@uu88s/dsh-session-handoff：把 DSH 会话复制 id 或交接给 codex resume
DSH Web 插件 @uu88s/dsh-session-handoff 支持一键复制 DSH 会话 id，或将完整会话（对话、工具调用与输出、文件变更清单）转写进 codex 会话库并登记索引，给出 codex resume 命令。采用两步预演、只增不改与可撤销；v1 仅适配 codex。安装需 dsh --profile web 与 Node 22+，交接结果为快照，源会话后续变更需重新交接。
Read Moredsh-openai-auth：在 Harness 桌面版复用本机 Codex ChatGPT 订阅
dsh-openai-auth 是 solstice621 维护的 DeepSeek Harness 客户端插件，在桌面版识别或完成本机 Codex CLI 的 ChatGPT 登录，复用 Codex 订阅额度，并提供原生 OpenAI/Codex 设置页（授权、额度、模型同步）。无需 OpenAI Platform API key；已验证 macOS 与 Harness 0.2.0-rc.2。安装包地址 github:solstice621/dsh-openai-auth#v0.3.2，MIT 许可。
Read Moredsh-codex-plus：把本机 Codex 订阅接入 DeepSeek Harness
dsh-codex-plus 是 mia-wong1016 维护的 DSH Web 插件，读取本机 Codex CLI 登录态，在侧边栏展示 5 小时与一周窗口额度、重置时间与重置券，支持选券一键重置。读额度时自动注册 openai-codex 路由，模型选择器出现 Codex (ChatGPT Plus/Pro)；token 不足 24 小时时向 auth.openai.com 续期并原子写回 auth.json，密钥进 DSH credential store，无需 API key。安装：dsh plugin --profile web add dsh-codex-plus。支持 Linux/Windows，Node 20+，MIT。
Read Morecodex自动化口播剪辑 skill：把竖屏口播成片流程写进 Agent
codex自动化口播剪辑 skill 是 SkillHub 社区包（v1.0.0，design-media），面向竖屏中文真人出镜短视频。它以 SKILL.md 规定启动门槛与八步流程：素材盘点、画面调校、语音结构与语义剪辑、HyperFrames 动画、字幕、音乐混音、导出自检，并强调先调光再包装、文字不挡脸、改版不覆盖终稿。安装可参考 skillhub.cn/install/skillhub.md，安装 @indiv-haikousohot/dfdf54554rtrt 或 @user_268e6861/dfdf54554rtrt 到当前 Agent 的 skills 目录；可与 video-use、HyperFrames 配合。适合需要可重复抖音风格口播成片的 Codex/Cursor 等 Skills 用户。
Read More使用 Nature Skills 运行自然风格学术写作与图表工作流程
SkillHub 社区 Skill「使用 Nature Skills 运行自然风格的学术写作和图表工作流程」（v1.0.0）将手稿润色、学术写作、引用、论文阅读、回复起草、数据处理、幻灯片与科学图表等能力打包为可重用的 Codex 或 Claude Code 技能包，且标注 requires_api_key=false。本文依据 SkillHub 页面与安装文档说明坐标、功能边界，以及通过 Agent 提示或 skillhub install --dir 安装到 ~/.cursor/skills/ 等目录的步骤与注意事项。
Read MoreCodex DSH Bridge：通过 MCP 将 Codex 会话连接到 DeepSeek Harness Web
journ10/codex-dsh-bridge 是一个 HTTP MCP 服务器，旨在连接本地 CLI 工具（如 Codex）与 DeepSeek Harness (DSH) Web 界面。它允许通过 MCP 协议管理 DSH 会话的生命周期，包括新建任务、发送消息、等待结果及查询状态。 安装需 DSH 版本 0.2.1-alpha.2，使用 `dsh plugin` 添加，默认监听 3080 端口。配置时需在 Codex 中指定 URL 并设置环境变量获取令牌。该插件支持同步和异步模式，但不支持非 Web profile。
Read Moresecond-opinion: External Code Review of Git Changes with Codex or Antigravity
second-opinion is an Agent Skill in the Trail of Bits skills marketplace. It invokes Codex, Antigravity, or Gemini CLI to perform independent code reviews and consolidate findings for uncommitted changes, branch diffs, or specified commits, supporting side-by-side comparison of two providers on the same patch. It does not automatically modify code or post to a remote. The article explains the review scope and focus, diff and temporary-file conventions, CLI invocation methods, and marketplace installation commands and official slash-command examples for Claude Code and Codex.
