← 返回 Skills 市场
yes999zc

Gateway Monitor

作者 yes999zc · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
312
总下载
0
收藏
1
当前安装
3
版本数
在 OpenClaw 中安装
/install gateway-monitor
功能描述
Provides real-time monitoring, log search, service status, alerts, and one-click config restore for OpenClaw Gateway and related services.
使用说明 (SKILL.md)

Gateway Monitor - OpenClaw 监控面板

实时监控 OpenClaw Gateway 状态、日志检索、服务健康检查的一站式监控面板。

功能特性

  • 实时监控：Gateway 运行状态、资源使用、会话上下文
  • 日志检索：错误/警告高亮，支持关键字搜索和过滤
  • 服务状态：launchd 服务、LiteLLM、oMLX、acpx
  • LiteLLM 按需唤起：默认可保持停止，支持自动唤起或手动唤起/停止
  • 告警系统：基于错误频率、资源消耗的自动告警
  • 一键还原：配置出错时可从备份恢复
  • 皮肤主题：深色 / 浅色 / 跟随系统，响应式布局

快速开始

安装

# 克隆项目
git clone https://github.com/yes999zc/gateway-monitor.git
cd gateway-monitor

# 无需依赖，直接运行
node server.js

# 浏览器访问
open http://127.0.0.1:18990

环境变量配置

# 可选配置
export PORT=18990                      # 服务端口（默认 18990）
export OMLX_MODELS_URL=http://127.0.0.1:9981/v1/models  # oMLX 模型端点
export OMLX_API_KEY=8888               # oMLX API 密钥
export LITELLM_BASE_URL=http://127.0.0.1:4000  # LiteLLM 端点
export LITELLM_CONTAINER_NAME=litellm-omlx  # LiteLLM docker 容器名
export LITELLM_AUTO_WAKE_DEFAULT=0     # 是否默认自动唤起（0/1）

API 端点

  • GET / - 仪表盘页面
  • GET /api/summary - 聚合状态快照
  • GET /api/logs - 日志列表
  • GET /api/gateway-status - Gateway 状态
  • GET /api/launchd-status - launchd 服务状态
  • GET /api/restore-config?confirm=true - 恢复配置
  • GET /api/gateway-restart?confirm=true - 重启 Gateway
  • GET /api/litellm-status?autoWake=1 - LiteLLM 状态（可自动唤起）
  • GET /api/litellm-control?action=wake|start|stop|restart&confirm=true - 控制 LiteLLM 容器
  • GET /api/omlx-capabilities - oMLX 能力检测（模型/VLM/Embedding/Rerank）
  • GET /api/litellm-wake - LiteLLM 按需唤起
  • GET /api/omlx-update?check=1 - 检查 oMLX 更新

监控面板截图

Dashboard

使用场景

  1. Gateway 健康检查：实时监控 Gateway 运行状态、token 使用情况
  2. 日志排查：快速定位错误日志，支持关键字搜索
  3. 配置恢复：配置出错时一键从备份恢复
  4. 服务管理：LiteLLM、oMLX 等服务状态监控与控制

安全说明

  • 密钥脱敏显示：API key 首尾保留，中间用 *** 填充
  • 恢复配置需要二次确认（前端弹窗 + URL 参数）
  • 重启 Gateway 需要二次确认

后台运行

# 使用 launchd 托管（推荐）
cp bin/ai.openclaw.gateway-monitor.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/ai.openclaw.gateway-monitor.plist

