Get Started on Cloud
BasicsAI AgentsPipelinesActions & ServicesEnvironmentsIntegrationsTargetsTestsDomainsSandboxesAgents & TunnelsYAMLBuddy GitFAQ

Claude Code

View as Markdown

Claude Code is Anthropic's agentic coding tool that lives in your terminal. It works with the full context of your project - reading across the codebase, running shell commands, editing files wherever changes are needed, and taking care of git along the way. Paired with Buddy, Claude Code can deploy your project and let Buddy handle the entire deployment workflow. On top of that, it can trigger and monitor your pipelines, ship changes across environments, and dig through build output and logs when something needs fixing.

Info
This page covers working with Buddy from within Claude Code. On top of that, you can run AI coding agents in a fully isolated Buddy sandbox - see Run agents in a sandbox - or as an action in a pipeline. You can also self-host Claude Managed Agents on Buddy Sandboxes.

Quick start

1

Install the Buddy CLI

bash
npm install -g bdy
$
2

Log in to Buddy

bash
bdy login
$
3

Link your project

Run this inside your project directory to connect it to a Buddy project:

bash
bdy proj link
$
4

Install the Buddy skill

bash
npx skills add buddy/buddy-plugin
$

Using Claude Code? Install the full plugin instead - npx skills add installs only the skill, without the slash commands.

5

Start Claude Code

bash
claude
$
6

Prompt the agent

Ask it to build and ship something end to end, for example:

Create a snake app and deploy it for me

Claude Code plugin

The Buddy plugin for Claude Code bundles the Buddy skill together with a set of slash commands. The skill teaches Claude how to use the bdy CLI (sandboxes, artifacts, tunnels, domains, distributions, and pipelines), while the commands give you one-step shortcuts for the most common workflows.

Installation

bash
claude plugin marketplace add buddy/buddy-plugin
claude plugin install buddy@buddy-plugin
$$

Requires the Buddy CLI (sudo npm install -g bdy) and authentication (bdy login).

What you get

  • The buddy skill - platform knowledge Claude uses automatically whenever you ask it to deploy, expose, or manage anything on Buddy, in your own words.
  • Slash commands - predefined workflows you invoke directly:
Command Description
/deploy [name] [path] Deploy an app to Buddy: auto-detects whether it is a static site (published as an artifact with a public URL) or a server-side app (deployed to a sandbox with a public endpoint).
/expose [port] Expose a locally running app to the internet via a Buddy tunnel; auto-detects the port and asks about authentication.
/status [name] Overview of everything running on Buddy: sandboxes with apps and endpoints, static sites (bucket artifacts) with their URLs, active tunnels, and pipeline run statuses.
/logs [name] [app-id] Show status and logs of a deployed app or a pipeline run, diagnose failures, and suggest fixes.
/domain [target] [domain] Attach a domain to a deployment - claim a free subdomain on a Buddy-owned domain, buy a new one, or reuse a domain from your workspace.
/ci [pipeline] Run a CI/CD pipeline and follow the result, or set up a new pipeline for the project (generates and registers buddy.yml).

Example prompts

Once the agent is running and your project is linked to Buddy, try prompts like:

  • Create a Next.js app and deploy it to production.
  • Deploy an Umami analytics instance and wire it into my app.
  • Deploy an AI chatbot with Postgres for history and Redis for rate limiting.
  • Deploy my app, set up a CDN, and buy and configure a domain with SSL.
  • Add a pipeline that runs on every change in the repository and executes my test suite.
  • Add a pipeline that runs every minute, checks that my site is up, and sends a notification to Slack, email, Telegram, or SMS if anything is wrong.
  • Check the last few CI pipeline runs for failures, read the logs, and fix the failing tests.
  • Analyze the logs from the last production deployment and fix the errors.
  • Find the last successful production deployment and roll back to it.
  • Check my app logs and open issues based on what you find.

Connect MCP

Give Claude Code access to Buddy over MCP so it can run pipelines, manage deployments, and read logs. See the MCP page for the regional server URLs and how to filter the exposed tool categories.

Add the server with the claude mcp command:

bash
claude mcp add --transport http buddy https://mcp.buddy.works/mcp
$

Or ask Claude Code to set it up for you:

Add the Buddy MCP server (https://mcp.buddy.works/mcp) to your MCP configuration.

Last modified on Jul 24, 2026

Next pageAntigravity