KubeStellar plugins for Claude Code - multi-cluster Kubernetes management tools
npx claudepluginhub kubestellar/claude-pluginsMulti-cluster Kubernetes diagnostics, RBAC analysis, and security checks. Find pod issues, security misconfigurations, and analyze permissions across all your clusters.
App-centric multi-cluster deployment and operations. Deploy apps, aggregate logs, check status, and sync from git across all your Kubernetes clusters - working with apps, not clusters.
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 79 focused plugins, 184 specialized agents, and 150 skills - optimized for granular installation and minimal token usage
Curated collection of 141 specialized Claude Code subagents organized into 10 focused categories
Official Claude Code plugin marketplace for KubeStellar - multi-cluster Kubernetes management tools.
Install the CLI tools via Homebrew before adding the plugins:
brew tap kubestellar/tap
brew install kubestellar-ops kubestellar-deploy
Or download binaries from GitHub Releases.
In Claude Code, run:
/plugin marketplace add kubestellar/claude-plugins
/plugin install kubestellar-ops
/plugin install kubestellar-deploy
Or go to /plugin → Discover tab → Install kubestellar-ops and/or kubestellar-deploy.
After installing (or updating) plugins, you must restart Claude Code for the new MCP servers to be loaded. Simply exit and relaunch the CLI:
# Exit Claude Code (Ctrl+C or type /exit), then restart it
claude
Run /mcp in Claude Code - you should see:
plugin:kubestellar-ops:kubestellar-ops · ✓ connected
plugin:kubestellar-deploy:kubestellar-deploy · ✓ connected
Add to ~/.claude/settings.json:
{
"permissions": {
"allow": [
"mcp__plugin_kubestellar-ops_kubestellar-ops__*",
"mcp__plugin_kubestellar-deploy_kubestellar-deploy__*"
]
}
}
Or run in Claude Code:
/allowed-tools add mcp__plugin_kubestellar-ops_kubestellar-ops__*
/allowed-tools add mcp__plugin_kubestellar-deploy_kubestellar-deploy__*
To update the plugins to the latest version available in the marketplace:
/plugin update kubestellar-ops
/plugin update kubestellar-deploy
Or update all installed plugins at once:
/plugin update --all
The plugins rely on the kubestellar-ops and kubestellar-deploy CLI tools installed via Homebrew. To upgrade them:
brew update
brew upgrade kubestellar-ops kubestellar-deploy
To see what versions you currently have installed:
/plugin list
For CLI tool versions:
kubestellar-ops --version
kubestellar-deploy --version
To remove a plugin from Claude Code:
/plugin uninstall kubestellar-ops
/plugin uninstall kubestellar-deploy
To remove the marketplace:
/plugin marketplace remove kubestellar/claude-plugins
To remove the CLI tools:
brew uninstall kubestellar-ops kubestellar-deploy
brew untap kubestellar/tap
Multi-cluster Kubernetes diagnostics, RBAC analysis, and security checks.
| Skill | Description |
|---|---|
/k8s-health | Check health of all Kubernetes clusters |
/k8s-issues | Find issues across clusters (pods, deployments, events) |
/k8s-analyze | Comprehensive namespace analysis |
/k8s-security | Security audit (privileged, root, host access) |
/k8s-rbac | Analyze RBAC permissions for a subject |
/k8s-audit-kubeconfig | Audit kubeconfig clusters and recommend cleanup |
/k8s-ownership | Set up and manage resource ownership tracking with OPA Gatekeeper |
/k8s-upgrade-check | Check for available upgrades |
/k8s-upgrade | Upgrade cluster (master and nodes) |
list_clustersList all discovered Kubernetes clusters from kubeconfig and KubeStellar.
| Parameter | Type | Required | Description |
|---|---|---|---|
source | string | No | Discovery source: all, kubeconfig, or kubestellar |
get_cluster_healthCheck the health status of a Kubernetes cluster.
| Parameter | Type | Required | Description |
|---|---|---|---|
cluster | string | No | Cluster name (uses current context if not specified) |
get_nodesList nodes in a cluster.
| Parameter | Type | Required | Description |
|---|---|---|---|
cluster | string | No | Cluster name (uses current context if not specified) |
audit_kubeconfigAudit all clusters in kubeconfig: check connectivity, identify stale/inaccessible clusters, and recommend cleanup.
| Parameter | Type | Required | Description |
|---|---|---|---|
timeout_seconds | integer | No | Connection timeout in seconds per cluster (default 5) |