プラグイン

Registers a janitor_scan tool that returns a deterministic, reviewable cleanup plan for session debris (plan docs, scratch scripts) with per-file verdicts and evidence; scan-only, never deletes.

Gitee Enterprise project management inside the conversation: issues, pull requests, kanban and the Gitee MCP toolchain.

Read-only clinic for DSH session logs: 22 named diagnostics (token waste, retry and failure loops, context bloat, cross-session amnesia, idle MCP servers and skills), each reported with a replayable evidence locator such as session.v4.jsonl.zstd#L101-L110, and each finding turned into an executable prescription — a profile-patch YAML snippet or a command with current to suggested values, risk, verification and source — plus a feedback command that retires a prescription you reject, after which the report states it was removed by your feedback. Zero dependencies, default zero egress, session files are never written.

Diving-Fish score lookup for MaimaiDX inside QQ, plus qq-bridge chat extensions. #查分 renders a B50 with song artwork from an OAuth authorisation that any member can use, and works without the bridge running; the extensions cover balance and auto-shutdown, reasoning tier switching by billing peak hours, holiday-table coverage, start/shutdown greetings, and an in-QQ feature toggle.

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

Texas Hold'em table for DeepSeek Harness: model-callable poker tools, six heuristic opponents, an optional coach, and a browser table whose buttons never post a chat message.

DeepSeek Harness 向けのエンドツーエンドな TypeSafe Jev（System One 意思決定モデル）：jev_decision（choice/score/noul、並列、型付き回答＋確信度）、API キーとスイッチ用の「設定 > プラグイン」カード、会話中のすべての意思決定（回答、確信度、レイテンシ、コスト）を表示するインラインツールビュー、自動ガード（決定論的検査＋Jev のリスク／ループ検査）、ローカルの /jev ダッシュボード、オンライン検証ベンチマーク（27 のラベル付き質問で 96.3%、jev-latest で中央値約 283 ms、2026-09-21）。設計上正直であり、実際の API のみを使用してモックへのフォールバックは行いません。

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Delete sessions from the DSH Web sidebar: adds a Delete action to the session row menu with a risk-consent dialog, then removes the session log, workspace accounting and live session state.

Kaze Tachinu (The Wind Rises) skin for the DSH Web GUI: a full-screen film wallpaper behind glassmorphism surfaces, sky-blue interaction tokens, redrawn vector logos for the sidebar and home hero, a restyled composer card with themed placeholder text, and a bottom fade on the message list.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Summarises the case evidence, diagnosis, repair procedure, parts list and cost-option comparison for a motor into a Markdown repair recommendation report with data provenance.

Fullscreen business-app framework for DeepSeek Harness Web with a dark-sidebar workbench bundling a database connectivity tester and SQL query panel, a two-level knowledge base (bill and accounting) with local search and Word document ingestion, metadata environment comparison with alter-SQL generation, a data dictionary, agent log-search report demos, a system test-case runner, Evernote-style notes, developer utilities, and mini-games.

Local and remote SSH terminals for DeepSeek Harness Web with three permission levels, human approval for risky AI commands, and encrypted credential storage.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Improve the current chat draft before sending with a confirm-before-apply comparison.

DeepSeek Harness 向けのセキュリティ重視 Feishu (Lark) チャネル。許可リスト方式のリモート Agent アクセス、ワークスペース内に限定したパス、シンボリックリンク検査、リスクに応じた承認、セッション分離、機密情報を伏せたログ、上限付きメッセージキューを備えます。

読み取り専用の DSH 環境ヘルスチェック：ディスク、メモリ、レイテンシ、~/.dsh の肥大化、古いプラグインの検出を、段階的なレポートとベースラインのトレンド比較付きで実行。何も削除しません。

DSH 用のエンタープライズワークベンチ：稼働中のセッションから AI 従業員、ナレッジベース、スキル、MCP サーバー、DSH プラグインを管理します。

タスク認識型の DSH プラグインナビゲーター：GitHub トピックとコミュニティリストからローカルインデックスを構築し、28 のバイリンガル能力クラスを横断して検索し、コミット単位の静的リスク監査、同意を条件とするピン留めインストール、構成チェック、復旧を提供します。