Plugins

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.

Session usage statistics panel: token and request stats at day/hour/minute granularity, an activity heatmap, bottom-bar session info takeover with per-turn cost chips, and cost estimation under multi-condition time-segmented pricing. Re-implemented from HaoyueQin/dsh-usage-statistics-panel with extensions.

Intent fitting for DSH: the agent predicts several directions first, asks a batch of clarifying questions each round, narrows the distribution until one converges, then proposes it for your confirmation. Bottom-right floating panel, local JSONL archive, a

Kaze Tachinu (The Wind Rises) skin for the DSH Web GUI: a full-screen film wallpaper behind glassmorphism surfaces, sky-blue interaction tokens, redrawn vector logos for the sidebar and home hero, a restyled composer card with themed placeholder text, and a bottom fade on the message list.

Skill usage scoreboard for DSH: counts both per-session deduplicated and per-load usage, scores `skill` tool calls and direct `read` of skill files, and shows the tally in a three-tab settings page (skill ranking, session board, management) with paging and JSON import/export.

DSH QQ bot bridge plugin, connect DeepSeek Harness with QQ bot.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

A lightweight plugin that adds model thinking token statistics to the bottom Dock.

Kimi Coding web search and web fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams (POST /v1/search and /v1/fetch), a settings card in the GUI stores it via the credentials service, and the fallback chain reads the Kimi CLI config for zero-setup installs.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Gemini-styled skin restyling the conversation ground, sidebar rows, hero greeting and composer through one stylesheet over the --dsw-* tokens, with light and dark both covered.

A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.

Connect Feishu chats to DeepSeek Harness projects, conversations, replies, and scoped tool approvals over WebSocket.

Provider-first three-level model selector for the DSH Web model seat: pick a provider, then a model from that provider, with inline search on both levels, failed-provider retry rows, and a Model · Provider trigger.

TickTick (滴答清单) daily task dispatcher: an interval timer pulls due tasks from a chosen list into a Markdown task file and notifies only when the task set changes (WeChat via ClawBot / flomo / macOS); it can also auto-execute each task in its own headless DSH session under a configurable timeout, optionally gated to DeepSeek's off-peak hours so peak-time work queues to the next off-peak window instead of starting, plus a settings panel for the deferred write-back queue and dispatcher_status / dispatcher_config / dispatcher_run / dispatcher_report tools.

Send QQ private-message notifications via a local NapCat bot: qq_send / qq_status / qq_napcat / qq_deploy native tools plus one-click deployment scripts.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Minecraft aus DeepSeek Harness heraus spielen: der Agent beobachtet, bewegt sich, baut ab und craftet über Tools, die von einem Live-Mineflayer-Bot gestützt werden

Reihenfolge der DSH-Seitenleisten-Fußzeile: zwingt den Slot sidebar.footer.action in einen vertikalen Stapel und erlaubt Nutzern, die Reihenfolge von oben nach unten der Einträge zu konfigurieren.

Wenn ein dsh-Turn unterbrochen wird — durch einen Web-Neustart oder ein Upstream-Problem (Rate-Limit, 5xx, Kontingentfehler) — injiziert dieses Plugin automatisch ein "continue", sodass deine Session dort weitermacht, wo sie aufgehört hat, mit einem Dead-Loop-Wächter, der die Kontrolle zurückgibt, wenn der Wiederholungsversuch nichts bewirkt.

GitHub-Picker im Composer: Klicken Sie auf das GitHub-Symbol unten rechts im Eingabefeld, um Issues und Pull Requests des Workspace-Repositories über die gh-CLI zu suchen und die Referenz als URL oder @owner/repo#number-Mention einzufügen.

WeChat iLink ClawBot-Brücke: offizielles Tencent iLink-Protokoll, Web-UI-Einstellungen (QR-Login, Modell, Preset, Berechtigungen, Sitzungsverwaltung mit Löschen), 24-Stunden-Auto-Erneuerung, die vor Ablauf einen neuen QR-Code sendet, ohne Ausfallzeit.

Ein kleines DeepSeek Harness-Web-Plugin: schwebende Nach-oben-Schaltfläche neben der offiziellen toBottom-Schaltfläche in der Chat-Ansicht.

dsh-Workspaces auf Discord abbilden — jede Session live beobachten, Agenten steuern und von überall auf die Kommandos des Harness zugreifen, ohne Inbound-Port.