# 手动后台运行
nohup node server.js > gateway-monitor.log 2>&1 &

更新日志

v1.0.1

  • 改进 UI 界面设计
  • 新增快照捕获功能
  • 增强监控能力检测

v1.0.0

  • 初始发布
  • Gateway 状态监控
  • 日志检索与告警系统
  • 一键配置恢复

许可证

MIT License

贡献

欢迎提 Issue 和 PR！

安全使用建议
Do not blindly run the commands in SKILL.md. The published skill bundle contains only instructions, not the code it tells you to run; it asks you to clone and execute a repository and to install a persistent launchd agent, and it references API keys and container controls that are not declared in the metadata. Before installing: (1) review the actual repository code (https://github.com/yes999zc/gateway-monitor) and the plist to ensure there are no network exfiltration endpoints or opaque behavior; (2) confirm why the skill metadata omits required binaries and env vars (node, git, launchctl, docker); (3) avoid putting real API keys in global env vars — use scoped/test keys and run the service in an isolated environment (VM/container) until you audit it; (4) verify what /api/restore-config and /api/gateway-restart actually do and whether they require elevated privileges; and (5) prefer an officially released package (release tarball with checksums or signed release) rather than cloning a live repo for production installation. If you want, provide the repository contents (server.js and bin files) and I can re-evaluate the code behavior specifically.
功能分析
Type: OpenClaw Skill Name: gateway-monitor Version: 1.0.3 The skill bundle describes a monitoring dashboard with high-privilege capabilities, including service control (restarting Gateway/LiteLLM) and configuration restoration. These actions are triggered via simple GET requests (e.g., `/api/restore-config?confirm=true` and `/api/gateway-restart?confirm=true` in `SKILL.md`), which poses a risk of accidental execution by the AI agent or CSRF. While the stated intent is administrative, the broad system-level permissions and the lack of source code to verify security claims (like key masking) warrant a suspicious classification.
能力评估
⚠ Purpose & Capability
The skill claims to be a Gateway monitoring dashboard, which plausibly needs access to local services, logs, and control actions. However the package metadata declares no required binaries or env vars while SKILL.md explicitly requires git, node, launchctl, and references Docker/container control and API keys. skill.yaml also references a build entry/server.js but no code is bundled. The declared requirements do not match the actions the instructions ask you to perform.
⚠ Instruction Scope
SKILL.md instructs the user to git clone a GitHub repo and run `node server.js`, copy a plist into ~/Library/LaunchAgents and run launchctl, and provides HTTP endpoints that perform config restore and gateway restart. It also references local admin-type operations (start/stop/restart services, wake containers) and sensitive env vars (OMLX_API_KEY). These instructions go beyond passive monitoring and include potentially disruptive privileged actions; the skill metadata did not surface or justify these operations.
⚠ Install Mechanism
Although the registry package is instruction-only (no install spec), the runtime instructions explicitly tell the user to download and run code from https://github.com/yes999zc/gateway-monitor. That is effectively a download-and-execute flow: code is fetched at runtime from an external repo rather than being provided for review in the skill bundle. This increases risk because the code you will execute is not included in the skill for pre-install review.
⚠ Credentials
The SKILL.md lists several environment variables (PORT, OMLX_MODELS_URL, OMLX_API_KEY, LITELLM_BASE_URL, LITELLM_CONTAINER_NAME, LITELLM_AUTO_WAKE_DEFAULT) including an API key, but the skill's registry metadata declares no required env vars or primary credential. Requesting API keys and container control without declaring them in metadata is a disproportionate and unexplained gap.
ℹ Persistence & Privilege
The skill does not set always:true and allows normal autonomous invocation. However the instructions explicitly recommend installing a LaunchAgents plist (copying to ~/Library/LaunchAgents and loading it) which would persist a service on the user's machine. Persisting a monitoring agent is plausible for this purpose, but it increases the blast radius if the code is untrusted — the skill package does not include the plist or service code for review.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install gateway-monitor
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /gateway-monitor 触发
  4. 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
v1.0.3
Sanitized package and synced latest gateway-monitor project updates
v1.0.2
Improve UI, add snapshot capture feature, enhance monitoring capabilities
v1.0.1
Improve UI, add snapshot capture feature, enhance monitoring capabilities
元数据
Slug gateway-monitor
版本 1.0.3
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 3
常见问题

Gateway Monitor 是什么？

Provides real-time monitoring, log search, service status, alerts, and one-click config restore for OpenClaw Gateway and related services. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 312 次。

如何安装 Gateway Monitor？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install gateway-monitor」即可一键安装，无需额外配置。

Gateway Monitor 是免费的吗？

是的，Gateway Monitor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Gateway Monitor 支持哪些平台？

Gateway Monitor 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 Gateway Monitor？

由 yes999zc（@yes999zc）开发并维护，当前版本 v1.0.3。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463942 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259883 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200739 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191401 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190375 · by oswalpalash

💬 留言讨论