dsh-codex-subscription — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 WSL043 · Codex Skill · ★ 127

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

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

About dsh-codex-subscription

DSH Codex Subscription — 在 DeepSeek Harness 使用 ChatGPT 订阅 简体中文 · English 把 ChatGPT / Codex 订阅直接接入 DeepSeek Harness 在 DeepSeek Harness 中直接登录 ChatGPT 并使用 Codex 订阅。无需 OpenAI API Key,也不依赖 Codex CLI; 模型、搜索、额度和图片生成都留在 DSH 里。 三步开始 · 安装 · 参与贡献 · 更新与卸载 已适配 DSH 的插件兼容性检查与设置接口,同时保留已支持版本的兼容。 三步开始 安装插件:打开 插件 → 添加插件,在 包名或地址 中填写 ,点击 安装。 登录订阅:按安装结果提示操作;若提示需要重启,先保存工作再重启。打开 设置 - Codex 订阅

ai-agentchatgptchatgpt-oauthchatgpt-pluscodexcodex-subscriptiondeepseekdeepseek-harnessdshdsh-plugin

Quick Facts

Stars127
Forks13
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score66.5608440224186/100
Open Issues1
Last Updated2026-10-03
Created2026-08-13
Platformsbrowser, cli, codex, node
Est. Tokens~15k

dsh-codex-subscription alternative? Top 6 similar tools

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

  • modsearch by liustack · ⭐ 540

    🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na

  • cetus by drewnekota · ⭐ 147

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher

  • graph-memory by adoresever · ⭐ 633

    Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory;Knowledge Graph Context Engine

  • teamclaude by KarpelesLab · ⭐ 373

    Multi-account proxy for Claude Code and Codex: pools Claude Max, ChatGPT/Codex, API-key and third-party backen

  • oc-codex-multi-auth by ndycode · ⭐ 193

    OpenCode plugin for ChatGPT Plus/Pro OAuth with Codex/GPT-5 routing, multi-account rotation, account switching

  • codex-multi-auth by ndycode · ⭐ 526

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

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is dsh-codex-subscription?

dsh-codex-subscription is Use your ChatGPT / Codex subscription with DeepSeek Harness via OAuth, with model access, usage quotas, search, and image generation — no API key or Codex CLI required.. It is categorized as a Codex Skill with 127 GitHub stars.

What programming language is dsh-codex-subscription written in?

dsh-codex-subscription is primarily written in JavaScript. It covers topics such as ai-agent, chatgpt, chatgpt-oauth.

How do I install or use dsh-codex-subscription?

You can find installation instructions and usage details in the dsh-codex-subscription GitHub repository at github.com/WSL043/dsh-codex-subscription. The project has 127 stars and 13 forks, indicating an active community.

What license does dsh-codex-subscription use?

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

What are the best alternatives to dsh-codex-subscription?

The top alternatives to dsh-codex-subscription on Agent Skills Hub include modsearch, cetus, graph-memory. 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