This skill should be used when the user asks to "install bdy", "install Buddy CLI", "login to Buddy", "authenticate with Buddy", "set up bdy", "configure Buddy authentication", or mentions Buddy CLI setup, authentication tokens, or workspace configuration.
Installs Buddy CLI and configures authentication with tokens or environment variables.
/plugin marketplace add sztwiorok/buddy-plugin/plugin install sztwiorok-buddy@sztwiorok/buddy-pluginThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/authentication.mdreferences/installation.mdBuddy CLI (bdy) is the command-line interface for interacting with Buddy services including Sandboxes and tunnels. This skill provides installation instructions and authentication configuration for the bdy CLI.
Use this skill when:
Interactive login (bdy login) cannot be performed by AI agents because it requires browser interaction. If user needs authentication:
bdy login in a separate terminal - Credentials will be stored persistently--token flag or environment variablesbdy workspace ls before proceedingInstall bdy using the appropriate method for your platform. See references/installation.md for detailed platform-specific instructions.
NPM (Recommended - All Platforms):
npm install -g bdy
Requires Node.js v20 or higher
macOS (Homebrew):
brew tap buddy/bdy
brew install bdy
Linux (APT):
# See references/installation.md for complete APT setup
sudo apt-get update && sudo apt-get install -y bdy
Windows (Chocolatey):
choco install bdy --version=1.16.12-prod --pre
Verify installation:
bdy version
IMPORTANT: Interactive login requires browser interaction and cannot be performed by AI agents.
Interactive Login (Recommended for Manual Setup):
User must run this in a separate terminal session outside of the AI agent:
bdy login
This opens a browser for authentication and stores credentials persistently in ~/.buddy/credentials, making them available for all terminal sessions including AI agent sessions.
Token-Based Authentication (For AI Agents):
If interactive login is not possible, use token-based authentication:
bdy login --token YOUR_PERSONAL_ACCESS_TOKEN
Or set environment variables:
export BUDDY_TOKEN="your-token"
export BUDDY_WORKSPACE="your-workspace"
export BUDDY_PROJECT="your-project"
For advanced authentication options including environment variables and regional configuration, see references/authentication.md.
bdy workspace ls
This command lists accessible workspaces, confirming successful authentication.
Set default workspace and project for CLI operations:
bdy login -w your-workspace -p your-project
Buddy operates in multiple regions. Specify region during login:
bdy login --region eu # Europe (default)
bdy login --region us # United States
bdy login --region as # Asia
For tunnel operations, use the tunnel token:
bdy login --tunnel-token YOUR_TUNNEL_TOKEN
Configure authentication without interactive login using environment variables:
export BUDDY_TOKEN="your-token"
export BUDDY_WORKSPACE="your-workspace"
export BUDDY_PROJECT="your-project"
export BUDDY_REGION="eu"
For complete environment variable reference and advanced configuration options, see references/authentication.md.
Authentication Failures:
Command Not Found:
Permission Errors:
For detailed information, consult:
After installing and authenticating:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.