OnourImpram

Claude OAuth — Development skill for Claude Code

Development community

Run Google, xAI and OpenAI models inside Claude Code over your own OAuth sessions.

How to install Claude OAuth

This entry records only its repository, not the path inside it, so there is no exact command to give. Open OnourImpram/claude-oauth and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude OAuth does

Run Google, xAI and OpenAI models inside Claude Code over your own OAuth sessions. The native claude path is never touched; a loopback router sits behind a real Claude Code process. Open defects listed by id.

Alternatives in Development

Claude Context Mode — An MCP server that sits between Claude Code and these outputs 5.3k ★
Claude Balancer — A load balancer proxy for multiple Claude OAuth accounts with automatic failover, request tracking, and web da 910 ★
MiniCode Architecture — 简体中文 This document describes the lightweight architecture decisions behind mini-code 388 ★

README

claude-oauth

Run other models inside Claude Code over their own OAuth sessions, **without replacing the native Claude path.** `claude` stays native. `claude-oauth` opens the router.

**Status: pre-release. Not ready to use, and deliberately not pretending otherwise.** Several capability claims below are gated on open defects (see [Known gaps](#known-gaps)). This README documents what is measured, what is not, and what is broken. Project page: · Security: [SECURITY.md](SECURITY.md) · Contributing: [CONTRIBUTING.md](CONTRIBUTING.md) · Changes: [CHANGELOG.md](CHANGELOG.md)

Why this exists

Two goals. The mechanism is the same for both; the second is the one that shaped the code.

**1. Make Claude Code reachable for students and researchers.** Claude Code is an agent harness, not a chat window: tools, subagents, skills, MCP servers and permission prompts in one loop. Learning it is worth a student's time. Paying for it is often not possible. Many students and researchers already hold a model plan of some kind: Google's student Gemini offer, a ChatGPT plan, an xAI plan. `claude-oauth` lets those plans answer inside Claude Code, over the account's own OAuth session, with no API key and no separate bill. The harness becomes learnable on the plan you already have, and the native `claude` path stays exactly as installed for the day you move to it.

**2. Raise the quality of work done inside Claude Code by letting other models verify it.** A model that wrote a change is the worst judge of that change. The working pattern behind this project is a maker and a checker that are never the same model: one produces the diff, the manuscript, the analysis; another, in a fresh context, reads the output and reports what is wrong with it. Claude Code already has the mechanism, the `Agent` tool and subagents. What it lacks is a second model to hand the work to. This repository supplies it: one delegate agent per routed mo