Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL
dsh plugin for openai codex subscriptions that can pool multiple accounts.
Project Overview项目介绍
This is a DSH-native plugin built exclusively for the DeepSeek Harness ecosystem, designed to let users manage a pool of multiple OpenAI Codex subscription accounts directly within DSH. It also includes a pre-vendored copy of the official OpenAI Docs skill pulled from OpenAI’s public skills repository. To install the plugin, users run a simple command via the DSH CLI: dsh plugin --profile web add github:Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL, which adds the plugin to the user’s DSH web profile automatically. It supports multi-account OpenAI Codex OAuth authentication, usage controls, web search, and image generation, and its user interface matches the language setting selected in DSH.
After installation completes, users need to restart their DSH instance to load the plugin fully into the runtime. Once DSH restarts, users navigate to the DSH settings menu, select OpenAI Codex from the sidebar, log in to their OpenAI subscription accounts, then select OpenAI Codex as the active model provider in the Models tab. It is intended for DSH users who want to use OpenAI Codex models within DSH and spread usage across multiple subscriptions to avoid hitting individual rate or quota limits. The plugin also includes an optional filter that recognizes new GPT-6 and Astra rollout entries without changing existing user model selections.
For local development, the plugin requires the pnpm package manager to work with the TypeScript source code. Developers first run pnpm install to install all required dependencies, then pnpm run build to compile the source code into a production-ready bundle, and can load the local build into DSH for testing via the DSH CLI. The main plugin code is distributed under the GPL-3.0-only license, while the vendored OpenAI Docs skill retains its original upstream license from the OpenAI skills repository. It is built only for DSH and does not work with any other AI agent platforms.
这是一个专为 DeepSeek Harness (DSH) 开发的原生插件,核心功能是帮助用户在 DSH 中管理多个 OpenAI Codex 订阅账号池。它支持多账号的 OpenAI OAuth 认证、使用权限控制,还提供网页搜索和图像生成能力,界面语言会自动跟随 DSH 的系统语言设置。用户可以通过 DSH 内置的命令行工具,直接输入指定命令就能将该插件添加到自己的 DSH Web 配置文件,完成安装流程。
安装完成后,用户需要重启 DSH 才能开始后续配置流程。首先打开 DSH 的设置界面,在侧边栏找到 OpenAI Codex 选项,登录自己的 OpenAI 订阅账号,随后在模型选项卡中选择 OpenAI Codex 作为默认提供商即可开始使用。该插件面向需要在 DSH 中使用 OpenAI Codex 模型、同时希望管理多个订阅账号来分摊用量限制的开发者和普通用户。
该插件使用 TypeScript 开发,开发阶段依赖 pnpm 包管理器,需要执行 pnpm install、pnpm run build 等命令完成构建。项目整体采用 GPL-3.0 许可证分发,其中内置的来自 OpenAI 官方技能仓库的 OpenAI Docs 技能保留其上游原许可证。该插件仅针对 DSH 开发,不支持其他第三方 AI 代理平台。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:DSH-CODEX-SUBSCRIPTION-POOL(Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL)
仓库:https://github.com/Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL
本站详情页:https://www.yhbd.top/plugins/eve-146t-dsh-codex-subscription-pool/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 GPL-3.0 · ⭐ 2 · 最近提交 2026-09-05 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add github:Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL
把 Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
OpenAI Codex Plugin for the DeepSeek Harness
Lets you manage your pool of OpenAI subscriptions in DSH.
Features
- Multi-account OpenAI Codex OAuth and usage controls
- Web search and image generation
- Chinese UI follows the language selected in DSH
- Model identity and routing guidance for agents
- The official OpenAI Docs skill, vendored from openai/skills
The plugin adds a durable runtime-context snapshot that tells an agent its
active provider/model, the models advertised by the openai-codex adapter,
what Sol, Terra, and Luna are for, and which orchestration tools accept an
explicit model. DSH writes this snapshot at session start and replaces it only
when the active model or advertised catalogue changes; it is not repeated on
every request.
Install the DeepSeek Harness Codex plugin
Add it to your DSH Web profile:
dsh plugin --profile web add github:Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL
Tutorial
# install the plugin
dsh plugin --profile web add github:Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL
# restart dsh
dsh --profile web
Then:
- Open Settings
- Click OpenAI Codex in the sidebar and login
- Choose OpenAI Codex as the provider in the Models tab
The optional model filter recognizes GPT-6 and Astra rollout entries while keeping the current model selection unchanged.
Development
pnpm install
pnpm run build
pnpm test
dsh plugin --profile web add ./openai-codex-auth
License
This project is distributed under GPL-3.0-only. The vendored OpenAI Docs skill retains its upstream license.
Q00/ouroboros
crafter-station/petdex
whiteguo233/OpenBiliClaw
anywhere-labs/Agents-Anywhere
agentrq/agentrq
freestylefly/wesight