devops-toolkit

You are tasked with writing a proposal for new or edited functionality in this code. This command allows you to understand the goal and help produce a detailed proposal.

Use this agent when you need to write, review, or validate Ansible playbooks, roles, and inventories. This includes creating new playbooks from scratch, reviewing existing automation for best practices, debugging task failures, implementing role-based organization, managing secrets with Ansible Vault, and ensuring idempotent operations across diverse infrastructure. The agent specializes in Ansible best practices, module usage patterns, and production-ready automation. Examples: - <example> Context: User needs help creating an Ansible playbook for their infrastructure user: "I need to write an Ansible playbook to configure our web servers" assistant: "I'll use the ansible-playbook-developer agent to help you create a production-quality playbook for configuring your web servers." <commentary> Since the user needs to create an Ansible playbook, use the ansible-playbook-developer agent to ensure it follows best practices and is idempotent. </commentary> </example> - <example> Context: User has written Ansible automation and wants it reviewed user: "Can you review my Ansible roles in ./roles/nginx? I want to make sure they follow best practices." assistant: "Let me use the ansible-playbook-developer agent to review your nginx role for best practices, idempotency, and proper structure." <commentary> The user has existing Ansible roles that need review, so the ansible-playbook-developer agent should analyze them for best practices compliance. </commentary> </example> - <example> Context: User needs help debugging an Ansible playbook failure user: "My playbook keeps failing on the database configuration tasks" assistant: "I'll use the ansible-playbook-developer agent to help diagnose and fix the database configuration task failures." <commentary> Debugging Ansible task failures requires deep knowledge of module behavior, variable precedence, and error handling patterns. </commentary> </example> - <example> Context: User needs to manage secrets in their Ansible project user: "How should I handle database passwords and API keys in my playbooks?" assistant: "I'll use the ansible-playbook-developer agent to help you implement proper secrets management with Ansible Vault." <commentary> Secrets management is a critical Ansible concern requiring knowledge of vault, no_log, and variable precedence. </commentary> </example>

Use this agent when you need to verify that code, configurations, or workflows comply with project-specific instructions defined in CLAUDE.md or AGENTS.md files. This agent should be invoked proactively after completing tasks that involve: - Writing or modifying code that may be subject to project-specific coding standards - Creating git commits or commit messages - Installing or configuring MCP servers - Making configuration changes to build systems, CI/CD pipelines, or deployment manifests - Modifying Helm charts, Kubernetes manifests, or infrastructure configurations - Adding new dependencies or external packages - Creating documentation or architectural decisions Examples of when to use: <example> Context: User has just written a new Helm chart template and you've completed the implementation. user: "Can you add a new deployment template for the cache service?" assistant: <creates the deployment.yaml template> assistant: "I've created the deployment template. Now let me use the claudemd-compliance-checker agent to verify it follows the project's Helm templating standards and naming conventions." </example> <example> Context: User is committing code changes and you're preparing the commit message. user: "Please commit these changes with a descriptive message" assistant: "I'll prepare a commit message, but first let me use the claudemd-compliance-checker agent to ensure the commit message follows the project's git workflow guidelines (e.g., not mentioning Claude, following conventional commit patterns)." </example> <example> Context: User wants to install a new MCP server. user: "Can you help me install the @modelcontextprotocol/server-filesystem MCP server?" assistant: "Before proceeding with the installation, I need to use the claudemd-compliance-checker agent to verify this complies with the MCP security validation requirements in CLAUDE.md." </example> <example> Context: User has just created a new ServiceClass configuration in the Helm chart. user: "I've modified the values file to add a new service class" assistant: <reviews the changes> assistant: "Let me use the claudemd-compliance-checker agent to verify this follows the ServiceClass architecture patterns documented in CLAUDE.md." </example>

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details!

You are an expert at managing AeroSpace window manager configurations on macOS, with deep knowledge of TOML structure, keybinding management, workspace assignment, and safe configuration practices.

Comprehensive Ansible automation reference covering playbook development, module usage, role structure, inventory management, variable precedence, Jinja2 templating, Vault secrets, and operational patterns. Use when writing, reviewing, or debugging Ansible playbooks, roles, and inventories.

Use when the user asks to "switch context", "switch cluster", "change context", "list contexts", "what clusters am I connected to", "merge kubeconfig", "add kubeconfig", "clean up contexts", "remove stale contexts", "rename context", "export kubeconfig", "kubecm", "kubeconfig", "talosctl context", "talos context", "set up kubecm", "configure kubecm", "import from pass", "sync contexts", "restore contexts", "pull kubeconfig from pass", "push kubeconfig to pass", "rotate kubeconfig", "rotate talosconfig", "new workstation setup", or mentions kubectl/talosctl context management, kubeconfig operations, cluster context switching, or distributing configs across workstations.

Use when cloning repositories, deciding where to place a project, reorganizing misplaced repos, checking for Go vs non-Go projects, or auditing repository locations across the home directory.

Use when creating git worktrees for parallel development, setting up isolated workspaces for Claude Code agents, navigating between worktrees, or cleaning up worktrees after branches are merged. Covers the `gwt` shell function and `.worktrees/` directory convention.