DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-oh-my-claude

Oh My Claude

适用于 dsh (DeepSeek Harness) 的 Claude Code:将您已登录的 Claude Code CLI 作为模型提供商运行,支持实时模型、会话恢复、审批、回退、记忆和远程 SSH 工作区

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-oh-my-claude@1.5.12
README兼容性版本

兼容性与来源证明

Oh My Claude 以 dsh-oh-my-claude 发布,当前版本为 1.5.12。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
npm
Registry 更新时间
2026/11/4

版本

1.5.12stable
2026/11/2
1.5.11stable
2026/10/29
1.5.10stable
2026/10/28
查看其余 21 个版本收起版本
1.5.9stable
2026/10/27
1.5.8stable
2026/10/26
1.5.7stable
2026/10/25
1.5.6stable
2026/10/23
1.5.5stable
2026/10/22
1.5.4stable
2026/10/19
1.4.2stable
2026/10/19
1.5.3stable
2026/10/8
1.5.2stable
2026/10/1
1.5.1stable
2026/9/29
1.5.0stable
2026/9/28
1.4.1stable
2026/9/28
1.4.0stable
2026/9/24
1.3.1stable
2026/9/21
1.3.0stable
2026/9/21
1.2.1stable
2026/9/18
1.2.0stable
2026/9/18
1.1.2stable
2026/9/15

相关插件

正在加载相关插件…

最新版
1.5.12
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
5.5 MB
文件数
343
Surface
web
许可证
MIT
发布源
npm
GitHub
★ 27
周下载
1,603
安全扫描
✓ v1.5.12 扫描通过
最近提交
2026/11/4
查看源码 ↗项目主页 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题
1.1.1
stable
2026/9/14
1.1.0stable
2026/9/13
1.0.0stable
2026/9/11

相关插件

继续浏览 models-usage 分类下经过校验的插件。

Our Free Model@ebony-vinyl/dsh-our-free-modelOur Free Model — 在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型,桌面端另有 EAC 协付渠道;2.0 起接入 LobsterAI、Qoder、TRAE、Cline、Loomy、Raccoon、MiniMax、ZCode、Gemini 十个账号渠道(原有匿名免费通道保留)(登录、账号池、积分领取、本地 OpenAI 网关与局域网转发、数据看板与运行日志),六页毛玻璃界面统一呈现。Usage@linxin666/dsh-usage用于 dsh Web GUI 的使用统计插件:检测各提供商的余额和编程套餐配额,并实时记录令牌使用情况;侧边栏 Settings 行上方显示紧凑的价格概览卡片Client Ui Model Capabilities@linxin666/dsh-client-ui-model-capabilities为自定义 pi-ai 提供商声明每个模型的能力(图像输入和推理力度),可直接在 Models 设置卡片中编辑;写入官方 llm-pi-ai 设置命名空间,不更改 DSH 源代码。Codex Subscriptiondsh-codex-subscription在 DeepSeek Harness 中通过 OAuth 使用 ChatGPT 和 Codex 订阅,支持配额、安全重置、网络搜索、图像和快速模式,并可通过 ChatGPT 移动应用(Beta)控制 DSH

README

查看图片 Oh My Claude

English | 中文

Claude Code, native inside dsh

Drive your logged-in Claude Code CLI as a first-class dsh provider: no API key, no extra services, no runtime dependencies.

Built with AI assistance, and open to more. Contributions from AI coding agents are welcome; start with CONTRIBUTING.md.


Claude Code CLI as an LLM provider for dsh. Every request drives claude -p with stream-json in and out, so it uses whatever login, hooks, CLAUDE.md files, MCP servers and rate limits Claude Code already has. No API key needed. The plugin speaks the CLI's own protocol (the one the Agent SDK wraps) directly, so it has no runtime dependencies.

Tour

dsh's access shield in a Claude session: Plan, Ask, Accept edits, Auto, Don't ask and Bypass rows with dsh's own icons

The shield is dsh's own control. In a Claude session its rows become Claude's six permission modes, each labelled with the dsh access level it sets underneath.

the Oh My Claude panel switching between its Memory, Rewind, Changes and Asides tabs

One ✻ button beside the composer opens the whole plugin: Memory, Instructions, Skills, Rewind, Changes, MCP, Asides, Diagnostics, Tasks and Tune, plus a Restore tab while the session is still blank.

the Changes tab listing the working tree diff with per-file line counts the Asides tab with a side question expanded above the tab strip the MCP tab's add-server form, filled with a server name, command and argument list

dsh's footer stats row ending with the Claude session cost and cached token count

Cost and cached token count, two figures dsh cannot compute, join dsh's footer stats row. The pill turns orange once a session passes the spend line you set. The dollar figures are what the turns would cost at API rates; on a Claude subscription you are not billed them.

dsh's context ring popover with Claude plan windows and the CLI's own context breakdown the panel as a phone sheet above the composer

Plan usage and the CLI's own context breakdown live in dsh's context ring popover. On a phone the panel becomes a sheet.

dsh's Select Workspace Directory dialog with a box dropdown in its footer listing This box and an ssh box

Once an SSH box is saved, dsh's own Add workspace dialog gains a box dropdown: a folder on that box becomes a workspace here, and the session in it runs Claude Code there.

