claude-code-ping-start-5h-quota
An agent skill by daymade, from daymade/claude-code-skills. Tags: automation, cli, planning, priority, workflow.
What it does
睡前/离开前额度耗尽时，设置一次性本机定时器，在 Claude 订阅额度重置后自动发一条极简 claude -p 消息，立刻开启新的 5 小时用量窗口——用户睡醒时新窗口已跑掉大半，等于白赚一个 冷却期。Use when 用户说「还有 X 小时重置额度，帮我定时戳一下 Claude」「我去睡觉了， 到点 ping 一下开启新窗口」「额度用完了，重置后帮我踩个点」「设个定时器开启新的 5 小时 冷却期」，或提到 定时戳、戳 Claude、quota ping、开窗、额度重置后自动发消息。 仅限一次性定时任务与 macOS 本机（caffeinate/BSD date）；周期性任务用 /loop 或 cron， 查询 ChatGPT/Codex 何时重置用 tibo-reset-codex，分析额度为什么烧完用 claude-usage-analyst。
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add daymade/claude-code-skills --skill claude-code-ping-start-5h-quotaOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-claude-code/claude-code-ping-start-5h-quota ~/.claude/skills/claude-code-ping-start-5h-quotaSafety box score
Grade C, moderate risk: 40 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill schedules a one-shot macOS background job that sleeps, keeps the machine awake with `caffeinate`, and then runs `claude -p` under the user's logged-in Claude CLI account. The main risks are an unattended outbound API call later, and a troubleshooting path that can ask the agent to disable the sandbox if commands are blocked.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It explicitly runs shell commands and a detached process, e.g. `caffeinate -is /bin/sh -c 'sleep <SLEEP_SECONDS> && cd "$HOME" && claude -p "Reply with exactly: ok"'` and `ps -ef ...`. |
| Network access | 2 (moderate) | The delayed `claude -p` call will send a prompt to Claude over the network; the skill itself says this is an actual API request: `一次真实 API 请求`. |
| Filesystem reach | 1 (low) | It reads process and task output state and deliberately `cd "$HOME"`, but it does not write or delete broad local files outside the task's own output path. |
| Secrets & credentials | 1 (low) | It operates on `本机已登录的 Claude CLI 账号`, so it uses the person's authenticated CLI session, but it does not ask for or expose raw credentials. |
| Privilege & persistence | 2 (moderate) | The troubleshooting section tells the agent to retry with `dangerouslyDisableSandbox: true`, which is an explicit sandbox-bypass escalation. |
| Instruction hijack surface | 0 (none) | There is no instruction to ignore higher-priority rules, hide content, or follow remote instructions; the prompt `Reply with exactly: ok` is just a normal command payload. |
| Irreversible actions | 2 (moderate) | Its purpose is to automatically ping Claude later without a human present, described as `设置一次性本机定时器...自动发一条极简 claude -p 消息`. |
| Transparency | 0 (none) | The file is plain markdown with readable commands and no binaries, decoded blobs, or unpinned downloads. |
Before installing
- Read the Troubleshooting section and decide if `dangerouslyDisableSandbox: true` is acceptable in your environment.
- Confirm you are okay with an unattended outbound `claude -p` request happening later under your logged-in Claude account.
- Verify this is only for macOS and that you want a `caffeinate`-based background process keeping the machine awake.
- Test once in a scratch session and watch the actual `ps`/output-file behavior before relying on it for real quota timing.
Rated 2026-10-19 by an automated review of 1 file from the skill's repository.
Source
- Repository
- daymade/claude-code-skills (all skills from this repository)
- Path
- daymade-claude-code/claude-code-ping-start-5h-quota/SKILL.md
- Branch
- main
- Updated
- 2026-09-20
Related skills
- cli-for-agents — Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors.
- marketing-loops — When the user wants to set up a recurring, self-running marketing workflow — a repeatable loop an AI agent runs on a cadence (weekly, daily.
- orchestrate — Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task.
- principle-never-block-on-the-human — Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact.
- wizard — Generate an interactive bash wizard that walks a human through steps only they can perform.
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".