codex-profiles — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 Ducksss · Codex Skill · ★ 149

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is codex-profiles safe to install? View the security audit →

About codex-profiles

codex-profiles Two Codex profiles. One Mac. No token swapping. Project page | llms.txt | GEO audit Switch Codex CLI and Desktop accounts with isolated profiles. Keep personal, work, school, and client state separated without copying token files around. is a small Bash wrapper around Codex's support. Each profile gets its own Codex home directory, so auth, settings, sessions, connectors, plugins, caches, logs, and local state stay separated while the wrapper launches Codex CLI or Codex Desktop with the selected profile. sh

account-switcherai-toolsautomationbashchatgptchatgpt-desktopclicodexcodex-clicodex-desktop

Quick Facts

Stars149
Forks10
LanguageShell
CategoryCodex Skill
LicenseMIT
Quality Score70.059640800894/100
Open Issues1
Last Updated2026-09-15
Created2026-04-25
Platformscli, codex
Est. Tokens~15k

codex-profiles alternative? Top 6 similar tools

Looking for a codex-profiles alternative? If you're comparing codex-profiles 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.

  • code-notify by mylee04 · ⭐ 288

    Cross-platform desktop notifications for Claude Code, Codex, and Gemini CLI. Install via Homebrew, npm, or scr

  • mobius by chussum · ⭐ 54

    ∞ macOS menu bar app for switching Claude Code / OpenAI Codex / Claude Desktop accounts in one click — auto-fa

  • codemap by JordanCoin · ⭐ 689

    a project brain for your AI. Give LLMs instant architectural context without burning tokens

  • claude-code-statusline by rz1989s · ⭐ 477

    Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos

  • daymon by daymonio · ⭐ 368

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • codex-settings by feiskyer · ⭐ 232

    Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is codex-profiles?

codex-profiles is Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens. It is categorized as a Codex Skill with 149 GitHub stars.

What programming language is codex-profiles written in?

codex-profiles is primarily written in Shell. It covers topics such as account-switcher, ai-tools, automation.

How do I install or use codex-profiles?

You can find installation instructions and usage details in the codex-profiles GitHub repository at github.com/Ducksss/codex-profiles. The project has 149 stars and 10 forks, indicating an active community.

What license does codex-profiles use?

codex-profiles is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-profiles?

The top alternatives to codex-profiles on Agent Skills Hub include code-notify, mobius, codemap. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools