Plugins

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Compares installed plugins against a downloaded DSH update and reports which interfaces they use that the update no longer exposes. Runs before you install, with a dry-run diagnose command for when it declines to act. Windows only, on the DSH desktop app, with Node.js 18+.

Multi-channel push notification plugin supporting Bark (iOS) and ntfy (Android/iOS/Web/Desktop) for turn completion, approvals, questions, and quota halts.

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

Config-driven lifecycle hooks for DSH: block or observe tool calls, and react to completed turns, messages, and title changes with shell commands.

Plot decision gate for novel writing: five beat_* tools register each node that changes the story into a decision point with 2-4 divergent options, beat_gate returns pass:false until the author picks, and beat_compile turns the picks into a chapter outline.

HarmonyOS delivery orchestration for DSH: freezes a four-dimension acceptance pack whose measurable criteria carry machine-checkable assertions, runs an adversarial pre-review before dispatch, hands the work to DevEco Code in Goal mode, then audits the delivery with independently gathered evidence (screenshots, UI tree, logs, hashed evidence bundle), recomputing assertion verdicts against measured values and filing rework orders; includes a cited rule catalog, a user-confirmation state and a gate calibration ledger.

Deck-generation skill for the National College Student Career Planning Competition. It takes a contestant's profile, materials and photographs, drafts a page-by-page outline for confirmation, then renders a 15-20 page reading-type PPTX (under 15 pages is flagged as a page-count error) using 17 page types, three built-in themes or a user-supplied template; the build audits the estimated layout (text overflow, per-page word count, missing evaluation dimensions, material gaps) and the rendered PDF is checked again for out-of-bounds and overlapping text. Requires Python 3.9+ with python-pptx, python-docx and Pillow; LibreOffice (soffice) and pdftotext are optional for the PDF layout re-check.

Group skills into named sets, toggle any combination, drag to reorder, and preview each group catalog token cost.

Whole-PDF paper translation for DSH on top of a BabelDOC installation you provide (Python CLI, with an OpenAI-compatible API key in its config.toml): bilingual dual-page output, a token cost estimate before running, a per-domain glossary reused across papers, and the server-side thinking overhead disabled for translation.

An AI reading buddy: it sits next to you while you read, and only knows the pages you have already reached — so it cannot spoil the rest, and it never summarizes the whole book for you. Highlight a sentence and ask about it, or just ask about what you finished; it usually restates what you seem to mean and asks one concrete question back. What you work out can be saved as a takeaway and later becomes a review card that jumps back to the sentence. EPUB, MOBI, FB2, TXT, Markdown, HTML, CBZ.

Compiles a repository into a source-grounded code map: structured pages where every claim carries a verifiable path:line citation, an interactive dependency graph, knowledge cards, four model tools and the /codemap command. Deterministic, no model calls, zero dependencies.

GitHub Trending radar inside the Harness Web UI: fetches the daily, weekly or monthly board (optionally filtered by a language), analyzes each repository into description, star gain, tech stack, highlights and risks, renders the result as a filterable card panel with paging, and registers the github_trending tool plus the /github-trending command.

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.

Crea vídeos explicativos narrados a partir de un guion. Usa por defecto diapositivas de tarjetas de texto (rápidas y precisas para tutoriales) o metraje generado por IA por segmento (requiere AGNES_API_KEY). Incluye 14 voces neuronales chinas en línea y 3 voces sin conexión para Windows, más un paquete de muestras de una orden para compararlas. Requiere ffmpeg. Para las voces en línea, copia el skill incluido video-remix a `<workspace>/.dsh/skills/video-remix` y ejecuta allí npm install.

Compila LaTeX con el TeX Live instalado en el equipo. La herramienta `latex` compone fórmulas en SVG, PNG o PDF y documentos completos en PDF (el texto chino cambia a xelatex con ctexart), guarda el archivo en el espacio de trabajo y devuelve una referencia Markdown. Una sección del prompt del sistema pide al modelo escribir `$...$` y `$$...$$` en vez de bloques de código. Si no encuentra TeX Live, aparece sobre el compositor un aviso para instalar BasicTeX o TinyTeX con un clic.

Memoria persistente compatible con Claude Code: el anfitrión inyecta el índice MEMORY.md al iniciar la sesión y el modelo mantiene los archivos con herramientas normales de lectura, escritura y edición. Una página de ajustes enumera los recuerdos guardados. Usa el mismo formato en disco que Claude Code; el modo claude comparte exactamente el mismo directorio de memoria.

Un intercom entre ventanas de DSH ya abiertas. Sin equipos ni sesiones nuevas: solo mensajes entre pares con límite de saltos.

Precalcula en segundo plano el resumen de compactación y confirma el resultado retenido cuando se activa la compactación por presión, eliminando una ida y vuelta del modelo en primer plano. Se registra como motor de compactación de sesión, fija el tramo resumido para que coincida la huella de la carga al confirmar, depura resultados de herramientas antes y vuelve al flujo estándar en primer plano si cambia la carga o se excede el contexto.

Exporta en modo de solo lectura una conversación de chat.deepseek.com a una nueva sesión DSH: crea un paquete de traspaso con los turnos seleccionados intactos y los anteriores reducidos a una línea cada uno, y rellena el compositor sin enviar. Según lo publicado, solo para Windows; requiere Edge o Chrome y un inicio de sesión previo en chat.deepseek.com.

Rebobina un turno terminado en la misma sesión: un botón junto a tu mensaje lo retira, junto con todo lo posterior, del contexto del modelo y devuelve su texto al compositor para editarlo. Opcionalmente restaura los archivos modificados por ese turno mediante DSH filesystem service.

Cambia el menú de modelos del compositor a una lista en dos niveles (proveedor y sus modelos), muestra juntos el modelo actual y su proveedor, pregunta el esfuerzo de razonamiento tras elegir un modelo y permite ocultar proveedores enteros o modelos concretos en los ajustes.