Plugins

Espacios de trabajo estilo Remote-SSH: convierta un host SSH y un directorio remoto en un espacio de trabajo DSH nativo; el agente opera el sistema de archivos remoto directamente mediante 12 herramientas rw_* (SFTP/exec), con rutas confinadas al espacio de trabajo y verificación de known_hosts.

Puerta de verificación para agentes de DSH: cada criterio de aceptación debe estar respaldado por evidencia real de herramientas con sello del servidor antes de que la puerta de finalización deje pasar un objetivo (auditoría consultiva, puerta de aplicación, permisos duraderos).

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.

Due diligence de empresas y empleos basada en evidencias para DSH: registra fuentes con niveles de evidencia, añade afirmaciones acotadas por la evidencia, verifica la entidad legal contra registros oficiales y genera un informe PROCEED/VERIFY/STOP con lista de verificación y preguntas de entrevista.

Plugin de dominio de desarrollo Rust para DeepSeek Harness (dsh): pirámide de verificación fmt→clippy→build+test→miri+audit(+semver) como herramientas orientadas al modelo + gobernanza a nivel de grafo (8 reglas anti-Goodhart, incl. densidad de #[allow] / pruebas eliminadas, blind-spot a través de Cargo.toml y pub

Plugin de dominio de desarrollo del kernel Linux para DeepSeek Harness (dsh): pirámide de verificación L1-L4 como herramientas orientadas al modelo + gobernanza a nivel de grafo (anti-Goodhart / blind-spot / patch-conflict) + contrato AGENTS.md como sección del prompt del sistema. JS puro, sin paso de compilación.

Disciplina de desarrollo guiada por especificaciones para dsh: cinco habilidades keel (anchor/spec/probe/build/audit), tres herramientas de revisión y seis plantillas de spec hacen cumplir specs antes que código, verificación de supuestos y control de alcance.

Herramientas HTTP de obtención antibot endurecidas con la pila de scraping de producción de SXS (millones de peticiones al día): rotación de grupo de UA, reintentos con retroceso exponencial, detección de muros antibot (captcha / desafíos de verificación) y limitación de tasa adaptativa — herramientas: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Pruebas de aceptación en navegador independientes para entregables de agentes: entra una especificación JSON y sale un veredicto en Chromium real.

Puertas de verificación con cómputo real: simplificación matemática, demostraciones lógicas, validación de regex, FOL con E-prover, comprobaciones de máquinas de estados y reparación de código, respaldadas por binarios compilados en Go con ejecutables de Windows precompilados.

DSH GUI Toolkit — Windows desktop control tools for DeepSeek Harness (DSH): screen layout, annotated screenshot, single-window capture, click / drag / type / key / scroll, semantic verification, window management, and UI Automation structured queries. Thi

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

TypeSafe Jev (modelo de decisión System One) para DeepSeek Harness, de principio a fin: jev_decision (choice/score/noul, en paralelo, respuestas tipadas + confianza), una tarjeta en Ajustes > Plugins para la API key y los conmutadores, vistas de herramientas en línea que muestran cada decisión en la conversación (respuesta, confianza, latencia, coste), un autoguard (comprobaciones deterministas + de riesgo/bucle con Jev), un panel local /jev y un benchmark de verificación en línea (96,3% en 27 preguntas etiquetadas, mediana ~283 ms en jev-latest, 2026-09-21). Honesto por diseño: solo API real, sin fallback simulado.

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.

Live Android device pane next to your DSH conversation: scrcpy-server H.264 streaming (WebCodecs, 30-60 fps), agent tap/swipe/text with auto-screenshot verification, uiautomator element tree with tap coordinates, host-managed recording + logcat debug sessions. FLAG_SECURE pages are detected automatically with a mitigation chain and a tappable text-view fallback. Emulators and USB real phones, human+agent co-operation, session-isolated, loopback-only.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Agent preset plugin for DeepSeek Harness that triages every request, delegates implementation to an expert, and schedules parallel work through a dependency-DAG taskboard and a file-based message bus before an independent review gate. Ships with only 11 core experts out of the box; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification.

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

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

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Reliable todo panel that survives restarts (official panel only re-renders on write — fixed via projection pre-warm) with three-state completion verification: evidence exists → verified, fake evidence → blocked, no evidence → unverified badge; settings toggle to fall back to official behavior.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.