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 guard22 · Codex Skill · ★ 132
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is opencode-multi-auth-codex safe to install? View the security audit →
opencode-multi-auth-codex Multi-account OAuth rotation plugin for OpenCode with a local dashboard, force mode, weighted settings, limits probing, and reliability hardening. Documentation map - primary operator and developer documentation for current behavior. - concise upstream/admin review summary. - final validation report (current readiness reference). - live/manual testing runbook. - full docs index with authoritative vs historical references. What this project does Rotates requests across multiple ChatGPT/Codex OAuth accounts. Keeps a local account store with migration, validation, and atomic writes. Provides a localhost dashboard to manage accounts and limits. Supports force mode (pin one alias), account enable/disable, and re-auth. Supports settings-driven rotation strategy (, , , ). Probes limits safely and keeps authoritative data quality rules. Gates non-core Antigravity features behind a feature flag. Current implementation status Core phases A-G are implemented in this workspace. Validation scripts are available for: unit, integration, web-headless, failure, stress, sandbox, soak. Web hardening fixes are in place: localhos
| Stars | 132 |
| Forks | 19 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 73.9845217395205/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-28 |
| Created | 2026-01-14 |
| Platforms | codex, node |
| Est. Tokens | ~35k |
These tools work well together with opencode-multi-auth-codex for enhanced workflows:
Looking for a opencode-multi-auth-codex alternative? If you're comparing opencode-multi-auth-codex 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.
OpenCode plugin for ChatGPT Plus/Pro OAuth with Codex/GPT-5 routing, multi-account rotation, account switching
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Codex CLI multi-account OAuth manager with account switching, health checks, runtime rotation, diagnostics, an
Run multiple AI coding accounts at the same time.
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Explore other popular codex skill tools:
opencode-multi-auth-codex is Multi-account authentication plugin for OpenCode/Codex — rotate API keys, manage sessions, auto-login. It is categorized as a Codex Skill with 132 GitHub stars.
opencode-multi-auth-codex is primarily written in TypeScript. It covers topics such as ai-coding, authentication, codex.
You can find installation instructions and usage details in the opencode-multi-auth-codex GitHub repository at github.com/guard22/opencode-multi-auth-codex. The project has 132 stars and 19 forks, indicating an active community.
The top alternatives to opencode-multi-auth-codex on Agent Skills Hub include oc-codex-multi-auth, Overture, codex-multi-auth. 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: