Плагины

Проверяйте файлы, которых касался агент, просматривайте артефакты сессии, предпросматривайте ограниченный контент и управляйте локальной памятью Workspace, не выходя из беседы.

Инфраструктура как код: план/применение с защитными ограничениями, просмотр state и output, а также валидация конфигурации через CLI terraform.

Блокирует чтение и запись агентами чувствительных файлов (.env, учётные данные, ключевой материал), маскирует утёкшие в результатах значения, похожие на секреты, ведёт журнал аудита и предоставляет безопасные инструменты проверки sg_*, которые никогда не печатают исходные значения.

Нативный для Cordis процесс полноценной инженерной разработки на основе доказательств: планирование со сначала инспекцией, явные доказательства проверки и шлюзы с учётом одобрений для чувствительных операций.

Безопасные возможности Kubernetes для DeepSeek Harness: инспекция рабочих нагрузок, ограниченные логи и события, диагностика сбоев и операции, требующие подтверждения.

Запускает биоинформатические анализы OmicVerse/OmicOS в постоянном ядре Python, с поиском по каталогу возможностей, инспекцией ядра и вкладкой аккаунта.

Инструменты DeepSeek Harness для поиска и просмотра плагинов в каталоге dshhub

Просмотр и управление актуальной цепочкой инструкций и навыками проекта текущей сессии dsh с созданием и редактированием на месте — что видите, то и получает модель

Типизированное защищённое управление контейнерами: ps/logs/inspect/exec/start/stop и compose up/down с JSON-выводом, таргетингом с учётом проекта и деструктивными операциями, требующими подтверждения.

Read, build and take apart EPUB 3 books with no external dependency — the ZIP reader/writer and the XML scanner are both built in. Inspect metadata, reading order and TOC for structural problems, assemble a book from chapters, or split one back into per-chapter HTML.

A read-only Cordis Inspect provider that lets an agent see the interface it is driving: outline() reports which UI regions the running shell actually rendered, with occupancy, geometry and current or past failure state; snapshot() returns one region's rendered node tree (tag, role, aria-label, own text, geometry, computed styles) addressed by slot key or CSS selector; failures() keeps a history of regions that failed to render and whether they recovered. Regions are addressed by the anchor the shell already writes for every slot, so it needs no region list and covers regions added later or contributed by other plugins. No UI, no tools, no dependencies, no network access.

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

Selection mode for HTML preview and browser tabs: click any element in a locally served demo page and its locator (selector, text, HTML snippet) is written into the chat input for precise AI editing.

Let a DSH model inspect and operate Windows applications through an installed Codex Computer Use runtime, with per-session app approval.

Read Plane: cross-agent session discovery, turn inspection, workspace aggregation and distillation from raw local session files.

Remote operations for the DSH Web app: manages SSH servers, collects hardware and process metrics, inspects logs with a read-only AI pass, and deploys a Git repo over SSH using git pull --ff-only plus a health check. Credentials are AES-256-GCM encrypted. Linux and macOS hosts; no Windows support.

Skills & MCP panel for the DeepSeek Harness Web GUI: list, search, inspect and hot-toggle skills and MCP servers from Settings.

Host-only command safety gate for DeepSeek Harness: blocks recognized dangerous operations and requests DSH approval when a command cannot be inspected.

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Discover and run project tasks through Harness Jobs, inspect run receipts, and check project configuration with an Agent tool.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Session health check for DSH, read-only: scans the whole session library (totals, largest sessions, warnings for oversized sessions and event-count blowups) and deep-inspects a single session log (tail-balance / crash-tail check, tool-call/result pairing, event-type distribution).

Hypatia knowledge console for the DSH Web GUI: a sidebar entry that opens shelf browsing, JSE search, record inspection, a local relationship graph, and guarded deletion in the main column.

Web management panel for Docker on DeepSeek Harness: manages Docker MCP servers (deploy/remove, official catalog search/pull, gateway start-stop-restart, custom deploy) and containers/images (list, start/stop/restart, remove, logs, inspect, interactive terminal, create, pull, build, load) across local CLI and SSH remote targets with one-click switching. Credentials are encrypted with Windows DPAPI, HTTP is loopback-only, and command parameters are whitelist-filtered. Build-free pure ESM; client is zero-dependency.