Codirigent — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 oso95 · Codex Skill · ★ 103

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

🔒 Is Codirigent safe to install? View the security audit →

About Codirigent

Codirigent A terminal workspace for running multiple AI coding CLIs in parallel Website · Download · Report a Bug · 繁體中文 · 简体中文 https://github.com/user-attachments/assets/51b821fd-dfc3-40f0-b1f3-e8727045f474 If you're running Claude Code, Codex, or Gemini across multiple projects at the same time, you know the pain: opening terminals, -ing into repos, arranging windows, losing track of which agent is doing what. Codirigent is a Tmux-style workspace built for this workflow. Open it once, and your sessions are already where you left them — right directory, right layout, right agent. Features Multiple sessions, one view — run Claude Code, Codex, and Gemini side by si

ai-agentsclaude-codeclicodexdesktop-appdeveloper-toolsgemini-clillmorchestrationrust

Quick Facts

Stars103
Forks10
LanguageRust
CategoryCodex Skill
LicenseGPL-3.0
Quality Score65.6934749836468/100
Open Issues6
Last Updated2026-07-09
Created2026-02-02
Platformsclaude-code, cli, codex, gemini, rust
Est. Tokens~23k

Compatible Skills

These tools work well together with Codirigent for enhanced workflows:

  • superset — semantic(0.47)+complementary+rare_topics+shared_platform (60%)
  • ccboard — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • forge-orchestrator — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)
  • octomind — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

Codirigent alternative? Top 6 similar tools

Looking for a Codirigent alternative? If you're comparing Codirigent 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.

  • genie by automagik-dev · ⭐ 334

    Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated work

  • toktrack by mag123c · ⭐ 189

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

  • hcom by aannoo · ⭐ 431

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • models by arimxyer · ⭐ 416

    TUI and CLI for browsing AI models, benchmarks, coding agents, and statuses for AI providers.

  • groundcrew by ClipboardHealth · ⭐ 64

    Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by def

  • run-kit by sahil87 · ⭐ 59

    A remote, phone-first console for your tmux — agent-agnostic, no database. Spawn and watch coding agents in pa

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is Codirigent?

Codirigent is A terminal workspace for running multiple AI coding CLIs in parallel. It is categorized as a Codex Skill with 103 GitHub stars.

What programming language is Codirigent written in?

Codirigent is primarily written in Rust. It covers topics such as ai-agents, claude-code, cli.

How do I install or use Codirigent?

You can find installation instructions and usage details in the Codirigent GitHub repository at github.com/oso95/Codirigent. The project has 103 stars and 10 forks, indicating an active community.

What license does Codirigent use?

Codirigent is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Codirigent?

The top alternatives to Codirigent on Agent Skills Hub include genie, toktrack, hcom. 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