Cachebeat

Keep the Anthropic prompt cache warm by firing a tiny heartbeat only after N minutes of true session inactivity (any exchange resets the clock), so the next real turn reads the conversation at cached price / cached quota instead of a full uncached re-read. The heartbeat is a background Stop hook this skill registers (asyncRewake) - it re-arms itself after every turn, with no tool calls and no permission prompts. Use when the session may sit idle (training runs, CI, downloads, the user stepping away) longer than the cache TTL. Args - idle threshold in minutes (default 50), optional max hours (d

85 stars 10 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ARahim3/cachebeat --skill cachebeat
Manual install
git clone --depth 1 https://github.com/ARahim3/cachebeat.git /tmp/cachebeat
mkdir -p ~/.claude/skills
cp -r /tmp/cachebeat/. ~/.claude/skills/cachebeat

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# cachebeat — prompt-cache keepalive heartbeat

## What you do when invoked

`/cachebeat [minutes] [hours]` arms the heartbeat; `/cachebeat stop` turns it off. **There is nothing
for you to run.** The heartbeat is the Stop hook in this skill's frontmatter: Claude Code registered it
when this skill loaded, and when this turn ends the hook reads these same arguments from the transcript.

- `minutes`: idle threshold — how long the session may sit silent before a beat. Default **50**,
  clamped to **5–55** (past ~55 the 1-hour cache TTL can lapse before a beat lands).
- `hours`: auto-stop deadline. Default **8**, clamped to 1–24 — the abandoned-session guard: every beat
  costs a small cached-price request, so a forgotten heartbeat must end itself.
- `stop` (or `off`): disarm.

Reply in **ONE line** and call no tools — arming: the idle threshold, the auto-stop time, and that
`/cachebeat stop` ends it sooner; stopping: that it is off. Nothing more.

If the user asks in plain words to start, change or stop the heartbeat, invoke this skill (Skill tool)
with the matching arguments: the hook only reads `/cachebeat` invocations.

## When the heartbeat wakes you

A system reminder starting with `[cachebeat]` (on some Claude Code versions: "Stop hook blocking error …"
followed by the same text) comes from the hook. It is not the user, and it is not an error.

- **"idle heartbeat …"** — reply with exactly `.` and nothing else: no tools, no summary, no status. The
Read the full skill on GitHub

Details

Skill name
cachebeat
License
MIT
Repo updated
13 October 2026

FAQ

What does the Cachebeat skill do?

Keep the Anthropic prompt cache warm by firing a tiny heartbeat only after N minutes of true session inactivity (any exchange resets the clock), so the next real turn reads the conversation at cached price / cached quota instead of a full uncached re-read. The heartbeat is a background Stop hook this skill registers (asyncRewake) - it re-arms itself after every turn, with no tool calls and no permission prompts. Use when the session may sit idle (training runs, CI, downloads, the user stepping away) longer than the cache TTL. Args - idle threshold in minutes (default 50), optional max hours (d

How do I install the Cachebeat skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ARahim3/cachebeat --skill cachebeat. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cachebeat popular?

It lives in ARahim3/cachebeat, which has 85 GitHub stars and 10 forks.

Related skills

Scammer

81

naxiaoduo/Scammer.skill

骗子.skill — 把骗局套路蒸馏成 AI,检测可疑消息,定位当前阶段,预判下一步。Distill scam patterns into AI, detect suspicious messages, locate current phase, predict next move.

AI, LLMs & Agents12

Deeprefine

91

HKUST-KnowComp/DeepRefine-Skill

Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

AI, LLMs & Agents

Turkce Humanizer

93

bushrabeg/turkce-humanizer

Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını yerleştirir. "Türkçeleştir," "AI kokusunu at," "bu Türkçe metni doğallaştır," "humanize et" gibi ifadelerle veya AI-üretimi görünen Türkçe paragraf sunulduğunda tetiklenir.

AI, LLMs & Agents

Stop AI Slop Zh

99

VincentOld/stop-slop-zh

识别并消除中文 AI 写作的典型痕迹——套话、排比三件套、名词化、抽象主语、金句收尾、总分总八股——让文本读起来像有人在说话,而不是 AI 在生成。适用于公众号、小红书、知乎、公文、学术摘要、产品文案、邮件等所有中文长短文写作场景。

AI, LLMs & Agents

Checkup

95

agentvitals/checkup

Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI agent 做一次专业体检(AgentVitals · AI体检)。当用户说"做个体检 / 测测你自己 / checkup / 看看你多稳 / 测福祉 / 测骨气"时使用。

AI, LLMs & AgentsIn 1 list

Natural Talk

99

chengzhi-c/natural-talk

自然人味交互与去 AI 腔。消除客服腔、谄媚评判、免责包装、强制平衡与假大空套话;提供专业、平视的同行交流姿态、文本防套路准绳与叙事创作工法(支持日常对话、代码沟通与深度小说创作);学术公文营销文案不适用。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.