Rancher assistant for multi-cluster Kubernetes management, troubleshooting, capacity analysis, and resource discovery
npx claudepluginhub futuretea/rancher-assistantRancher assistant for multi-cluster Kubernetes management, troubleshooting, capacity analysis, and resource discovery (Community)
Claude Code 插件,用于 Rancher 多集群 Kubernetes 管理。采用 Sub-Agent + Skill 架构,Skill 负责意图识别,Agent 负责干活,各自独立上下文、支持并行。
┌─────────────────────────────────────────────────────────────┐
│ Skill Layer (触发器) │
│ - 识别用户意图 │
│ - 决定调用哪个 Sub-Agent │
│ - 汇总结果 │
└─────────────────────────────────────────────────────────────┘
│
┌───────────────────┼───────────────────┐
▼ ▼ ▼
┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ Sub-Agent 1 │ │ Sub-Agent 2 │ │ Sub-Agent N │
│ (独立上下文) │ │ (独立上下文) │ │ (独立上下文) │
└──────────────┘ └──────────────┘ └──────────────┘
/plugin marketplace add futuretea/rancher-assistant
/plugin install rancher-assistant@rancher-assistant
/plugin list
安装成功后,你应该能看到 rancher-assistant 在已安装插件列表中。
触发词: "list clusters", "cluster overview", "list projects", "compare clusters", "集群列表", "集群概览"
执行方式:
rancher-cluster-explorer触发词: "diagnose pod", "pod logs", "why is pod failing", "check events", "troubleshoot", "诊断 Pod", "排查问题", "查看日志"
执行方式:
rancher-pod-diagnosticianrancher-deployment-tracker触发词: "node capacity", "cluster capacity", "resource usage", "node health", "容量", "节点分析", "资源使用"
执行方式:
rancher-node-analyzer触发词: "rollout history", "deployment changes", "watch deployment", "diff", "what changed", "部署历史", "变更", "跨集群对比"
执行方式:
rancher-deployment-tracker触发词: "list resources", "get all", "dependency tree", "what depends on", "资源列表", "依赖关系", "资源清单"
执行方式:
rancher-resource-scout触发词: "inspection", "inspect cluster", "health check", "patrol", "巡检", "集群巡检", "健康检查", "集群体检", "日常巡检"
执行方式:
rancher-cluster-inspectorrancher-assistant/
├── .claude/
│ └── settings.local.json # 工具权限配置
├── .claude-plugin/
│ ├── marketplace.json # 插件市场元数据
│ └── plugin.json # 插件元数据
├── agents/ # Sub-Agent 定义
│ ├── cluster-explorer.md # 多集群导航 Agent
│ ├── pod-diagnostician.md # Pod 诊断 Agent
│ ├── node-analyzer.md # 节点分析 Agent
│ ├── deployment-tracker.md # 部署追踪 Agent
│ ├── resource-scout.md # 资源发现 Agent
│ ├── cluster-inspector.md # 集群巡检协调器 Agent
│ ├── cluster-info-inspector.md # 巡检维度: 集群基础信息
│ ├── node-health-inspector.md # 巡检维度: 节点健康
│ ├── capacity-inspector.md # 巡检维度: 资源容量
│ ├── workload-inspector.md # 巡检维度: 工作负载健康
│ ├── event-inspector.md # 巡检维度: 异常事件
│ └── system-inspector.md # 巡检维度: 系统组件
├── skills/ # Skill 触发器
│ ├── cluster-management/SKILL.md
│ ├── resource-troubleshooting/SKILL.md
│ ├── capacity-analysis/SKILL.md
│ ├── deployment-management/SKILL.md
│ ├── resource-discovery/SKILL.md
│ └── cluster-inspection/SKILL.md
├── .gitignore
├── CLAUDE.md
├── LICENSE
└── README.md
# 列出所有集群
"列出所有 Rancher 集群"
# 集群概览
"production 集群的整体状况"
→ 启动 cluster-explorer
→ 并行获取容量、节点、项目信息
→ 生成概览报告
# 多集群对比
"对比 production 和 staging 集群"
→ 并行启动 2 个 cluster-explorer
→ 对比容量和健康状况
# 查看日志
"查看 Pod api-server-abc123 的日志"
→ 直接调用 kubernetes_logs
# Pod 诊断
"诊断 Pod api-server-abc123"
→ 启动 pod-diagnostician
→ 并行获取 Pod 详情 + 日志 + 事件
→ 生成诊断报告
# 多 Pod 诊断
"诊断命名空间 production 中所有失败的 Pod"
→ 先列出异常 Pod
→ 并行启动多个 pod-diagnostician
→ 汇总所有诊断结果
# 节点健康检查
"所有节点的健康状况"
→ 启动 node-analyzer
→ 分析所有节点状态
# 集群容量
"集群还有多少可用容量?"
→ 启动 node-analyzer
→ 获取 CPU/内存/Pod 使用率
→ 给出容量规划建议
# 多集群容量对比
"哪个集群还有空间部署新应用?"
→ 并行启动多个 node-analyzer
→ 对比各集群可用容量
# 发布历史
"api-server 的发布历史"
→ 启动 deployment-tracker
→ 展示修订版本列表
# 跨集群对比
"对比 staging 和 production 的 api-server"
→ 启动 deployment-tracker
→ 使用 kubernetes_diff 跨集群对比
→ 展示镜像版本、副本数等差异
RuFlo Marketplace: Claude Code native agents, swarms, workers, and MCP tools for continuous software engineering
No description available.
Code intelligence powered by a knowledge graph — execution flows, blast radius, and semantic search