Shots by tools/playwright/tour.ts.

Install

You need the Claude Code CLI on PATH and logged in (claude --version works, claude opens without asking you to sign in), and dsh 0.2 (0.2.0-rc.1 or newer). On dsh 0.1.x, install the npm tag for your line from the Compatibility table below. Nothing else: no API key, no Node build step.

From dsh's Plugins page, in the web app or DSH Desktop:

  1. Open Plugins in the sidebar and press Add plugin.
  2. Enter dsh-oh-my-claude and press Install.
  3. Press Enable now, or turn on its switch later under Installed plugins.

It loads without a restart. Reload the page and "Oh My Claude" appears in the model picker with the models your login can use. Pick one and chat.

From a terminal, then restart dsh however you run it:

dsh plugin --profile web add dsh-oh-my-claude
systemctl --user restart dsh-web.service

To install straight from the repository instead of npm, use github:lcestou/dsh-oh-my-claude as the package name in either route.

The plugin speaks English and Chinese and follows dsh's own language setting (Settings → General → Language), switching as soon as you change it.

If the picker lists it as Oh My Claude (not logged in), run claude auth login in a terminal on the box that runs dsh, or press Log in under Settings → Oh My Claude → Boxes.

DSH Desktop (macOS and Windows) uses the Plugins page steps above. The plugin looks for claude in the usual install folders, since an app started from the Dock does not see your shell's PATH. On Windows it runs Claude as a plain child of dsh, so restarting the app ends a running turn, and the parts that need a Unix shell (Log in from Settings, SSH boxes) are not available. The server half has run under Electron on Linux the way Desktop runs it, and on Windows 11 with Claude Code installed from npm.

When a newer version is on npm, an orange pill with the version number appears in Settings and on the panel's Runtime line; a click copies the update command for a terminal. On the Plugins page, dsh updates a third-party plugin by removing it and adding it again. Details, and the repairs the plugin makes on its own after a dsh upgrade, are under Plugin updates.

Optional, in ~/.dsh/settings.yaml:

agent-default-model:            # make Claude Code the default for new sessions
  provider: claude-code
  model: claude-fable-5-1       # any model id the picker lists
subagent-model-selection:       # let dsh subagents run on Claude Code too
  enabled: true
  allowedModels:
    - provider: claude-code
      model: claude-haiku-5-5   # any model id the picker lists

Working on the plugin itself? Start at docs/developing.md.

Compatibility

dsh ships prereleases only and moves client APIs between them, so every release of the plugin records the dsh line it was written for and the dsh it was driven on. "Runs on" is the range the code carries branches for; "tested on" is the dsh installed on the box when the release was cut. The update pill reads the floor off the registry and never offers a release to a box whose dsh is below it.

PluginRuns on dshTested on dshnpm tag
1.5.120.2.0-rc.1 through 0.2.2-alpha.20.2.2-alpha.2latest, dsh-0.2
1.5.110.2.0-rc.1 through 0.2.2-alpha.20.2.2-alpha.2none, superseded by 1.5.12
1.5.100.2.0-rc.1 through 0.2.2-alpha.20.2.2-alpha.2none, superseded by 1.5.11
1.5.90.2.0-rc.1 through 0.2.1-rc.40.2.1-rc.4none, superseded by 1.5.10
1.5.80.2.0-rc.1 through 0.2.1-rc.40.2.1-rc.4none, superseded by 1.5.9
1.5.70.2.0-rc.1 through 0.2.1-rc.30.2.1-rc.3none, superseded by 1.5.8
1.5.60.2.0-rc.1 through 0.2.1-rc.30.2.1-rc.3none, superseded by 1.5.7
1.5.50.2.0-rc.1 through 0.2.1-rc.20.2.1-rc.2none, superseded by 1.5.6
1.5.40.2.0-rc.1 through 0.2.1-rc.20.2.1-rc.2none, superseded by 1.5.5
1.5.30.2.0-rc.1 through 0.2.1-alpha.10.2.1-alpha.1none, superseded by 1.5.4
1.5.20.2.0-rc.1 through 0.2.0-rc.20.2.0-rc.2none, superseded by 1.5.3
1.4.20.1.5-rc.1 through 0.1.7-rc.20.1.7-rc.2dsh-0.1.7
1.4.10.1.5-rc.1 through 0.1.7-rc.20.1.7-rc.2none, superseded by 1.4.2
1.4.00.1.5-rc.1 through 0.1.7-rc.20.1.7-rc.2none, superseded by 1.4.1
1.3.10.1.5-rc.1 through 0.1.6-alpha.20.1.6-alpha.2dsh-0.1.6
1.2.10.1.5-rc.1 through 0.1.6-alpha.20.1.6-alpha.2dsh-0.1.5

