AI Commands

AI coding agents and IDE extensions work best when they understand your tools programmatically. These commands expose the CLI's structure, capabilities, and project context in machine-readable formats.

CLI Capabilities

Show the CLI's capabilities in a structured format for AI consumption:

agentuity ai capabilities show

This outputs a machine-readable description of what the CLI can do, useful for:

• AI coding agents that need to understand available commands
• IDE extensions building Agentuity integrations
• Documentation generators

Schema Inspection

Output the CLI's command schema for programmatic consumption:

# Show the full CLI schema
agentuity ai schema show
 
# Generate schema in a specific format
agentuity ai schema generate

The schema includes:

• All available commands and subcommands
• Required and optional parameters
• Parameter types and validation rules
• Command descriptions and examples

Project Context Files

During development (agentuity dev or bun run dev), the CLI generates AGENTS.md files to help AI coding assistants (e.g., Claude Code, Codex, Cursor) understand Agentuity patterns:

.agents/
└── agentuity/
    └── sdk/
        ├── agent/AGENTS.md   # Agent creation patterns
        ├── api/AGENTS.md     # Route creation patterns
        └── web/AGENTS.md     # Frontend patterns

These files are auto-updated when the CLI version changes and should be added to .gitignore.

Prompt Generation

Generate context-aware prompts for LLMs working with Agentuity projects:

# Generate prompt for building agents
agentuity ai prompt agent
 
# Generate prompt for building APIs
agentuity ai prompt api
 
# Generate general LLM prompt
agentuity ai prompt llm
 
# Generate prompt for web/frontend development
agentuity ai prompt web

Each prompt type includes:

• Relevant SDK patterns and best practices
• Code examples for the target domain
• Common pitfalls to avoid
• Links to documentation

Integration Examples

IDE Extension

Use the CLI to provide autocomplete, validation, and project configuration help:

import { execSync } from 'child_process';
 
// Get CLI capabilities for IDE integration
const capabilities = JSON.parse(
  execSync('agentuity --json ai capabilities show').toString()
);

import { execSync } from 'child_process';
 
// Get agentuity.json schema for configuration validation
const schema = JSON.parse(
  execSync('agentuity --json ai schema generate').toString()
);

AI Coding Agent

# Generate context for an AI agent working on your project
agentuity ai prompt agent > /tmp/agentuity-context.md
 
# Include in your AI agent's system prompt
cat /tmp/agentuity-context.md

OpenCode Plugin

Install the Agentuity plugin for OpenCode to enable AI-assisted development:

# Install the plugin
agentuity ai opencode install
 
# Remove the plugin
agentuity ai opencode uninstall
 
# Run a task in headless mode
agentuity ai opencode run "Create an agent that validates email addresses"
 
# Run in a cloud sandbox environment
agentuity ai opencode run --sandbox "run the test suite"
 
# Output raw JSON events (for programmatic consumption)
agentuity ai opencode run --json "fix the bug"

The plugin provides specialized agents, slash commands, and MCP servers for Agentuity development. See OpenCode Plugin for full documentation.

Cadence Mode

Cadence enables long-running autonomous work sessions. Access it via:

• Interactive: Use the /agentuity-cadence slash command within OpenCode
• Headless: Run agentuity ai opencode run "/agentuity-cadence <task>" from the CLI

# Start a Cadence session interactively in OpenCode
/agentuity-cadence Build a complete auth system with tests
 
# Or run headlessly from the CLI
agentuity ai opencode run "/agentuity-cadence Build a complete auth system with tests"

See OpenCode Plugin: Cadence Mode for details on controlling Cadence sessions.

Next Steps

• Getting Started with the CLI: Install and authenticate
• Local Development: Run agents locally
• Creating Agents: Build your first agent