By basher83
Manage Sidero Omni Talos Kubernetes clusters on Proxmox with GitOps: bootstrap ArgoCD External Secrets and Longhorn stacks on existing clusters, monitor health and issues across nodes apps and storage, review infrastructure and GitOps manifests pre-commit for validation, perform disaster recovery by destroying and recreating clusters from specs.
Generate a deployment plan using soft guidelines with anchored outputs.
Bootstrap GitOps stack (ArgoCD, ESO, Longhorn) onto existing Talos cluster
Execute disaster recovery drill - destroy and recreate cluster from specs
Load context for a new agent session by analyzing codebase structure and README
Check Omni cluster and GitOps health status
Use this agent to review mothership-gitops manifests before committing. Validates ArgoCD Applications, Helm values, External Secrets, namespace labels, and Tailscale Ingress patterns. <example> Context: User added a new ArgoCD Application. user: "Review my new ArgoCD app before I commit" assistant: "I'll use the gitops-reviewer agent to validate sync waves, destination namespace, and source configuration." <commentary> New ArgoCD apps need sync wave ordering validation to ensure dependencies deploy first. </commentary> </example> <example> Context: User deployed a new service with a web UI. user: "Check if my Homarr deployment is configured correctly" assistant: "I'll use the gitops-reviewer agent to verify the deployment has Tailscale Ingress for UI access." <commentary> Web UIs must have Tailscale Ingress - cluster-internal-only UIs are not acceptable. </commentary> </example> <example> Context: User is about to commit GitOps changes. user: "Review my mothership-gitops changes" assistant: "I'll use the gitops-reviewer agent to validate all modified manifests against GitOps patterns." <commentary> Pre-commit review catches sync wave ordering issues, missing Ingresses, and ESO configuration problems. </commentary> </example>
Use this agent to review Omni-Scale infrastructure manifests before committing. Validates machine classes, cluster templates, provider configs, and spec files against known patterns and constraints. <example> Context: User modified a machine class and wants to verify it before committing. user: "Review my changes to machine-classes/matrix-worker-hotel.yaml" assistant: "I'll use the omni-reviewer agent to validate the machine class against schema requirements and known constraints." <commentary> Machine class changes should be validated for required fields, CEL selector syntax, and provider data schema before committing. </commentary> </example> <example> Context: User created a new cluster template. user: "Check this cluster template before I deploy it" assistant: "I'll use the omni-reviewer agent to validate the cluster template structure, machine class references, and CNI configuration." <commentary> Cluster templates need multi-doc structure validation, version format checks, and machine class reference verification. </commentary> </example> <example> Context: User is about to commit changes to Omni-Scale repo. user: "Review my Omni-Scale changes before I commit" assistant: "I'll use the omni-reviewer agent to validate all modified infrastructure manifests." <commentary> Pre-commit review catches issues like CEL reserved keywords, missing required fields, or spec inconsistencies. </commentary> </example>
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Personal Claude Code plugin marketplace for homelab and infrastructure automation.
/plugin marketplace add basher83/lunar-claude
/plugin install <plugin-name>@lunar-claude
| Plugin | Description |
|---|---|
| meta-claude | Skill creation and multi-agent composition patterns |
| plugin-dev | Plugin development toolkit (skills, agents, commands, hooks) |
| hookify | Conversation pattern hooks for behavior control |
| claude-dev-sandbox | Development sandbox for testing components |
| Plugin | Description |
|---|---|
| ansible-workflows | End-to-end Ansible automation with multi-agent pipelines |
| proxmox-infrastructure | Proxmox VE cluster management, CEPH, VLAN networking |
| Plugin | Description |
|---|---|
| python-tools | Python toolkit: uv scripts, ruff/pyright, Agent SDK |
| git-workflow | Atomic commits, branch cleanup, conventional commits |
| Plugin | Description |
|---|---|
| netbox-powerdns-integration | NetBox IPAM and PowerDNS automation |
| omni-scale | Sidero Omni + Talos Kubernetes on Proxmox |
| Plugin | Description |
|---|---|
| lunar-research | Multi-agent research pipeline (external repo) |
Structure validation:
uv run scripts/verify-structure.py
Local testing:
/plugin marketplace add /path/to/lunar-claude
/plugin install plugin-name@lunar-claude
See individual plugin READMEs for details.
npx claudepluginhub basher83/lunar-claude --plugin omni-scaleEasily create hooks to prevent unwanted behaviors by analyzing conversation patterns
End-to-end Ansible workflow automation: design, create, validate, and review playbooks and roles with orchestrated multi-agent pipelines
Project setup and validation toolkit for standardizing repos with mise, hk, and changelog tooling across Python, Rust, Terraform, and Ansible projects
Comprehensive plugin development toolkit for creating Claude Code plugins with AI-powered guidance for skills, agents, commands, and hooks
Human-in-the-loop Architecture Decision Record workflow
KSail MCP server + expertise skill — spin up and manage local Kubernetes clusters (Kind/K3d/Talos/vCluster) and GitOps workloads declaratively.
Claude Code skill pack for Cast AI (18 skills)
Kubernetes and Helm operations - deployments, charts, releases, diagnostics
Kubernetes cluster operations, health diagnostics, and operator-specific agents
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research