Read MoreDeepSeek Harness Plugin: Codex and Claude Code Subagent Presets
The `dsh-preset-codex-claude` plugin enables DeepSeek Harness (DSH) to integrate Codex and Claude Code through official subagents. It supports read/write separation and parallel execution, and provides two permission modes: full access and read-only. Installation first requires installing dependency packages into the DSH root directory, then importing them via a Profile. The plugin provides four tools (such as `subagent_codex`), and subagents run as independent processes without inheriting session context. When using the plugin, attention should be paid to version compatibility, process-level caching, and session isolation issues.
Read Morejuyanjy/dsh-codex-bridge: Connect and Guide Local Codex Sessions from Harness
The DeepSeek Harness plugin `dsh-codex-bridge` connects to and controls the local Codex process via the Codex app-server protocol. It provides status monitoring (such as account, thread, and real-time stream information), interactive control (sending commands and taking over a session), and a visualization panel, with support for automatic message continuation. The plugin runs in a Node.js environment. Note that session takeover must be explicitly declared, and some data uses a sampling mechanism.
Read Moreesroamer/codex-dsh-collab: A Desktop-Level Collaboration Plugin for Codex and DSH
`esroamer/codex-dsh-collab` is a DeepSeek Harness (DSH) plugin designed to address pain points in collaboration between Codex and desktop environments. It allows Codex to delegate tasks to desktop-visible DSH agents, supporting task tracking, workspace-aware collaboration, and scoped credential management. Installation requires adding the plugin in DSH and running a PowerShell script to authorize the workspace. The project is released under the MIT license and supports Windows only.
Read Moredsh-context-window: Replicating Codex's Context Window Management
`dsh-context-window` is a DSH plugin designed to address information loss caused by traditional summarization compression when the context window fills up. It replicates Codex’s context-window swapping mechanism, using context swapping instead of frequent compression and preserving details through notes and handoff checkpoints. Core functionality includes two modes: the `handoff` mode without summarization (recommended, directly writing to a handoff checkpoint) and the `seam-region` mode with traditional compression. The plugin provides `new_context` and `notes` tools for the model to invoke, and generates handoff information containing the objective, tasks, notes, and the last request when swapping context windows. Note that `handoff` mode does not emit a UI-visible compression event, and swapping is only allowed at step boundaries.
Read MoreDSH Codex Subscription: Use Your ChatGPT / Codex Subscription Directly in DeepSeek Harness
The DSH Codex Subscription plugin allows users to sign in to their ChatGPT account via OAuth and use Codex subscription models directly in DeepSeek Harness without manually managing API keys. The plugin supports quota monitoring, search, image generation, and custom context window settings. To use it, users must install the plugin via the terminal and restart DSH, then sign in with an account that has Codex access in the settings.
Read Moredsh-plugin-local-agent-bridge: Control Claude Code and Codex in the Browser
`dsh-plugin-local-agent-bridge` is a client plugin that connects local Claude Code and Codex sessions to the DeepSeek Harness browser interface. It uses a local process bridge to keep authentication and execution on the host terminal while the browser serves only as the UI, avoiding frequent window switching. The plugin provides a unified panel, keyboard shortcuts, multiple permission modes, session monitoring, and native tool approval. Installation must meet specific version requirements and be launched through the built-in web profile to ensure credentials are not transferred.
Read Moredsh-memory: A Codex-Style Persistent Memory Plugin for DeepSeek Harness
The DeepSeek Harness plugin `dsh-memory` provides persistent memory for agents, addressing the loss of context in multi-turn conversations. Its core features include persistent storage, automatic summary injection, a memory toolset, and configuration via a web interface. Installation requires specifying a version hash and restarting the environment. The plugin operates in the `$DSH_HOME/memories/` directory and achieves long-term memory capabilities similar to Codex by automatically distilling conversation turns and periodically merging them into a global summary. It supports initializing seed memory from `AGENTS.md` and provides tools for reading and writing memory.
