Plugins

Compact top tools, untitled inbox and lower Working/Settled shelves; native menus, search highlighting, keyboard navigation, metadata backups and an original-layout switch. Chinese UI. On DSH 0.2.1-rc.5: macOS Desktop verified; Windows Desktop checked for cold starts, compact/original layouts at 1280x820 and 1471x1200, search, project filtering and native session menus. Linux and arbitrary third-party plugin combinations remain unverified.

DeepSeek Harness plugin adding an OKX perpetual-futures price dashboard: BTC/ETH candlesticks at 1m/3m/15m/1h/4h/1D, EMA overlays, line/Fibonacci/ruler drawing tools, close-line alerts through desktop notification, sound or email (email delivery additionally needs the dsh-qq-email plugin), and an in-panel backtester. Market data comes from OKX public endpoints and no API key is required.

Namecheap MCP connector for DeepSeek Harness: domains, DNS records, nameservers and contacts as native agent tools.

Control the user's own Chrome (or Edge/Brave/Vivaldi/Opera) from DeepSeek Harness by reusing the OpenAI Codex `chrome` plugin's browser runtime: tabs, logged-in sessions, accessibility trees, screenshots and input, exposed as native DSH MCP tools plus a b

DSH 插件：远程连接 + 逆向分析（REA / Ghidra）

Portable DSH plugin development assistant with native OpenSpec and baseline-bound delivery tools

DSH plugin: delete sessions from the sidebar (row menu + hover button) and via slash commands and agent tools. Trash-first, workspace-accounting aware.

WeChat DevTools (wechatide) MCP bridge for DeepSeek Harness: drives the IDE's own internal MCP server (wechatide mcp over stdio) — project open/import, compile, preview/upload, simulator screenshot, console/network logs, page automation and CloudBase — wi

链本体（三级模型：源 → key → 额度，按 key 记账/闸门/自动停用）：注册 web_search 的 provider 并供应配置卡片。由 dsh-websearch-tavily-keys-select 依赖，通常无需单独安装。

Skill Forge for DeepSeek Harness: distill a conversation or pasted context into a reusable SKILL.md, so a similar question later hits a skill instead of re-deriving the answer. Includes 4 model tools and a Web GUI panel.

DSH slash command /rea: hand a reverse-engineering request to the reverse-engineer-anything skill and the REA MCP tools, with a titled and glyphed / menu row

Tavily web search for DeepSeek Harness: a ctx.web search provider plus tavily_search/extract/crawl/map/research tools, with its configuration UI on the plugin's own detail page

Auto-continues turns stalled by DSML tool-call markup leaking into reasoning.

给大肥鱼会话用的 QQ 群/私聊工具：列群、看群记录、发群消息（可引用/@）、发表情、收藏表情（SnowLuma 收藏夹）、好友/私聊记录、发私聊消息、私聊唤醒、群成员、戳一戳感知/戳回去、更改头像、好友管理（资料/备注/分组/删好友/名片赞/好友申请）、QQ 空间说说（列表/详情/发表/评论/点赞/权限）、挂载会话选择。11 个工具组加 1 个设置组件，可在插件页逐个开关。

Spanish practice panel for DeepSeek Harness: six locally graded drill types (verb conjugation across 11 tenses, noun gender, plurals, vocabulary recognition, sentence cloze, ser/estar and subjunctive grammar points) plus a model-graded scenario-writing tab, 8-level spaced repetition, and four agent tools. Answers are computed and graded inside the plugin, so the model is only used for teaching and explanations.

Two halves with one account store: a left-panel GitHub repositories viewer that is read-only by construction (three GET endpoints, every non-GET refused with 405 before routing, request body never read, tokens never leave the host), and a github-manager skill exposing exactly two tools — github_accounts and github_api — so the agent does the writing. Sign-in is GitHub Device Flow, and the store self-invalidates on mtime so a token added later is picked up without a restart.

Two DSH delegation presets — a fixed 8-seat crew, or up to 3 day-rate temps by convention — with call-time guards that refuse the other shape's delegation tools. The 8-seat preset additionally needs @deepseek-ai/dsh-experimental-agent-team-profile in the profile's dsh.profile.bundles; without it that preset has no team tools and degrades to solo work.

Cursor-style mode switching for the dsh web UI: plan mode with a delegation gate, multitask mode with a tool-call quota, and the create_plan / request_more_edits / list_running_agent tools. Adds a plan card with Build buttons and compacts the subagent dropdown to running rows.

Event-driven trigger plugin (the doorbell beside dsh-proactive's alarm clock): recursive fs watchers with per-rule debounce windows and glob filters, plus a loopback-only local webhook endpoint with per-rule tokens, fire rules that wake a target session through the host agents service - live sessions get a direct follow-up, cold ones are resumed first - and inject a rendered prompt with template variables (paths, count, payload). Rules hot-reload from the event-gate rules file without restarting DSH, every trigger appends to an auditable JSONL history queryable via the trigger_list and trigger_history tools, and a loopback health route reports install and runtime status. Typical uses: auto-organizing a downloads folder, diagnosing CI or monitoring alarms posted from local scripts, and watching logs for errors. Pure JS, no build step, MIT.

Manage subagents and Agent Teams teammates in DeepSeek Harness: stop running instances, then really remove them by retiring their catalog and roster records with seq-preserving log tombstones and moving their session directories to a recoverable trash; model tools, a conversation-header panel and an offline CLI.

Grouped on/off switches for the skills a DSH profile exposes: the effective set is the union of the groups that are switched on, with a catalog-derived group for the skills shipped with the harness, a panel over the composer, and skill_toggles_* tools for agents.

Searches the installed skill catalog on a trigger word, requires a use-or-skip decision for every candidate, and blocks other tools until all selected skills are loaded.

Two PDF tools for the DSH sidebar in one install — jump to any page and browse the whole document with locally rendered pages and thumbnails, or open a PDF with DSH's native preview. Ships a /pdf command too.

Bundles a deep-read paper library and the paper-deepread-html skill: a sidebar panel to browse interactive reading reports, upload PDFs into a managed library, deep-read them with an agent (or through an optional site auto-read worker), and manage or rebuild the library; ships the paper_deepread, paper_deepread_uploads and paper_deepread_reports model tools. Deep-read/ingest and report builds require Python 3 (the bundled skill prepares a PyMuPDF venv on first use; index rebuild falls back to plain python3).