# Codex CLI Model Bridge

Install, audit, repair, and manage Codex custom model Providers and model catalogs...

- Repository: https://github.com/zjp1997720/zhijian-skills (788 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-26
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add zjp1997720/zhijian-skills --skill codex-cli-model-bridge -g -a claude-code -y`
Codex: `npx skills add zjp1997720/zhijian-skills --skill codex-cli-model-bridge -g -a codex -y`
Cursor: `npx skills add zjp1997720/zhijian-skills --skill codex-cli-model-bridge -g -a cursor -y`
Gemini CLI: `npx skills add zjp1997720/zhijian-skills --skill codex-cli-model-bridge -g -a gemini-cli -y`

## Description

Install, audit, repair, and manage Codex custom model Providers and model catalogs backed by a loopback CLIProxyAPI or Codex Router. Use whenever the user asks to add, remove, upgrade, restore, or diagnose third-party models in Codex or the Codex desktop model picker; mentions Grok, OpenCode Go, DeepSeek, Gemini, GLM Coding Plan, GLM-5.3, subscription-backed CLI models, custom model_provider, model_catalog_json, or Codex Fast mode; or wants the same local proxy models synchronized between Codex and WorkBuddy. Preserve unrelated Codex configuration and credentials. Isolated profile is the default Windows path.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Codex CLI Model Bridge

Manage subscription-backed or local proxy models in Codex without treating Codex like WorkBuddy. Codex uses a Responses API Provider plus a model catalog; WorkBuddy uses independent JSON entries. Share CLIProxyAPI infrastructure and verified Provider facts, but keep each application's writer and state separate.

Codex selects one `model_provider` for a task. Model catalog entries do not carry per-model Provider routing. Preserve the Provider identity that owns the majority of indexed task history (normally `openai`). For normal Desktop use, the supported bridge design keeps `model_provider = "openai"`, keeps ChatGPT subscription auth intact, and points the built-in Provider's `openai_base_url` at an owner-only loopback header-rewriting proxy. CLIProxyAPI then routes native GPT subscription models and verified third-party models behind one catalog without changing the task Provider identity. Keep the isolated `$CODEX_HOME/cli-proxy.config.toml` profile as the default path on Windows and as a fallback everywhere else.

This is transparent single-Provider routing, not per-model Provider routing. Never set the Desktop default to `cli_proxy` or vendor `ZAI` when most history belongs to `openai`.

When the user wants GLM-5.3 from a Coding Plan key, read [glm-coding-plan.md](references/glm-coding-plan.md). If Desktop already uses Codex Router on port 4202, add `zai-coding` there and keep the OpenAI Provider identity. Do not run `npx @z_ai/coding-helper`.

On Windows, start with the isolated profile. Read [windows.md](references/windows.md). Do not require Homebrew, LaunchAgents, or Codex Router.

## Resolve the Skill directory

Resolve this loaded Skill's directory as `<skill-dir>`. Resolve `<python>` as the first available of `python3`, `py -3`, and `python`. Use the deterministic entry point:

```bash
<python> <skill-dir>/scripts/bridge.py
```

Examples below use `python3`. Substitute `<python>` when that command is missing.

The rest: https://github.com/zjp1997720/zhijian-skills/blob/HEAD/skills/codex-cli-model-bridge/SKILL.md