Read MoreDeepSeek Harness Plugin: Using OpenAI Codex Subscription via OAuth
This document introduces the `dsh-codex-oauth` plugin in the DeepSeek Harness plugin system. It fills a gap in the upstream adapter by providing OAuth credential storage and login commands for Codex authentication. Installation requires addressing pnpm build limitations, and login supports both Web UI and CLI modes. The plugin registers the `codex` provider route, supports models such as `gpt-5.x-codex`, and allows transport and caching policies to be configured via a configuration file. Usage requires a ChatGPT Plus subscription and enforces strict file permissions.
Read Moredsh-codex-relay: Provider Plugin for Selecting Codex Models in DeepSeek Harness
# Introduction The design philosophy of DeepSeek Harness (hereinafter referred to as DSH) is "everything is a plugin," and model inference is also handled by provider plugins. If you are already logged into Codex CLI locally and wish to directly utilize the models exposed by your native Codex account and their inference strength within a DSH session—rather than manually transferring context between two separate tool sets—you need a bridging layer. The plugin introduced below, `@necokeine/dsh-codex-relay`, accomplishes exactly that. # What is this `dsh-codex-relay` is a DSH provider plugin maintained by necokeine, belonging to the model inference category. The current version is 0.1.2, and the license is MIT. It works by...
Read Morecatalog-capabilities-zh: Maintain a source-based Chinese capabilities catalog for DSH
catalog-capabilities-zh is an MIT-licensed community project maintained by MeowTnT3r. Acting as a DSH bundle plugin and runtime skill, it maintains a source-based Chinese capabilities catalog for skills, plugins, and marketplace capabilities. It follows the "everything is a plugin" philosophy, addressing the pain points of scattered DSH user plugins, predominantly English READMEs, and difficulty in finding them. Its core feature is a default curated mode where only user-confirmed entries are written to the documentation; scanning serves only as a discovery aid, and explicit full inclusion requires the `--all` or `full` mode. It does not rewrite installation logic; instead, it orchestrates existing trusted installers in the environment during installation. If the target is already installed, it only verifies update instructions. When only providing a link, it reads public repository metadata for checks and introduction without executing the repository code. Entries support sorting by Chinese...
Read Moredsh-observability: Add attribution for DSH external sub-agent calls
dsh-observability is an MIT-licensed plugin maintained by jeremy9682, aimed at solving the observability issue of verifying session outputs after DSH invokes external sub-agents (such as Codex and Cursor). The repository contains two core plugins: dsh-codex-observability and dsh-tool-cursor. The former tracks directories such as `~/.codex/sessions` via fingerprinting, writes attribution pointers like `sessionRef` into journal files, recording only the pointers without storing prompt or transcript content. The latter provides the `cursor_delegate` tool, supporting the delegation of tasks to the Cursor CLI, and defaults to read-only but supports editing.
Read Moredsh-agent-conductor: Dispatching Tasks to External Agent CLIs within DeepSeek Harness Sessions
dsh-agent-conductor is an MIT-licensed plugin maintained by MJorgin, designed to extend the capabilities of DeepSeek Harness (DSH) sessions. It allows users to dispatch self-contained tasks to 11 external Coding Agent CLIs (including Codex, Claude Code, Gemini, Cursor, and others) within DSH, directly bringing back the standard output results from the target CLI into the current conversation. The tool offers two integration methods: a zero-dependency Skill, which enables natural language triggering by copying the `skills/conductor/` directory; and an optional Host-only Bundle, which can be installed as a Profile tool via the `dsh plugin` command.
Read Moredsh-openai-oauth: Integrating Codex Model into DeepSeek Harness via ChatGPT Login
`dsh-openai-oauth` is a standalone community plugin for DeepSeek Harness (DSH) designed to address external model login status, credential storage, and model list management. This plugin works by connecting to the official local Codex app-server, leveraging the OAuth mechanism of ChatGPT accounts to handle login, credential saving, token refreshing, and model access, eliminating the need for users to separately prepare an OpenAI API key or maintain a hardcoded model version list. Key features include automatic registration to DSH's web, headless, and custom profiles, with support for configuring providers and models via the interface or the `~/.dsh/settings.yaml` file. The model list is updated in real-time from the current
Read Moredsh-codex-auth: Reusing Codex CLI Login to Integrate GPT Auth and Codex Capabilities into DSH
dsh-codex-auth is a DSH client plugin (v0.3.0) maintained by suntianc. It leverages the local Codex CLI's ChatGPT login state to provide openai-codex LLM routing, global web search, image generation, and a native GPT Auth settings interface. Installation is recommended via `dsh plugin --profile web add dsh-codex-auth`. The plugin uses an unofficial backend API and is intended solely for personal development. Please review the source code and license before installation.
