← 返回 Skills 市场
LLM NeverDie
作者
josephtandle
· GitHub ↗
· v1.2.0
302
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install neverdie
功能描述
Your OpenClaw should never have zero LLMs. NeverDie protects against the silent killer — every model in your fallback chain going down at once. It enforces p...
安全使用建议
This skill appears to do what it claims: it deploys a local Node.js monitor that reads OpenClaw logs, writes local state/alert files, and optionally sends brief Telegram alerts to api.telegram.org. Before installing: (1) verify you are comfortable storing the Telegram bot token/chat ID in ~/.openclaw/workspace/.neverdie-config.json (or as env vars); (2) inspect your gateway.err.log contents to ensure no sensitive data will be incidentally read (the monitor does not transmit log contents, but it scans those files); (3) be aware setup.sh will add a cron job entry to ~/.openclaw/cron/jobs.json so the monitor persists and runs even when LLMs are down; remove that entry manually if you uninstall and the automated uninstall fails; (4) review the bundled scripts (fallback-monitor.js and setup.sh) yourself if you want to confirm there are no changes to the alert text or additional network calls — the provided code only contacts api.telegram.org. Note: there are minor robustness bugs in setup/uninstall node -e calls (a bug in passing CRON_FILE in one uninstall path), which look like sloppy scripting rather than malicious behavior. If you accept those tradeoffs, the skill is coherent with its stated purpose.
功能分析
Type: OpenClaw Skill
Name: neverdie
Version: 1.2.0
The 'neverdie' skill is a resilience utility designed to monitor OpenClaw for LLM failures and notify users via Telegram. It includes a standalone Node.js monitor (`fallback-monitor.js`) and a setup script (`setup.sh`) that configures a persistent cron job. The code demonstrates good security practices by explicitly avoiding the exfiltration of raw log data or API keys, instead sending only hardcoded alert strings to the external Telegram API. All high-risk behaviors, such as file system access and persistence, are directly aligned with the stated purpose of providing out-of-band monitoring.
能力评估
Purpose & Capability
Name/description (LLM resilience, fallback monitoring) match the included artifacts: a Node.js monitor, a setup script, and SKILL.md with instructions to copy the monitor, register a cron job, and optionally configure Telegram. Required binary (node) is appropriate and proportional.
Instruction Scope
Instructions are narrowly scoped: read model IDs from ~/.openclaw/openclaw.json (the provided snippet extracts only the model fields), scan local gateway.err.log for failure patterns, write state/alert files to the workspace, and send short, fixed-format Telegram messages when configured. Caveat: the monitor reads gateway.err.log (local logs can sometimes contain verbose/error payloads), so review your gateway logs if they contain sensitive content. The skill explicitly claims it does not transmit log contents; the code constructs Telegram messages from fixed alert strings, not raw logs.
Install Mechanism
This is instruction-only with bundled scripts; there is no remote download or package installation. Files are copied within the user's ~/.openclaw workspace. No external install URLs or extracted archives are used.
Credentials
Only optional credentials requested are the Telegram bot token and chat ID (stored in a local workspace config file or provided via environment variables NEVERDIE_TELEGRAM_TOKEN / NEVERDIE_TELEGRAM_CHAT_ID). No unrelated cloud keys or secrets are required. The monitor reads ~/.openclaw/openclaw.json only to check model IDs per the instructions, and the code paths shown do not read or transmit API keys.
Persistence & Privilege
The setup registers a recurring systemEvent cron job in ~/.openclaw/cron/jobs.json to run the monitor every 5 minutes; this is expected for a standalone monitor and is within the skill's scope. The monitor writes state and alert files to the workspace. It does not modify other skills or global system configuration beyond the OpenClaw cron/jobs.json entry.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install neverdie - 安装完成后,直接呼叫该 Skill 的名称或使用
/neverdie触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.0
Security: Telegram alerts now contain only fixed hardcoded strings — no log excerpts or error details are ever sent externally. Log details stay in local alert file only.
v1.1.0
Security hardening: redact API keys/tokens from log excerpts before Telegram delivery, config isolation (only reads model IDs, never credentials), explicit security documentation, connection error detection
v1.0.0
Initial release: provider-diverse fallback chains, standalone monitor that works without any LLM, Telegram alerts, Ollama safety net
元数据
常见问题
LLM NeverDie 是什么?
Your OpenClaw should never have zero LLMs. NeverDie protects against the silent killer — every model in your fallback chain going down at once. It enforces p... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 302 次。
如何安装 LLM NeverDie?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install neverdie」即可一键安装,无需额外配置。
LLM NeverDie 是免费的吗?
是的,LLM NeverDie 完全免费(开源免费),可自由下载、安装和使用。
LLM NeverDie 支持哪些平台?
LLM NeverDie 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 LLM NeverDie?
由 josephtandle(@josephtandle)开发并维护,当前版本 v1.2.0。
推荐 Skills