shunt-xai

Subagents on ChatGPT/Codex GPT-6 models (Sol, Luna) and GPT-5.6 models (Luna, Sol, Terra), routed through shunt at the inference layer.

5 agents

Subagents on DeepSeek models (deepseek-v4-pro, deepseek-v4-flash), routed through shunt at the inference layer via DeepSeek's Anthropic-compatible endpoint.

2 agents

Subagent on Moonshot AI's kimi-k2.7-code, routed through shunt at the inference layer via Moonshot's Anthropic-compatible endpoint.

2 agents

Subagents on Z.ai GLM models (glm-5.2, glm-4.7), routed through shunt at the inference layer via Z.ai's Anthropic-compatible endpoint.

2 agents

A Claude Mod for the gateway itself: a band above the prompt shows the shared account pool's usage and reset times (the session's own rate limits off shunt), and /shunt:usage shows the pool's full breakdown, read from GET /usage. Requires function hooks (early access).

1 command

Subagent on Xiaomi's mimo-v2.5-pro, routed through shunt at the inference layer via Mimo's Anthropic-compatible endpoint.

1 agent

同步给 dondon：读取本机 Claude Code、Codex、WorkBuddy、Grok 最近的聊天记录，在本地隐去敏感信息后写成 800 字以内的工作近况，并找出聊天里用到的文档；用户确认后推给 dondon bot（未配置推送的复制给用户粘贴），让它的早报和提醒贴着用户手上的事；用户同意后可每天自动同步（由 bot 那边写近况，本机不需要 Agent 在场）。用户说「同步给 dondon」「把近况发给 bot」「开启/停止自动同步」「sync to dondon」时使用；不上传密钥密码，聊天摘录只在用户同意的自动同步里上传。

1 skill

Generate and edit AI images and videos from inside Claude Code through one remote MCP server. Nano Banana 2, GPT Image 2.5, Seedream 4.5, Flux 2 Pro and Z-Image for stills; Veo, Kling, Seedance, Grok Imagine and MiniMax for clips. quote_generation prices any call before you spend, and failed generations are refunded automatically. OAuth via /mcp; no API key to paste.

1 MCP server

Semantic code search — ccc skill, optional SessionStart index hook, and MCP server (Grok: disable hook/MCP for skill-only).

1 skill · 1 MCP server · hooks

Point it at a GitHub issue and get back a reviewed pull request. Hyperflow turns one AI coding session into a structured engineering pipeline: plan sharpens and decomposes the work, dispatch fans out parallel workers, and a domain specialist reviews every step — nothing ships unreviewed. 18 skills, 22 specialist reviewer and investigator agents, adaptive depth so a 5-line fix never triggers a deep run, and persistent per-project memory that lives in your repo and never leaves it. Runs on whatever model your session already uses — zero config, no API keys, no daemon. Works across Claude Code, Codex App/CLI, OpenCode, Grok, Antigravity, and Cursor.

18 skills · 23 agents · hooks

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode, Kilo Code, Pi, Oh My Pi, Antigravity, Cursor, Kimi, Copilot, Qoder CLI, Grok Build.

Turn your agent into a 7-role Hyperliquid trading desk: research, risk, execution and review.

17 skills · 7 agents