| 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):
| Alias | Model | Use |
|---|
composer | composer-2-fast | default, fastest composer variant |
codex | gpt-5.3-codex-xhigh-fast | extra-high coding |
opus | claude-opus-4-7-thinking-xhigh-fast | 1M ctx |
opus max | claude-opus-4-7-thinking-max | 1M ctx, max thinking |
sonnet | claude-4.6-sonnet-medium-thinking | 1M ctx, medium thinking |
gemini | gemini-3.1-pro | code investigation, planning, web research |
gemini fast | gemini-3-flash | simple tasks |
grok | grok-4.3 | creative solutions, unconventional, 1M ctx |
gpt | gpt-5.5-extra-high | 1M extra-high reasoning |
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.
| Alias | Model flag | Use |
|---|
opus, default | omit --model | default general reasoning |
sonnet | --model claude-sonnet-4-6 | fast 1M ctx |
haiku | --model claude-haiku-4-5 | fastest simple tasks |
codex | --model gpt-5.3-codex | code-focused OpenAI |
gpt | --model gpt-5.5 | latest GPT via OpenAI |
--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:
agy -p "How would you implement feature X?"
codex exec --skip-git-repo-check "How would you implement feature X?"