Read Moredsh-codex-sync: Two-Way Synchronization Bridge Between Codex and DSH
dsh-codex-sync is a DSH workflow plugin maintained by Walvez, providing continuous bidirectional bridging between OpenAI Codex and DeepSeek Harness: project conversations can be imported, exported, and incrementally synchronized, ~/.codex/skills is mounted in real-time as DSH Skills, mcp_servers are automatically mirrored, and a reverse MCP can be installed on the Codex side to retrieve DSH plugins. The installation command is `dsh plugin --profile web add dsh-codex-sync`, licensed under MIT, requiring Node >= 20.
Read MoreTwo approaches to integrate DeepSeek V4 into Mixagents based on Codex and Pi respectively
Mixagents is maintained by Utopia-V, open-sourced under the MIT License, and its community directory is categorized under "Models and Providers". There are two independent components in the repository: Codex DeepSeek Subagent allows the main task to continue using OpenAI, while handing over retrieval and text work to deepseek-v4-flash; pi-dsh-mimic 0.1.1 only reproduces DSH Minimal during Pi's first request, and then reverts to Pi's tools and plugins. The directory page provides the `dsh plugin add` command, and the actual installation shall be subject to the GitHub documentation.
Read More### 正式技术译法（符合海外开源项目命名习惯）： `deepseek-harness-external-migration: Migrate configurations and sessions from Codex and Claude Code into DeepSeek Harness`
A MIT plugin maintained by buguoshixc that migrates configurations and chat histories from Codex, Claude Code, Qoder and OpenCode to DeepSeek Harness. The process includes scanning, previewing and confirming the import: scanning is read-only and does not return credentials, and import requires `confirm=true`. First export a review package for configurations, replace MCP keys with environment variables, and no automatic overwriting. Requires dsh 0.1.0-rc.5 and Node.js 22.19+/24+. Installation command on the catalog page: `dsh plugin add github:buguoshixc/deepseek-harness-external-migration`.
Read MoreIntegrate ChatGPT Subscription into DeepSeek Harness via dsh-llm-codex-oauth
# 翻译结果： dsh-llm-codex-oauth is maintained by Player-MINEPIG under the MIT license. It uses the Codex OAuth device code to log into ChatGPT, exposing subscriptions such as Plus/Pro as a dsh codex-oauth provider. Credentials are only written to the local credential store; it can view images but does not generate them. The author states that calling the undisclosed backend violates the terms and carries the risk of account ban. Installation: dsh plugin add github:Player-MINEPIG/dsh-llm-codex-oauth.
Read MoreConnect Codex CLI Subscription to DeepSeek Harness with dsh-codex-subscription
The community plugin dsh-codex-subscription (npm package name: dsh-llm-codex) is maintained by yequ172672. It reuses the ~/.codex/auth.json file from the local Codex CLI, and enables the use of ChatGPT subscription models in DeepSeek Harness without requiring a Platform API Key. This article covers the directory page, verification of installation commands via GitHub and npm, token refresh, proxy configuration, and the text-only limitation.
Read MoreConnect ChatGPT Subscription to DeepSeek Harness with dsh-codex-connect
DSH-Codex-Connect is a community-maintained plugin for DeepSeek Harness models and their providers. It uses ChatGPT OAuth to access the OpenAI Codex model catalog without turning subscriptions into OpenAI Platform API credentials. This article checks the installation commands against the catalog page and GitHub README, covers login on the settings page, optional search/image viewing features, diagnostic commands, conflict resolution with the legacy dsh-codex, as well as Alpha compatibility boundaries.
