No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ndycode · Codex Skill · ★ 526
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-multi-auth safe to install? View the security audit →
codex-multi-auth: multi-account OAuth for the official Codex CLI is a multi-account OAuth manager for the official CLI. It gives Codex CLI users explicit ChatGPT account login, account switching, health checks, local diagnostics, project-scoped storage, and default-on runtime Responses rotation without taking over the official binary. Use for account management, or only when you intentionally want the optional forwarding wrapper. Use it when you need a local Codex CLI multi-account workflow with visible account state, safer recovery commands, and a loopback-only runtime rotation proxy for request-bearing forwarded Codex sessions. [!NOTE] Legacy scoped prerelease package is m
| Stars | 526 |
| Forks | 67 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 76.2487414896511/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-02 |
| Created | 2026-02-22 |
| Platforms | cli, codex, node |
| Est. Tokens | ~18k |
These tools work well together with codex-multi-auth for enhanced workflows:
Looking for a codex-multi-auth alternative? If you're comparing codex-multi-auth with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Multi-account proxy for Claude Code and Codex: pools Claude Max, ChatGPT/Codex, API-key and third-party backen
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
Lightweight Agent Workstation for Codex + Claude code — with dots, task scheduler, git worktree & remote contr
Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Ski
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - th
Explore other popular codex skill tools:
codex-multi-auth is Codex CLI multi-account OAuth manager with account switching, health checks, runtime rotation, diagnostics, and recovery tools for @openai/codex. It is categorized as a Codex Skill with 526 GitHub stars.
codex-multi-auth is primarily written in TypeScript. It covers topics such as account-health, account-switching, chatgpt.
You can find installation instructions and usage details in the codex-multi-auth GitHub repository at github.com/ndycode/codex-multi-auth. The project has 526 stars and 67 forks, indicating an active community.
codex-multi-auth is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-multi-auth on Agent Skills Hub include teamclaude, inspector, codexia. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: