Plugins

Memoria entre sesiones para DeepSeek Harness mediante el dominio oficial de almacenamiento: las memorias persisten a través de ctx.storage (tabla storageDomain) y se inyectan en el prompt del sistema mediante una sección registrada (memory:recall), con herramientas memory_save / memory_forget para que el agente lea y escriba su propia memoria (maxMemories configurable).

Panel de gestión de atención de tokens para DeepSeek Harness: seguimiento de uso y coste de tokens por tarea/día/semana/mes (aciertos/fallos de entrada, salida, razonamiento), precios punta/valle de DeepSeek, reconocimiento del tipo de tarea y consejos sobre cuándo cambiar de sesión, escribir un traspaso o compactar el contexto.

Gestor de niveles de esfuerzo de razonamiento para modelos API personalizados, con memoria de preferencias entre sesiones: conmutadores en línea bajo/medio/alto/máx dentro de Ajustes → Modelos, con escritura atómica de la configuración.

Forma de paquete estático de la puerta de seguridad de instalación de plugins de DSH: revisa cordis_define/cordis_run con una política a prueba de fallos, además de herramientas de revisión/auditoría y un popup de aprobación en el navegador (agree / agree+whitelist / reject; agree+whitelist escribe la familia de plugins en tru).

Control deslizante de esfuerzo de razonamiento en arte de píxeles para DSH Web con arrastre continuo de 0 a 100, escrituras reguladas a 16 ms, confirmaciones con ajuste a nivel y un fuego de brasas WebGL que se enciende cuando se mueve el control.

Registra la skill remove-pdf-background-gray para DSH: blanquea los fondos de escaneo grises/blanco roto en PDF basados en imágenes preservando la resolución, la geometría de página y los bordes del texto con suavizado (escritura Flate sin pérdida), mediante un único script de Python (pypdf + Pillow + numpy).

Conjunto de habilidades del agente de notas virales de Xiaohongshu/RED: investigación de notas populares, generación/reescritura de notas, verificación, análisis de cuentas autorizadas, inicio de sesión por QR y publicación controlada.

Examina el código local y GitHub/npm antes del desarrollo para encontrar implementaciones reutilizables, evalúa reutilizar frente a reescribir y comprueba el acoplamiento de la arquitectura.

Memoria nativa por espacio de trabajo sobre las propias costuras del harness: hechos y un perfil siempre activo y acotado en la unidad JSON del dominio de almacenamiento, escrituras con aprobación y citas `(sessionId, seq)`, recuerdo determinista y FTS de session-query sobre sesiones pasadas; sin servidor externo ni SQLite personalizado.

Revisa todos los archivos que el agente escribió en una sesión desde la cabecera de la sesión, con hunks por archivo y las escrituras rechazadas contadas aparte de los cambios.

Bloc de escritura Markdown con alcance de sesión acoplado junto a la conversación, con modos de edición/vista previa, reescrituras de IA basadas en selección, revisión de diferencias, deshacer y recuperación de borradores.

Kit operativo basado en evidencias: seis herramientas de solo lectura (capacidades, planes por etapas, lector de skills, búsqueda en memoria local, auditoría de releases, checklist) y cinco skills empaquetadas; solo planifica y audita, nunca escribe en remoto.

Claude Code's auto memory in DeepSeek Harness: the index in every request, and tools to write and edit it

Second-model gate on the assistant turn, installed in two parts: copy engine/ into ~/.dsh/plugins/ and mount it by absolute path in the profile patch (the bundle itself only installs the settings panel), then switch off the default dry-run mode that only logs verdicts. Once active, a separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. The web panel edits criteria and thresholds, and every verdict is appended to an audit log.

The cyber-elixir of youth for the desktop client: fixes the `desktop welcome: Web authentication failed` (HTTP 431) launch failure — an Electron random-port launch lets `dsh-auth-*` login cookies pile up per port (70+ of them, ~229 B each), the startup request headers blow past Node's default 16 KB cap, and the client can no longer launch. Two fixes in one: a scriptable cleaner that removes leftover login cookies from the cookie database (Chromium SQLite) — explicit, offline, keeps a `.bak` copy, `--expired-only` narrows the scope — and a `patch` feature on the settings panel that fixes the launch port through the profile `cordis.patch.yml`, so the client always starts from a single port and cookies stop accumulating across different ones (rewrite `port` as a `!!js` expression to keep the `--port` flag in charge; a per-profile snapshot makes one click revert it). Read the README for usage. Interface, CLI output and market metadata in 9 languages. The purge runs from the bundled CLI (`dsh-cookie-cleaner --clean`) only while the client is fully closed; the in-app half is read-only. npm: `dsh-cookie-cleaner`.

A consent-gated personal profile store: people are indexed by name, entries by person and key, and no profile record is read before the current session is authorised. Sensitive entries come back masked unless the user authorises that tier separately; credential-like values are refused at write time. Ages and next birthdays are computed at read time, so asOf restores the answer for a past date, and facts that rot (height, weight, address) carry freshness warnings. Five profile_* tools plus a settings page to browse, edit, delete and revoke grants.

A memory plugin that forgets on purpose: short-term memories expire after 48h, long-term ones are rescheduled by Ebbinghaus/SM-2 curves and rarely-used ones fall asleep instead of bloating your context. Long-term writes stop in an approval center, so the agent cannot rewrite your persona on its own.

Prompt booster for the composer. Left-click the composer button and the draft is lightly polished and replaced in place (undoable, no popup). Right-click opens a menu with 8 built-in modes plus your own, where each mode's template can be edited or new modes added (saved on the host), and the model used for the rewrite is picked from the live dsh model list. Other modes show a before/after preview. Based on rongxingda/dsh-prompt-enhance (Apache-2.0); do not install both — both add a composer button and share Ctrl+Alt+E, so disable one of them if the upstream is present.

Adds two enhancements to DSH ask_user_question choice cards: right-clicking an option expands a per-option note that is merged into the submitted custom answer, and a footer field asks a side question answered by a fork subagent from the session context, read-only, with no write-back. Keeps left-click, skip, paging and the countdown working as before, and only claims generic choice cards, not plan review or approval cards. Supports DSH 0.2.x from 0.2.0-rc.1 (verified on 0.2.2-rc.1) and Node.js 20+. Derived from buaaflyaway/dsh-question-note (MIT) and inspired by MichengAI/dsh-btw (Apache-2.0); do not install it together with dsh-question-note — both take over the same ask_user_question card.

Optimize prompts in the DeepSeek Harness composer: identify missing requirements, insert a sentence from 90 method cards, or compare and edit a full rewrite before you send.

A sticky-note wall in the DSH sidebar: nine paper colors, categories, search, archive, to-do checklists with stable item ids, and agent read/write tools.

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.

Qoder-style workspace mode and branch chips on the session row; picking a branch arms it, and the first message creates a dedicated git worktree and moves the session into it. Windows only: the write grant runs PowerShell Set-Acl; elsewhere Worktree mode reports an error and stays in the main checkout.

Multi-round deep research in the DSH sidebar: each round fans sub-questions out to parallel sub-agents, then continues from where the last round stopped and writes a cited report.