orchestrate-agent-clis

name: orchestrate-agent-clis description: > Execute and orchestrate multiple AI agent CLIs (agy, Codex, Cursor, Claude Code, Pi) for getting alternative opinions, comparing approaches, or leveraging different AI models' strengths. Use when the user explicitly mentions agent names like "ask agy", "ask cursor", "ask codex", "ask pi", "use composer", "use pi", "try grok", or when needing diverse perspectives on complex problems, alternative implementation approaches, or multi-agent collaboration.

Orchestrate Agent CLIs

Execute different AI agent CLIs to get alternative perspectives, compare approaches, or leverage specific model strengths.

Defaults

• If user names an agent but not provider, model, or effort, use that CLI's default
• Do not ask which provider, model, or effort to use unless user explicitly asks to choose
• Do not pause to recommend alternatives when the requested agent can run with defaults
• Ask only for missing task inputs that block execution, such as absent file paths or destructive write intent

Available CLIs

agy (Antigravity CLI)

Google's Antigravity CLI, the successor to Gemini CLI.

agy -p "<prompt>"

Has internet access. Good for research and current information.

Discover models (use when a --model name fails or may be stale):

agy models

Codex

codex exec --skip-git-repo-check "<prompt>"

No model-list subcommand. Set with -m <model> (e.g. -m gpt-5.5-codex). Discover current OpenAI model IDs at https://platform.openai.com/docs/models or the interactive /model picker in codex (no subcommand).

Claude Code

claude -p "<prompt>"

Full-featured Claude agent with tool access.

No model-list subcommand. --model takes an alias (opus, sonnet, haiku) or a full ID (e.g. claude-opus-4-8). Discover current IDs at https://docs.claude.com/en/docs/about-claude/models/overview.

Cursor Agent

cursor-agent --model=MODEL -p "<prompt>"

Available models (not extensive, favorites):

Note: If these models fail, you can get the list of available models by running this command, but don't use head or tail, otherwise you'll cut out important models out:

cursor-agent models

Pi

pi -p "<prompt>"

Multi-provider agent (Anthropic, OpenAI, Google, xAI, etc)

Model and thinking mode are optional for Pi. Omit --model and --thinking unless user requested them.

• --thinking <off|minimal|low|medium|high|xhigh> controls reasoning depth.
• --tools read,grep,find,ls for read-only runs.
• --continue / --resume to reuse sessions.
• --list-models [search] to discover models.

File References

Reference files using @ prefix with relative paths:

codex exec --skip-git-repo-check "Review @src/components/Button.tsx"
agy -p "Create tests for @src/utils/helpers.ts"
cursor-agent --model=composer-2 -p "Refactor @src/api/client.ts"
pi -p "Review @src/api/client.ts"

Task Guidelines

Read-Only Tasks

For questions, plans, reviews, or analysis, instruct agents not to make file changes:

cursor-agent --model=gemini-3.1-pro -p "Analyze the architecture in @src/core/ - explain only, do not modify files"

Comparison Workflows

Get multiple perspectives on the same problem:

# Get agy's opinion first
agy -p "How would you implement feature X?"

# Then compare with Codex
codex exec --skip-git-repo-check "How would you implement feature X?"