プラグイン

保険商品の比較および提案のエキスパート — 条項分析、費用対効果、カバレッジ計画、検証可能なクライアント向け PDF 提案を生成する。

保険会社業務アナリスト — 単なるテキスト説明ではなく、実際のソルベンシー、収益性、組み込み価値（EV）、投資リスク、規制遵守の計算を実行する。

保険会社の財務および業務アナリスト — ソルベンシー、財務、投資、流通チャネル、ピア比較を実際の計算で実施。

保険アクチュアリ — 単なる説明ではなく、実際の保険数理計算（C-ROSS II BEL+RM に基づく生命および P&C 準備金評価、NBV/VNB/IRR の利益テスト、組み込み価値 EV、価格設定およびロス三角形準備金）を実行する。

Windows 向けの Tauri 2 デスクトップアプリケーション。グローバルの @deepseek-ai/dsh パッケージを検出（またはインストール）し、DSH Web サーバーを起動して自身のウィンドウに埋め込みます。システムトレイ管理、ログイン時の自動起動、グローバルホットキー、デスクトップショートカットを備えます。

DeepSeek Harness のコンテキストマネージャー：毎ターンを自動で要約して優先度順のレコードにし、それらとピン留めしたクロスセッションノートおよびカスタムテキストを各モデルリクエストに注入し、任意サイズの実際の会話範囲を要約へ折りたたんでトークンを節約します。永続的で再起動にも安全です。注意：手動の多段階インストールが必要で、3 つのパッケージフォルダーを profiles/node_modules にコピーし、提供された cordis.patch.yml の行を追加して DSH を再起動します。標準のワンコマンドインストールではありません。

メイン会話の横にネイティブのサイドバイサイドチャット：完全なネイティブ UI を持つ独立したアーカイブ済み DSH セッションで、親コンテキストのオンデマンド取得、選択範囲の引用、保持または削除のライフサイクルを備えます。

DSH Web GUI 插件：给所有 Tool 调用加缩进，并在 设置→工具调用外观 里调 Tool/思考摘要的缩进、灰度与行间距 | Indent every tool call in DeepSeek Harness's web UI, with a settings panel for indent / dim / line spacing

Claude Code Desktop 风格的 DeepSeek Harness 桌面版界面插件

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

Conversation task-completion reminder for DeepSeek Harness (Web UI and DSH Desktop): a Windows system toast (Web Notification) on every stop — task complete, the agent waiting for your answer (ask_user_question pending), or an error stop (any failed turn

A port of the T3 Code model picker into the composer: a provider rail, search results grouped under provider headings, favorites kept in the browser, unavailable-provider badges, and Cmd/Ctrl+1..9 jump shortcuts for the first nine rows of the visible list.

Turn-rail settings for the DSH Web conversation locator: tick thickness, rail side, a curved length gradient anchored on the hovered tick, and a plain-text hover preview with adjustable line count, font size, and width.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.

Panel to edit dsh's native AGENTS.md from the web settings page: every layer in the instruction chain is clickable, three activation scopes, and a visual budget meter.

Long-term memory and self-evolving skills for the DeepSeek Harness · DeepSeek Harness 的长期记忆与自我演进能力 —— Plain Markdown on disk, no vector store

TIC-80 fantasy console for DeepSeek Harness: 3-column embedded web player, 14 agent tools, live hot reload, and native CLI export.

Windows system-drive (C:) cleanup for DSH: rule-based scan, five-tier safety grading, a staging area with a rollback ledger, UAC elevation, and migration to another drive — a model tool plus a Web GUI panel.

Git worktree-aware workspace browser for DeepSeek Harness: project sections, repository-grouped worktrees, and automatic workspace synchronization.

DSH markdown preview: clicking a markdown document in the conversation opens a rendered preview panel docked to the right of the chat.

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-down with context-growth curves and anomaly flags, global filters with shareable URLs, monthly budget progress with month-end projection, and day/month aggregate fast-path queries (O(days)) with incremental rescan.

Visual channel configuration UI for DeepSeek Harness (feishu / imessage / telegram / ...)