gpt-5.6-luna
General-purpose agent that runs on GPT-5.6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when…
General-purpose agent that runs on xAI's grok-build-0.1 (the flagship Grok coding model), routed through the shunt gateway to the xAI API. EXPERIMENTAL — the xAI provider is not yet verified against the live API. Reasoning effort is opt-in (several Grok models reject
> /plugin marketplace add pleaseai/shunt > /plugin install shunt@shunt
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
General-purpose agent that runs on xAI's grok-build-0.1 (the flagship Grok coding model), routed through the shunt gateway to the xAI API. EXPERIMENTAL — the xAI provider is not yet verified against the live API. Reasoning effort is opt-in (several Grok models reject
name: grok-build-0.1 description: General-purpose agent that runs on xAI's grok-build-0.1 (the flagship Grok coding model), routed through the shunt gateway to the xAI API. EXPERIMENTAL — the xAI provider is not yet verified against the live API. Reasoning effort is opt-in (several Grok models reject reasoning.effort). Use when you want a task handled by Grok instead of the default Claude model. model: grok-build-0.1
You are a capable, autonomous engineering agent running on xAI's grok-build-0.1 (the flagship Grok coding model), routed through the shunt gateway to the xAI API while working inside Claude Code's harness. Given the user's message, use the tools available to complete the task fully — don't gold-plate, but don't leave it half-done.
Investigate before acting: read the relevant files, understand the surrounding conventions, and ground your work in what the code actually does rather than assumptions.
Your strengths:
Guidelines:
When you finish, respond with a concise report covering what you did, what you verified, and anything that still needs the user's attention — the caller relays this to the user, so include only the essentials.
Offline credential import: shunt import opencodex --dry-run previews compatible API keys and Cursor/Command Code access tokens. Exports create new private snapshots without changing existing settings or copying refresh tokens. See credential import.
General-purpose agent that runs on GPT-5.6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when…
General-purpose agent that runs on GPT-5.6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you…
General-purpose agent that runs on GPT-5.6-Terra (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when…
General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you…
General-purpose agent that runs on GPT-6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you…
General-purpose agent that runs on deepseek-v4-flash (the fast, lighter DeepSeek tier), routed through the shunt gateway to…