mixagents — security grade SAFE, quality 52/100

Security audit verdict: SAFE · quality 52/100

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 Utopia-V · Codex Skill · ★ 184

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

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

About mixagents

English mixagents 这里收录两套彼此独立的 Agent 集成。它们解决的问题不同,可以单独安装。 Codex DeepSeek Subagent 让 Codex 主任务继续使用 OpenAI,把边界明确、文本量较大的任务交给 子代理。当前版本使用一次性 plaintext Hook,绕过 Codex 跨 provider 子任务正文不可读的问题。 安装使用 · 高级说明 · 安全边界 pi-dsh-mimic 只修改 DeepSeek V4 Pro 在 Pi 中的第一次请求:先使用 DSH Minimal 的 persona 和两个 工具,第一次有效响应后恢复 Pi 原生请求与完整工具目录。在同一个冻结 Project2 任务中, 默认 Pi 得到 92,四次相同流程得到 96–98;这个结果不代表通用 benchmark。 安装使用 · 实验与设计 · 证据账本 · 安全边界 安装前 两套集成都会把任务内容发送给用户配置的第三方 provider。Codex 组件会在本地用户状态中 短暂保存明文任务;Pi 组件提供可以读写文件的 。DeepSeek 与 OpenCode 的费用独立于 ChatGPT/OpenAI 订阅。仓库级说明见 SECURITY.md。 各组件的源码、测试和文档都在自己的 目录中。根目录 只保留旧 raw URL 的转发入口。Issue 与贡献约定见 .github/CONTRIBUTING.md。 本仓库是独立社区项目,与 OpenAI、DeepSeek、Pi 或 OpenCode 均无隶属或官方背书关系。

ai-agentscodexdeepseekextensionsmulti-agentpiresponses-apisubagenttypescript

Quick Facts

Stars184
Forks13
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score51.9478635863879/100
Open Issues2
Last Updated2026-09-04
Created2026-08-04
Platformscodex, node
Est. Tokens~14k

Compatible Skills

These tools work well together with mixagents for enhanced workflows:

  • Deepseek-API — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • villani-code — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • recall — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

mixagents alternative? Top 6 similar tools

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

  • Codeman by Ark0N · ⭐ 763

    Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemi

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • codex-multi-auth by ndycode · ⭐ 500

    Codex CLI multi-account OAuth manager with account switching, health checks, runtime rotation, diagnostics, an

  • codex-app-transfer by Cmochance · ⭐ 302

    Local desktop gateway that translates OpenAI Codex CLI's Responses API into Chat Completions for Kimi / DeepSe

  • vibepod-cli by VibePod · ⭐ 165

    Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H

  • agent-skills by simota · ⭐ 80

    90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anth

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is mixagents?

mixagents is Harness-native agent components for Codex and Pi: a DeepSeek V4 Flash subagent and a DSH Minimal mimic for V4 Pro.. It is categorized as a Codex Skill with 184 GitHub stars.

What programming language is mixagents written in?

mixagents is primarily written in TypeScript. It covers topics such as ai-agents, codex, deepseek.

How do I install or use mixagents?

You can find installation instructions and usage details in the mixagents GitHub repository at github.com/Utopia-V/mixagents. The project has 184 stars and 13 forks, indicating an active community.

What license does mixagents use?

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

What are the best alternatives to mixagents?

The top alternatives to mixagents on Agent Skills Hub include Codeman, 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.

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