Read MoreIntegrate Official Documentation for AI Programming Assistants with openai-docs Skill: Say Goodbye to Outdated APIs and Fabricated Parameters
# Official curated Skill "openai-docs" from OpenAI: Retrieve and cite the latest documentation via Developer Docs MCP (search/fetch/OpenAPI) This skill covers API usage, Codex manual self-knowledge, model selection and prompt engineering. It explains the paired installation with Docs MCP across platforms including Codex, Cursor and Claude Code, typical prompt usage scenarios, and precautions such as read-only document access and narrow-scope migration, to alleviate the issues of outdated documentation and parameter hallucinations in AI programming assistants.
Read MoreGenerate bitmap assets in the coding workflow using Codex's imagegen Skill
# Introduction to OpenAI Codex System-level Skill `imagegen` This skill enables generation and editing of bitmap assets including photos, illustrations, mockups and sprites within coding conversations via either the built-in `image_gen` command or an explicit CLI. Details including default auto-installation location, two operating modes, prompt templates, save path conventions, applicable boundaries and official CLI examples are provided to facilitate directly integrating visual assets into project repositories.
Read More# skill-installer: The "Package Manager" for Installing Skills on Codex
Skill-installer is a system Skill pre-installed by OpenAI alongside Codex, used to install Skills to `$CODEX_HOME/skills` (default path: `~/.codex/skills`) from the official curated/experimental catalog or any GitHub repository path. Based on the official SKILL.md and Codex documentation, this article explains how to use `skill-installer` to list and install Skills, covers script parameters, private repository and download fallback strategies, as well as the boundaries of local testing and plugins distribution.
Read MoreBuild ChatGPT Apps with chatgpt-apps Skill: MCP Server + Widget UI
### 正式翻译结果： ### Introduction to OpenAI's official curated Skill chatgpt-apps: How to scaffold, refactor and troubleshoot ChatGPT Apps SDK applications (MCP server + Widget UI) following a docs-first workflow. The article verifies the capabilities of Skills, application prototype classification, upstream example priority, usage boundaries between MCP Apps bridge and window.openai, as well as the installation and activation methods in Codex and Cursor. It also provides prompt examples for paired use with openai-docs and local joint debugging steps for Developer Mode.
Read More`define-goal`: Clarify the Goal First, Then Let the Agent Take Action
This article introduces OpenAI's curated Skill `define-goal`: it is used to refine vague intentions into specific, measurable and verifiable goals before coding, and call `get_goal/create_goal` again in accordance with quality standards. Based on the official SKILL.md documentation, the article explains the workflow, comparisons between good and bad goals, Codex installation (via `$skill-installer`), and the method of enabling it in tools such as Cursor/Claude Code through the SKILL.md directory. It also reminds that this skill only performs goal definition and does not manage long-cycle execution deliverables.
Read MoreTurn Notion research into cited structured documents with notion-research-documentation
### Official English Translation: This article introduces the OpenAI curated skill `notion-research-documentation`: under the premise that Notion MCP has been connected, it enables cross-page retrieval and evidence synthesis within Notion, and generates cited documents in templates such as briefings, summaries, comparisons, and full reports. It follows the official SKILL.md instructions for installation and activation (including Codex's `$skill-installer` and Cursor's skills directory), covers the official five-step workflow, competitive product comparison examples, as well as precautions such as permissions, timeliness, and warehouse deprecation.
Read More`playwright-interactive: Using Persistent JS_REPL for UI Iteration and Debugging`
# Introduction to OpenAI's Featured Skill: playwright-interactive This skill enables persistent handling of Playwright/Electron via js_repl, allowing rapid iterative UI debugging on local web and Electron applications. It also supports completing QA checklists, functional validation, visual QA and viewport adaptation following official workflows. This article details the installation steps, pre-configuration requirements, typical code snippets, as well as notes such as the possible removal of js_repl in the current Codex, and makes a comparison with the CLI-oriented Playwright Skill.
Read MoreLinear Skill: Let AI Agents Directly Operate Linear Tickets, Not Just Write Code
### 译文： Officially selected by OpenAI: Skill Linear, which enables Agents to read, create and update Issues, projects and team workflows via Linear MCP. This article introduces its positioning, core capabilities, installation steps for Codex/Cursor, typical usage scenarios such as Bug triage and Standup synchronization, as well as precautions including OAuth and rate limits.
