Frequently Asked Questions

General

What is Agentic Stacks?

Agentic Stacks is a package manager for domain expertise. You pull skill packs into your project and your AI coding assistant instantly gains deep knowledge about a specific domain — OpenStack deployment, Kubernetes cluster operations, Ceph storage, Docker containers, bare metal server management, and more. It's AI for ops teams — instead of searching docs and runbooks, your agent already knows the procedures, the gotchas, and the recovery steps.

Think of it like npm or pip, but instead of code libraries you're installing operational knowledge that makes your coding agent an expert operator.

What's in a stack?

A stack is a git repo containing:

  • CLAUDE.md — the agent's brain. Sets identity, safety rules, and routes to skills.
  • skills/ — structured markdown files teaching the agent how to perform specific operations.
  • stack.yaml — machine-readable manifest with metadata.

When an agent reads the stack, it gains the ability to deploy, configure, troubleshoot, and upgrade the target software.

Is this free?

Yes. Agentic Stacks is open source (MIT license). All curated stacks in the agentic-stacks org are free. Third-party stacks are managed by their own authors.

Using with AI Agents

Which AI agents work with Agentic Stacks?

Agentic Stacks works with any AI coding assistant that reads markdown project files. Because stacks are plain markdown, they work with any LLM tools and coding agents regardless of the underlying model:

  • Claude Code (Anthropic) — reads CLAUDE.md automatically
  • OpenAI Codex CLI — reads AGENTS.md (copy from CLAUDE.md)
  • Gemini CLI (Google) — reads GEMINI.md
  • Cursor / Windsurf — reads .cursorrules or project docs
  • VS Code with GitHub Copilot — reference skills in prompts or copilot instructions
  • JetBrains IDEs — AI assistant plugins can reference the .stacks/ directory
  • Custom agents — any agent built on Claude, GPT, Gemini, or open source AI models

Models from OpenAI, Anthropic, Google, and open source projects can all consume stack skills since they're plain markdown.

How do I use this with Claude Code? 
pipx install agentic-stacks
agentic-stacks init my-project
cd my-project
agentic-stacks pull kubernetes-talos
claude

That's it. Claude Code reads the CLAUDE.md in your project, which points to .stacks/*/CLAUDE.md. The agent now has deep expertise in whatever stacks you've pulled.

How do I use this with OpenAI Codex CLI or Codex agents?

Codex CLI reads AGENTS.md. After pulling stacks:

agentic-stacks init my-cluster
cd my-cluster
agentic-stacks pull kubernetes-talos
cp CLAUDE.md AGENTS.md
codex

The skills are plain markdown — OpenAI models read them just as well as Claude. The routing table in CLAUDE.md/AGENTS.md tells the agent where to find each skill.

How do I use this with Gemini CLI?

Gemini CLI reads GEMINI.md:

agentic-stacks init my-storage
cd my-storage
agentic-stacks pull ceph
cp CLAUDE.md GEMINI.md
gemini
How do I use this with Cursor or Windsurf?

Open your project directory in Cursor or Windsurf. These editors read project-level markdown files. You can either:

  • Point their rules file to .stacks/*/CLAUDE.md
  • Copy the CLAUDE.md content into .cursorrules or the editor's equivalent
  • Simply reference the skills directory in your prompts: "Read .stacks/kubernetes-talos/skills/deploy/"
Can I use multiple stacks at once?

Yes — that's the whole point. Compose stacks for cross-domain expertise:

agentic-stacks init my-cloud
cd my-cloud
agentic-stacks pull kubernetes-talos
agentic-stacks pull hardware-dell
agentic-stacks pull ceph

Your agent now knows Kubernetes deployment, Dell server management, and Ceph storage — and can combine that knowledge. "Deploy a Kubernetes cluster with Ceph storage on these Dell servers" becomes a conversation, not a project.

How It Works

Where does the knowledge come from?

Stack authors research official documentation, release notes, and real-world operational experience, then distill it into structured skills. Every command is verified against official docs. Every config field is checked. Version-specific behaviors are noted.

Stacks also improve over time — when operators hit issues, they feed the fix back into the stack's known issues or skill content.

How is this different from just giving the agent documentation?

Documentation tells you what a tool does. A stack teaches the agent how to operate it — the right order, the safety checks, the decision points, the gotchas, and the recovery procedures. Stacks go beyond static docs to enable real AI operations — the agent doesn't just read about a tool, it learns the judgment calls that experienced operators rely on. This takes you beyond vibe coding into structured, verifiable infrastructure operations.

Stacks include:

  • Routing tables — the agent knows which skill to use for which task
  • Safety rules — hard guardrails preventing destructive operations
  • Decision guides — structured trade-off analysis for choosing between options
  • Known issues — version-specific bugs and workarounds
  • Workflows — step-by-step paths for common operations
Do stacks execute commands on my system?

No. Stacks are passive knowledge — they're markdown files that teach the agent. The agent then proposes commands for you to review and approve. Your agent's existing permission model (approval gates, sandboxing, etc.) still applies.

Can I contribute or create my own stack?

Yes! See the authoring guide.

agentic-stacks create my-org/my-stack

This scaffolds the full structure. Write your skills, validate with agentic-stacks doctor, and publish.

Still have questions? Open an issue on GitHub.