# aracli-deploy-management

A reference skill for running and operating OpenClaw-compatible agent systems: infrastructure choices and three ways to manage them.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/aracli-deploy-management/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/aracli-deploy-management

## What it does

The skill walks through where an agent can live. Five infrastructure options are covered: cloud VMs, managed container platforms, dedicated hardware, serverless and edge, plus hybrid setups. Each one comes with trade-offs and a sample start command, such as `docker compose up -d agent-runtime` or `wrangler deploy`.

The second half covers operating agents once they are running. Three routes: CLI, API, and MCP. A CLI suits operators and CI/CD pipelines. An API is language-agnostic and can enforce auth and audit logging. MCP exposes deploy operations as tools so the agent manages infrastructure itself. A comparison table lines up setup speed, automation, audience, observability, and auth model.

Nothing gets installed or executed by the skill — it is a written guide. If you go the MCP route, scope permissions carefully: without confirmation steps, dry-run modes, and blast radius limits, an agent can push straight to production unsupervised.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill aracli-deploy-management -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/aracli-deploy-management/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/aracli-deploy-management/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill aracli-deploy-management -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/aracli-deploy-management/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill aracli-deploy-management -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/aracli-deploy-management/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills aracli-deploy-management
```

2. **Manually: put the files in place**
- File: `.github/skills/aracli-deploy-management/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill aracli-deploy-management -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/aracli-deploy-management
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/aracli-deploy-management/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill aracli-deploy-management -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/aracli-deploy-management/SKILL.md

## When to use it
- pick between cloud VMs, dedicated servers, and serverless for an agent
- compare CLI, API, and MCP as deployment management routes
- run an agent as a containerized service
- roll back and tail logs from the terminal
- wire a hybrid setup with an API layer and a GPU runtime

## Example prompts
- Compare cloud VMs and dedicated servers for running an agent — which is cheaper under constant load?
- Show me how to manage agent deployments through MCP tools
- Set up a hybrid: API on Railway, agent runtime on dedicated hardware

## Similar
- [platform-quick-deploy](https://affpapa.org/en/nevibecode/skills/platform-quick-deploy.md) — skill · 2700 installs
- [platform-destructive-deploy](https://affpapa.org/en/nevibecode/skills/platform-destructive-deploy.md) — skill · 2700 installs
- [convex-deploy-guard](https://affpapa.org/en/nevibecode/skills/convex-deploy-guard.md) — skill · 36300 installs
- [render-deploy](https://affpapa.org/en/nevibecode/skills/render-deploy.md) — skill · 559 installs
- [vercel-deploy](https://affpapa.org/en/nevibecode/skills/akillness-vercel-deploy.md) — skill · 347 installs
- [serverless-deploy](https://affpapa.org/en/nevibecode/skills/serverless-deploy.md) — skill · 2700 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 199 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md