Read Moreyeet: Official OpenAI Skill, Run stage → commit → push → Create PR in one sentence
yeet is a curated Agent Skill maintained by OpenAI in the openai/skills repository. It only uses the GitHub CLI to complete git add, commit, push and create or update a Pull Request in one go when the user explicitly requests it. This article verifies its workflow based on the official SKILL.md: automatically creating a branch from the default branch, perceiving PR templates, avoiding duplicate PRs, and creating new PRs as Drafts. It also explains the installation methods and typical trigger phrases in Codex and Cursor. It is suitable for GitHub developers who want to hand over the final mile of Git release to AI Agents.
Read More# migrate-to-codex: Official Migration Skill to One-Click Move Claude Code Configuration to Codex
OpenAI's official Skill `migrate-to-codex` can convert Claude Code's instructions, Skills, Hooks, MCPs and sub-Agents into Codex's standard directory structure, supports scan, plan, dry-run and verification, and outputs a migration report. This article introduces installation and activation, typical commands, as well as the complementary relationship and limitations between it and Codex /import.
Read More### 版本1（面向技术用户，贴合原文语境）： `vercel-deploy`: Let AI Agents Deploy Projects to Vercel with One Click ### 版本2（更地道的技术文档译法）： `vercel-deploy`: Enable AI Agents to One-Click Deploy Projects to Vercel
Vercel-deploy is a Vercel deployment Skill in the OpenAI Skills curated directory, which guides AI Agents to one-click deploy applications to Vercel. It uses preview deployment by default; prioritizes Vercel CLI, and automatically downgrades to the deploy.sh script when not logged in, and can return previewUrl and claimUrl without prior account configuration. It supports automatic detection of frameworks such as Next.js, Nuxt, Astro, etc., and is applicable to tools such as Cursor, Codex CLI, and Claude Code.
Read MoreDrive Real Browsers via Terminal: Getting Started with OpenAI's Official Playwright Skill
OpenAI's featured Skill "playwright" wraps the Playwright Agent CLI into a terminal browser automation workflow: opening pages, taking snapshots to obtain element references, filling forms and clicking, taking screenshots, and debugging with Trace. Verified based on the official SKILL.md, this article introduces the installation methods (Codex skill-installer, Cursor .cursor/skills), the usage of the wrapper script, typical command examples, as well as precautions such as re-snapshotting when refs fail and not writing @playwright/test by default. It is suitable for E2E exploratory automation and UI process troubleshooting scenarios.
Read Moregh-address-comments: Structured Processing of GitHub PR Review Comments with Agent Skill
gh-address-comments is a curated Skill by OpenAI Codex. It pulls all review and inline comments of the current branch PR via gh CLI and GraphQL scripts, summarizes them with serial numbers for users to select the entries to handle, and then hands them over to the Agent for code modification. This article introduces its three-step workflow, the capabilities of fetch_comments.py, the installation methods of Codex and Cursor, as well as applicable scenarios and precautions under the human-in-the-loop design.
Read MoreJoint Report by OpenAI: Coding Agents Can Accelerate Scientific Software Maintenance but Cannot Verify Scientific Correctness
OpenAI released a field report in July 2026, summarizing 8 cases of life science software transformed by Codex, Claude Code, GPT-5.5 and other tools. Installation packaging, framework migration and performance optimization can significantly speed up projects, with some projects seeing their runtime shortened by more than 60 times, but Agents cannot guarantee scientific correctness. The report emphasizes independent testing harness, human acceptance and long-term maintenance responsibilities, noting that the bottleneck has shifted from code writing to verification and governance.
Read MoreOpenAI Integrates GPT-Live Full-Duplex Voice Access into Codex, Paving the Way for Hands-Free Operation of Coding Agents
On July 23, 2026, OpenAI integrated GPT-Live full-duplex voice access into Codex and ChatGPT Work in ChatGPT desktop build 26.715. Developers can use natural voice to initiate parallel coding tasks across threads between Chat, Work and Codex, review PRs, and remotely guide Agents. macOS also supports Appshots screen context. Based on OpenAI's official Changelog and Voice documentation, this article sorts out the GPT-Live architecture, typical scenarios, enabling steps, quota and permission boundaries, to help readers understand the interactive upgrade of Agentic Coding from typing commands to hands-free orchestration.
Read More