BitFrost — Development skill for Claude Code
Use Codex, GLM, and other coding agents as Claude Code subagents.
How to install BitFrost
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open SavaSoftworks/BitFrost and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What BitFrost does
Use Codex, GLM, and other coding agents as Claude Code subagents.
Alternatives in Development
- OpenAI Codex CLI — (Rust implementation) 67.8k ★
- Vibe Kanban — Get 10X more out of Claude Code, Gemini CLI, Codex, Amp and other coding agents 23.5k ★
- Hapi — App for Claude Code / Codex / Gemini / OpenCode, vibe coding anytime, anywhere 3.6k ★
README
A bridge between agents
BitFrost lets Claude Code delegate tasks to models through coding apps installed on your machine.
Works in Claude Code (CLI and desktop app), on Linux and macOS 12.3+.
Subagent permission requests and questions come straight to you.
In auto mode, Claude answers subagent questions and a safety review decides permission requests.
Related Skills
Coding Usage Bar
macOS menu bar usage monitor for Claude Code, Codex, GLM, DeepSeek, and MiniMax
TokenLink
Native macOS menu-bar monitor for Codex, Claude, Kimi, MiniMax, and GLM coding plans, with optional M5Stack St
Linktokenview Docs
LinkTokenView(联视未来)国产大模型 Token API 聚合平台,提供 OpenAI 兼容接口,统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型,支持 Token Plan 与 Co
Glm Subagent MCP
Delegate work to a Claude Code subprocess billed against a GLM Coding Plan.
Wtagent
Turn ChatGPT Web (including Pro) into Codex. Turn Claude Web into Claude Code. Also DeepSeek, Gemini, Grok, Ki
Quota Peek
所有大模型额度,一眼看清 — 本地优先的 macOS 菜单栏工具,查看 Codex/Claude/Kimi/GLM 订阅额度
Related Agents
Model Runner
Deterministic wrapper that runs a prompt on a non-Claude model (OpenAI via Codex, Cursor's composer/grok/glm,
Glm Agent
Runs Z.AI GLM on the user's GLM Coding Plan. Three modes - consult (direct API call, 1M context, for inputs to
Glm Worker
Coding worker on GLM (Zhipu), served by the multi-model gateway's upstream. Use when the user says "use glm",