shunt-zai

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 xAI Grok models (grok-4.6, grok-4.5, grok-build-0.1), routed through shunt at the inference layer. EXPERIMENTAL — the xAI provider is not yet verified against the live API.

3 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

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

教育类技能集合：把学科问题转成可交互教学网页与讲解视频。edu-solid-geometry 立体几何解题（建系+向量法，3D + MathJax）；edu-analytic-geometry 解析几何/圆锥曲线解题（sympy 精确计算 + 实时交互 2D 画板 + KaTeX）；edu-chem-reaction 化学反应微观 3D 演示（sympy 自动配平 + 原子守恒，morph/mechanism 双引擎，Three.js + KaTeX）；edu-math-video 数学题讲解视频（GLM-TTS 中文配音 + 中英双语字幕 + 手绘动画，渲染成 MP4）。

6 skills

Read local images, videos, web pages, and Windows screenshots through Doubao, GLM, or Qwen-compatible vision APIs.

1 skill · 4 MCP servers

Z.AI vision, search, reader, and GitHub exploration via MCP

1 skill

Real-time status line showing model, context, color-coded progress bar, cost, API rate limits (5h/7d), and unified usage tracking for Claude, Codex, Gemini, Antigravity, and z.ai CLIs. Supports Max/Pro plans with i18n (English/Korean).

4 commands · hooks

Run any third-party LLM provider with an Anthropic-compatible API as real Claude Code agent-team teammates (terminal claude inside tmux or iTerm2) or one-shot subagents via the cc-fleet CLI — driven just like native teammates; your main session's own auth (OAuth or API key) is untouched, provider workers bill the provider key.

3 skills · hooks

vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.

1 skill