后刷新
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kimi 7d 和 Kimi 5h 不是两池独立额度,而是同一套使用的双重限制。
这意味着:
如果 7d 已经偏高(如 >70%)
如果 7d 还健康
对用户的表述要求
❌ Kimi 5h 快刷新了,现在最适合用 Kimi
✅ Kimi 5h 虽然快刷新了,但 7d 已经到 76%,不建议因为短期窗口重置就继续烧 Kimi。现在优先 MiniMax / Codex。
对用户回复时:
./scripts/check_all_usage.sh(或 check_all_usage.sh -v 询问详细用量时)当用户说:
默认理解为:
./scripts/check_all_usage.sh./scripts/check_all_usage.sh -v不要只因为 5h 快刷新,就给出误导性建议。
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.