What you get

  1. Any Claude model your login can use, in dsh's own picker. Hide the ones you don't use with a switch in Settings, or with hiddenModels in the plugin config. Models
  2. Every dsh session resumes its Claude Code session, tool history included, and a terminal claude /resume sees the same one. Sessions
  3. Restart dsh without killing a running Claude turn. Restarts
  4. dsh's access shield sets Claude's six permission modes per session. Permission mode
  5. Claude's permission prompts, questions and plan reviews become dsh dialogs, each option's preview under the question. Approvals
  6. One spark button opens Memory, Rewind, Changes, MCP and seven more tabs, all reachable from the keyboard. The panel
  7. Cost and cached tokens in dsh's footer, with a spend line that turns the pill orange. Cost pill
  8. Plan usage (5-hour, weekly, extra usage) in dsh's context ring, which turns amber near a limit and red at one, with a notice above the composer. Only limits the session's model counts against, graded by Anthropic, so a new model needs no update. Plan usage
  9. Restore or import any past Claude transcript, from dsh or from a terminal, and search inside them for what was said. Session browser
  10. Claude's slash commands and skills show up in dsh's slash menu under their own names, as /claude-<name> where dsh already uses the name. A skill dsh also serves runs on any model, and so does one only Claude Code has: typed in a session on another model, it goes to that model with its instructions (switch it off in Settings). Command bridge

Defaults you never have to touch, such as secret redaction in tool results and surviving the CLI's own updates, are on How it works.

Configure

Settings come in two kinds. The switches under Settings → Oh My Claude and in the panel's Tune tab apply at once and are kept on the box, so every browser sees the same ones. The keys below are install-time: they go as config: on the bundle row in the profile's cordis.patch.yml and take effect when dsh next loads the plugin, which a dsh restart does. dsh's own Plugins page lists the plugin with an on/off switch but has no form for these keys. Three keys people change first:

permissionMode: dsh      # follow the session's shield (default), or pin one of the CLI's six modes
spawn: keeper            # Claude outlives a dsh restart (default); node or dsh for a plain child
sshHost: ""              # "[user@]host" drives a claude on another machine over ssh

Every key, with its default, is in docs/configuration.md.

Remote boxes and accounts

Mount the plugin twice with different configDir values for two logins. List other boxes running dsh and this plugin under Settings → Oh My Claude → Boxes and jump between them. Or give a box a name and user@host and drive the claude there over SSH, with nothing on the far side but the CLI; Tailscale and WireGuard peers appear as hosts to pick from. All of it is on docs/remote.md.

What it touches

  • Runs the claude binary you already have, on this box or on one you add over SSH.
  • Reads Claude Code's login (~/.claude/.credentials.json, on macOS the Claude Code-credentials Keychain entry when that file has no live token, or ANTHROPIC_API_KEY when set) to fetch the model list and your plan usage. That token goes only to api.anthropic.com.
  • Writes its own state under ~/.local/state/dsh-oh-my-claude/; login tokens for SSH boxes are files only you can read. CLAUDE.md, settings.json and MCP servers change only when you edit them from the panel.
  • Listens on a Unix socket for the keeper that holds Claude across a dsh restart. Its HTTP routes live inside dsh's own server, so on DSH Web it opens no TCP port. Under DSH Desktop, whose web server answers 403 to anything but its own window, the bridge that hands dsh's tools to Claude also listens on 127.0.0.1, behind the same key.
  • Calls out to api.anthropic.com (models, plan usage), status.anthropic.com, downloads.claude.ai (the CLI's release pointer), registry.npmjs.org (plugin update check) and api.github.com (the repo's star count). SSH goes only to boxes you add.

Not covered

  • dsh's shell and file tools are not proxied (except bash for background jobs); Claude Code uses its own, under its own permission mode.
  • Claude Code sessions are not deleted when dsh sessions are.

Bugs and feedback

Found a bug, or something that reads wrong? Open an issue at github.com/lcestou/dsh-oh-my-claude/issues with the dsh and Claude Code versions (dsh --version, claude --version) and what you expected to see. Settings → Oh My Claude → Report a problem writes that report for you.

License

MIT.

