cafleet — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 himkt · Codex Skill · ★ 51

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

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

About cafleet

CAFleet https://github.com/user-attachments/assets/bd2b195a-f3de-4fa3-bcc8-3c6ef9f1016a Agent Teams reinvented for collaborative coding across multiple coding-agent backends (Claude Code, Codex, and OpenCode), with full code transparency. Who is CAFleet for Developers running multi-agent coding teams in tmux who want every inter-agent message persisted and auditable. Teams mixing , , and members in one fleet. Operators who want a single-file SQLite broker with no server to run. Install CAFleet works with three coding agents: (Claude Code), (OpenAI Codex CLI), and . Install the plugin in whichever one you use — the broker CLI is shared. 2.1. CAFleet skills Use your favorite tool to install skills (for example, GitHub CLI , vercel , or the marketplace of each coding agent). (a) GitHub CLI (recommended) (b) Claude Code marketplace (if you prefer) (c) Codex (if you prefer) 2.2. CAFleet CLI (required for CAFleet to function) bash uv tool install cafleet # or: pip install cafleet cafleet db init # apply schema migrations (idempotent; rerun after u

agentagent-teamsclaude-codecodexcoding-agentopencodeskills

Quick Facts

Stars51
Forks4
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score63.0967120332732/100
Open Issues2
Last Updated2026-09-22
Created2026-03-28
Platformsclaude-code, codex, rust
Est. Tokens~22k

cafleet alternative? Top 6 similar tools

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

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • aivo by yuanchuan · ⭐ 194

    Use your favorite coding agent with any model.

  • antigravity-workflows by harikrishna8121999 · ⭐ 187

    Community-driven workflows for Antigravity AI. Like Claude Skills - reusable prompts and automation for AI cod

  • ask-user-questions-mcp by paulp-o · ⭐ 147

    Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your L

  • my-ai-tools by jellydn · ⭐ 121

    Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, Open

  • ralph-starter by multivmlabs · ⭐ 97

    Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is cafleet?

cafleet is 🛰️ Coding Agent Fleet (cafleet) is a coding agent orchestrator for multi-agents collaboration across coding agent providers. It is categorized as a Codex Skill with 51 GitHub stars.

What programming language is cafleet written in?

cafleet is primarily written in Rust. It covers topics such as agent, agent-teams, claude-code.

How do I install or use cafleet?

You can find installation instructions and usage details in the cafleet GitHub repository at github.com/himkt/cafleet. The project has 51 stars and 4 forks, indicating an active community.

What license does cafleet use?

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

What are the best alternatives to cafleet?

The top alternatives to cafleet on Agent Skills Hub include palot, aivo, antigravity-workflows. 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