Plugins

Remote-SSH-ähnliche Arbeitsbereiche: Verwandeln Sie einen SSH-Host und ein Remote-Verzeichnis in einen nativen DSH-Arbeitsbereich; der Agent bedient das Remote-Dateisystem direkt über 12 rw_*-Tools (SFTP/exec), mit arbeitsbereichsbezogenen Pfaden und known_hosts-Verifizierung.

Verifikations-Gate für DSH-Agenten: Jedes Akzeptanzkriterium muss durch servergestempelte echte Tool-Evidenz belegt sein, bevor das Abschluss-Gate ein Ziel durchlässt (beratendes Audit, durchsetzendes Gate, dauerhafte Genehmigungen).

Bündel von Agentenfähigkeiten für virale Notizen auf Xiaohongshu/RED: Recherche zu Trend-Notizen, Erstellung/Umschreiben von Notizen, Verifizierung, Analyse autorisierter Konten, QR-Anmeldung und kontrolliertes Veröffentlichen.

Evidenzbasierte Unternehmens- und Job-Due-Diligence für DSH: protokolliert Quellen mit Evidenzstufen, ergänzt evidenzgebundene Aussagen, prüft die Rechtseinheit gegen offizielle Register und erstellt einen PROCEED/VERIFY/STOP-Bericht mit Prüfliste und Interviewfragen.

Rust-Entwicklungs-Domain-Plugin für DeepSeek Harness (dsh): Verifikationspyramide fmt→clippy→build+test→miri+audit(+semver) als modellseitige Tools + Graph-Layer-Governance (anti-Goodhart 8 Regeln inkl. #[allow]-Dichte / gelöschte Tests, blind-spot über Cargo.toml und pub

Linux-Kernel-Entwicklungs-Domain-Plugin für DeepSeek Harness (dsh): Verifikationspyramide L1-L4 als modellseitige Tools + Graph-Layer-Governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md-Vertrag als System-Prompt-Abschnitt. Reines JS, kein Build-Schritt.

Spec-driven-Entwicklungsdisziplin für dsh: fünf Keel-Skills (anchor/spec/probe/build/audit), drei Review-Tools und sechs Spec-Vorlagen erzwingen Spezifikationen vor Code, Annahmeprüfung und Scope-Kontrolle.

Anti-Bot-HTTP-Abrufwerkzeuge, gehärtet durch SXS' Produktions-Scraping-Stack (Millionen Anfragen pro Tag): UA-Pool-Rotation, Neuversuch mit exponentiellem Backoff, Anti-Bot-Wall-Erkennung (Captcha / Verifizierungs-Challenges) und adaptive Ratenbegrenzung – Tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Unabhängige Browser-Abnahmetests für Agenten-Deliverables: JSON-Spezifikation hinein, echtes Chromium-Verdikt heraus.

Verifikations-Gates mit echter Berechnung: mathematische Vereinfachung, Logikbeweise, Regex-Validierung, E-Prover-FOL, Zustandsmaschinen-Prüfungen und Code-Reparatur, gestützt auf in Go kompilierte Binärdateien mit vorgefertigten Windows-Executables.

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 (System-One-Entscheidungsmodell) für DeepSeek Harness, durchgängig: jev_decision (Choice/Score/Noul, parallel, typisierte Antworten + Konfidenz), eine Karte Einstellungen > Plugins für API-Key und Schalter, Inline-Tool-Ansichten, die jede Entscheidung in der Konversation zeigen (Antwort, Konfidenz, Latenz, Kosten), ein Auto-Guard (deterministische + Jev-Risiko-/Loop-Prüfungen), ein lokales /jev-Dashboard und ein Online-Verifikationsbenchmark (96,3 % bei 27 gelabelten Fragen, Median ~283 ms auf jev-latest, 2026-09-21). Ehrlich ausgelegt: nur echte API, kein Mock-Fallback.

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.