Claude, Claude Code and the Claude spark mark are trademarks of Anthropic, PBC. This project is an independent dsh plugin that drives the Claude Code CLI you already have; it is not made, endorsed or supported by Anthropic. The spark is drawn here only to say which sessions and controls belong to Claude Code, in the way the CLI itself draws it.

  • Claude gets dsh's subagents, jobs, goals and web search over MCP. dsh tools over MCP
  • Edit CLAUDE.md, settings.json and MCP servers from the panel, on this box or a remote one, and sign in to an MCP server that needs it. Instructions, settings.json editor, MCP
  • Run Claude on another box over SSH, or mount several accounts. Remote boxes and accounts
  • Report a problem with a redacted box report, copied or filed as an issue. Report a problem
  • All the orange is a switch, per group, any colour. Claude look
  • Pick what dsh adds to your prompts, with the size of each block on the label. dsh context
  • A card offers each new Claude Code release for the box a session runs on, and installs it from dsh; a headless claude -p never updates itself. Channel, auto-install and history per box sit under the switch in Settings. Claude Code updates
  • What the last five versions changed, read from the plugin's own changelog, in Settings. Changelog
  • Every skill the CLI can reach, grouped by scope, with add, edit and remove for your own and the project's. What each costs, from the CLI's own /skill-doctor, is a table you can sort, beside what else drives your usage: the MCP servers behind the most requests, and how the work was shaped. Skills
  • A mark on the browser tab and an optional desktop notice when a session you are not looking at finishes, or stops to ask you something. Session notices
  • dsh's own goal and every earlier goal of the session, beside Claude Code's goal and its scheduled tasks. Tasks
  • Edit or remove a message you steered in while Claude works, or all of them as one, until Claude reads it. A file or image on the message stays on it; only the text changes. Nothing goes out while you edit. Send now stops Claude and sends one as the next turn. Steering
  • Claude's working line (spinner, verb, figures) repeats above the composer once you scroll up past it, so reading back through a long turn never hides what Claude is doing. A switch in Settings turns it off. Turn status
  • Select text in a reply to quote it into your message, or to ask Claude about it as a side question that leaves the conversation alone; leave the question blank and Claude explains the passage. A quote in your own message reads like one in Claude's replies, indented with the accent bar. Asides
  • A finished turn keeps a closing line where the working verb was, the way the terminal ends one: ✻ Crunched for 27s · done 3:21 AM. A turn you stopped reads Interrupted · What should Claude do instead?. Turn status
  • On dsh 0.1.7, Claude's tool calls show as dsh's own tool cards, the way every other provider's do, with the text streaming between them. Inline text is a switch away in Settings. Tool rows
  • A new session in a workspace opens on the Claude box and model that workspace last ran. Remember model per workspace
  • After each reply, Claude's guess at your next prompt shows above the composer: Use writes it into the box, Send sends it as it is, and it folds away while you type something else. On by default, as in the terminal; a switch in Settings turns it off. Suggested next prompt
  • Claude's background shell tasks and subagents are listed on the Tasks tab while they run, each with Stop and, for a shell task, Output, plus Stop all once two or more run. A shell task that ended keeps its row and its Output for the last ten; the subagents a session already ran sit under Earlier subagents, each openable as Markdown. A subagent's row in the chat names each step as the CLI reports it. Tasks
  • If an ANTHROPIC_API_KEY in dsh's environment is what Claude Code bills instead of your login, the session says so in one line at its start. Where things live
  • Each plan window says where it is heading at the current rate: the percent it ends at, or when the cap lands. Plan usage
  • Once the context window is 75% full (adjustable in Settings), a card above the composer says so and offers Compact, which sends Claude's own /compact. Context nudge
  • A Run button on every shell snippet Claude writes puts it in the composer as a prompt; Enter sends it, and it runs through Claude's Bash tool and dsh's approval. Run a snippet
  • A session renamed in dsh keeps that name in claude --resume, and a name set on the Claude side renames the dsh session. How it works
  • Switch a session between Claude and another model, such as DeepSeek or a local one, and back: Claude sees the prompts, replies and tool use the other model had in between. Sessions
  • Up in an empty composer brings back your last prompt, Up again older ones, Down newer ones and back to empty, as in the Claude Code terminal; typing a character ends the walk. A new session recalls from the workspace's latest transcript. Switch it off under Settings ("Prompt recall").
  • Ctrl+R in the composer searches the prompts typed before: this session, the workspace or everywhere on the box (Ctrl+S cycles). Enter sends the row, Tab writes it into the composer, Esc closes. Switch it off under Settings ("History search").
  • Esc Esc in an empty composer while nothing runs opens the Rewind tab on the latest prompt, as the terminal's double Escape opens /rewind; after the rewind that prompt is back in the composer to edit and resend. Switch it off under Settings ("Edit last prompt"). The three composer gestures are listed in dsh's Keyboard shortcuts dialog too.