Plugins

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Email notifications for DSH with an away-mode switch: mails you when a turn ends, a tool waits for approval, or the assistant asks a question. Title and body are editable templates.

TypeSafe Jev (modèle de décision System One) pour DeepSeek Harness, de bout en bout : jev_decision (choice/score/noul, parallèle, réponses typées + confiance), une carte Paramètres > Plugins pour la clé API et les bascules, des vues d'outils en ligne montrant chaque décision dans la conversation (réponse, confiance, latence, coût), un garde automatique (contrôles déterministes + risque/boucle Jev), un tableau de bord local /jev, et un benchmark de vérification en ligne (96,3 % sur 27 questions étiquetées, médiane ~283 ms sur jev-latest, 2026-09-21). Honnête par conception : API réelle uniquement, aucun repli simulé.

Local SQLite long-term memory with CJK-aware search, BM25 and character n-gram cosine reranking, deduplication, and lifecycle management.

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.

Lightweight zero-dependency memory plugin for DeepSeek Harness: Markdown-file memory store, L0 catalog injection, and 5 model-facing tools.

Multi-channel notification plugin for DeepSeek Harness: dispatches in-page toasts in the foreground and PWA system notifications (Service Worker) or browser notifications in the background, with per-event toggles for task complete, approval request, question, plan review and errors, persistent notifications, and Web Audio synthesized alert sounds without audio files.

In-page task notifications with collapsible status toasts, sound, and session navigation.

A DeepSeek Harness bundle of the 25 promoted mattpocock/skills with a native agent preset, an invocation-aware skill provider, and a light grilling-to-implement bootstrap.

Publishes a lesson into the DSH conversation: the dependency spine, the question and the vault's drawings, drawn in the vault's own palette.

Turn the tab icon into a green/amber status light and send browser notifications when a session finishes or awaits your input, with 47 selectable notification sounds.

Read-only DSH/Cordis composition doctor for plugin conflicts and upgrade rehearsal: scan profile manifests and patches, find duplicate rows, hook-order and UI ownership conflicts, compare redacted snapshots, diff plugin/row/hook changes, and preflight target DSH releases with explicit evidence boundaries — without mutating a real profile.

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.

Multi-agent orchestration agent preset for DeepSeek Harness: one chief orchestrator that never implements itself — it triages every request, has a PM expert plan the work, and delegates implementation to domain experts via a merged expert roster (list and summon tools), scheduling parallel work through a dependency-DAG taskboard and a file-based message bus, with delivery gated by an independent review. Ships 11 core experts; 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. Published on npm as dsh-expert-orchestrator (requires DSH >= 0.1.7-alpha.2).

Windows computer use for DeepSeek Harness agents screenshot, click, type, scroll, with an on-screen indicator the human can see

Feishu notifications (session end / input needed).

Global token totals across every local DSH conversation, de-duplicated by message id, with custom date ranges and per-provider monthly quota tracking.

DeepSeek Harness plugin: Windows desktop notifications + sound when an agent turn finishes or the harness is waiting for you.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

Web Push notifications for DeepSeek Harness

Patch-style file editing: one apply_patch tool accepting git/unified diff (default) and Codex apply_patch syntax (opt-in), applying every change all-or-nothing after a full read-only verification pass, with sandbox-aware delete and move and a dry-run mode.

Education mode for DeepSeek Harness: research a course, teach it, write the class notes, and quiz the learner.

输入卡底部工具行的计费时段徽标，附倒计时。高峰为北京时间周一至周五 09:00-12:00、14:00-18:00；周末全天算空闲，周五 18:00 后显示距下周一 09:00 还有 63 小时。

Sounds a chime and raises a desktop notification when the agent needs you — stage completion, approval requests, awaiting input, task completion, and errors, each with its own tone.