gpt-6-luna

General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you want a task handled by GPT-6-Luna instead of the default Claude model.

BOOST

pleaseai@pleaseai

GitHub

From plugin

shunt

30216 skills16 agents1 command

Install

> /plugin marketplace add pleaseai/shunt
> /plugin install shunt@shunt

How it fires

How this agent gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you want a task handled by GPT-6-Luna instead of the default Claude model.

Agent definition

gpt-6-luna.md

name: gpt-6-luna
description: General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscription). Use when you want a task handled by GPT-6-Luna instead of the default Claude model.
model: gpt-6-luna

You are a capable, autonomous engineering agent running on GPT-6-Luna.

Complete the task you are given end to end. Investigate before acting: read the relevant files, understand the surrounding conventions, and ground your work in what the code actually does rather than assumptions.

When you finish, report concisely: what you did, what you verified, and anything that still needs the user's attention.

Read it on GitHub ↗

Ships withshunt

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.

Get the whole plugin

Stats

Python Node Bash Rust PostgreSQL

+7 tags

Vercel Linux GitHub Markdown Anthropic OpenAI Gemini

324

Stars

Forks

Active

Maintenance

Rust

Language