multi-cli — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 Spielewoy · Codex Skill · ★ 245

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

🔒 Is multi-cli safe to install? View the security audit →

About multi-cli

multi-cli Run multiple isolated instances of any AI coding tool : simultaneously. No more logging in and out. Launch as many sandboxed profiles as you need, each with its own auth, config, sessions, and extensions. Switch between work accounts, client projects, or personal setups instantly. 🌐 Language / 语言: 🇬🇧 English Supported Tools r

account-isolationaccount-managementai-agentsai-cliai-codingai-coding-toolsbashclaude-codeclicodex-cli

Quick Facts

Stars245
Forks16
LanguagePowerShell
CategoryCodex Skill
LicenseMIT
Quality Score72.4376170644489/100
Last Updated2026-08-19
Created2026-04-26
Platformsclaude-code, cli, codex, gemini
Est. Tokens~19k

Compatible Skills

These tools work well together with multi-cli for enhanced workflows:

  • claude-code-profiles — semantic(0.31)+complementary+rare_topics+similar_pop+shared_platform (60%)
  • dotbot — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • ClaudeCodeStatusLine — semantic(0.15)+complementary+rare_topics+similar_pop+shared_platform (54%)

multi-cli alternative? Top 6 similar tools

Looking for a multi-cli alternative? If you're comparing multi-cli 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.

  • TokenTracker by mm7894215 · ⭐ 1.1k

    Local-first AI token usage & cost tracker for 28 coding tools incl. Claude Code, Codex, Cursor, Gemini & Qoder

  • speckit-agent-skills by dceoy · ⭐ 134

    Agent skills for Spec Kit

  • claude-code-profiles by quinnjr · ⭐ 95

    Manage multiple Claude Code configuration profiles. Switch between work, personal, and other accounts without

  • parallel-code by johannesjo · ⭐ 1.0k

    Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • Claude-Skills by borghei · ⭐ 475

    368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-lev

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular PowerShell Agent Tools

Frequently Asked Questions

What is multi-cli?

multi-cli is Run multiple AI coding accounts at the same time.. It is categorized as a Codex Skill with 245 GitHub stars.

What programming language is multi-cli written in?

multi-cli is primarily written in PowerShell. It covers topics such as account-isolation, account-management, ai-agents.

How do I install or use multi-cli?

You can find installation instructions and usage details in the multi-cli GitHub repository at github.com/Spielewoy/multi-cli. The project has 245 stars and 16 forks, indicating an active community.

What license does multi-cli use?

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

What are the best alternatives to multi-cli?

The top alternatives to multi-cli on Agent Skills Hub include TokenTracker, speckit-agent-skills, claude-code-profiles. 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