Plugins
Browse, filter, and install DeepSeek-Harness plugins.
521 plugins found
dsh-model-as-tool
try-works/dsh-model-as-tool
Install Desert Ant Labs on-device models as DSH tools and skills, with per-platform capability gating
dsh-capability-composer
xiamubumu/dsh-capability-composer
Composes tools, skills and MCP servers into switchable per-session sets, shrinking the resident tool surface and the system prompt on demand.
dsh-preset-categorizer
anonamerjaxon-dev/dsh-preset-categorizer
Reads the installed plugins, MCP servers and skills, groups them by capability, and reports which preset each belongs in; can register one preset per category on request.
dsh-context (agent-embodiment)
qiangweiliu/dsh-context
Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.
dsh-freemodels-opencode
xiean676/dsh-freemodels-opencode
Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list from upstream, tick which models the opencode provider exposes, test any of them with a real request that ends in one of seven verdicts, and order both the settings card and the model selector by a hand-written S/A/B/C capability rating.
dsh-plugin-usage-analytics
wjf1/dsh-plugin-usage-analytics
Local-first usage analytics for DSH: subscribes to session events and aggregates tool calls, turns, errors, latency and capability usage into daily tables, shown in a sidebar panel (6 KPIs, 14-day trend, top tools, capability breakdown) and served over a fenced local HTTP API with 18 JSON-RPC methods. Zero runtime dependencies, local mode makes no outbound requests, and no message bodies are collected.
dsh-model-picker
faxble/dsh-model-picker
Model quick picker for DeepSeek Harness: a button left of the model dropdown opens a full model-selection dialog with provider grouping, live search, provider filter, capability tags read from the user's own input config, reasoning badges, recent-model shortcuts and a reasoning-effort picker; the choice writes back to the native dropdown immediately.
dsh-output-loop-guard
adistancethereis/dsh-output-loop-guard
DSH guard against self-repetition in streamed model output: detects a degeneration loop in reasoning or visible text, aborts the runaway turn and wakes the agent with a corrective notice.
dsh-prompt-freeze
lemonel/dsh-prompt-freeze
A DeepSeek Harness plugin that freezes tool declarations to improve prompt cache stability.
dsh-plugin-selfcheck
xiaocxiaohai666/dsh-plugin-selfcheck
Prints every plugin in the DeepSeek Harness loader tree at boot, with the exception text for anything that failed, and checks dependency version drift, profile config validity, web port reachability and registered tools.
dsh-workbench-agent-studio
lucky01222/dsh-workbench-agent-studio
Agent Studio for DSH Web: configure models, prompts, per-plugin tool bindings and Skills; trial-run with editable tool results and run history; preserve session capability snapshots; export standalone presets; draft Agents with a guided creator preset.
dsh-vision-unlock
wmk66ds/dsh-vision-unlock
Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.
ccreach-dsh-web-search
tyjean428/ccreach-dsh-web-search
CCReach capability-search provider for DeepSeek Harness, letting agents discover data sources, tools, APIs, MCP servers, skills and workflows.
dsh-workspace-capabilities
fleey/dsh-workspace-capabilities
Chooses which skills and MCP servers each workspace may use, from a "Skills & MCP" item in the workspace row's "..." menu; unchecked skills leave the session catalog, the `skill` tool and `/name`, and unchecked servers have their `mcp__<server>__*` tools denied for that workspace's sessions, running ones included from the next turn.
dsh-files-to-chat
ruaibeite/dsh-files-to-chat
Right-click a file or folder in the right sidebar file tree to add it to the composer as an @ reference (⌘/Ctrl and Shift multi-select insert a whole batch), open it with the default application, or reveal it in the system file manager. Open and reveal go through the built-in open-in-app host capability, so those entries appear unless the host explicitly reports the capability as unsupported.
dsh-thinking-slider
lihihe/dsh-thinking-slider
Turns the composer's reasoning-effort menu into a draggable slider and takes over the stock model-and-reasoning-level chip. Dragging follows the pointer continuously; releasing snaps to the nearest level and submits one session update per drag. The track draws its own fill, tick marks and white knob, only the highest levels (xhigh, max, ultra) get a flowing brand-colour gradient, and both ends carry the lowest and highest level names. The same card expands into the official model list. Arrow keys step one level, PageUp and PageDown two, Home and End jump to the ends, and each move submits. A generation counter on the directory object discards late responses, and reduced-motion turns the animations off. All data comes from the stock modelDirectories directory; no new capabilities are added.
dsh-system1
exoticknight/dsh-system1
Connect multiple decision providers and models through one interface: Jev via TypeSafe, Clef via Cloudflare, Drex via Nace, Decider via meraGPT, self-hosted Laya, and compatible custom providers. Agents and plugins can classify content, filter candidates, score against criteria, or locate objects in images, then use structured results in their workflows.
dsh-model-control
uio-o/dsh-model-control
Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.
dsh-tool-browser
yuehancn/dsh-tool-browser
Open a page, wait for it the way it actually needs, extract the readable article, and take a screenshot. Playwright is optional: when it is absent the tools fall back to a static fetch and say so in the result, because a page whose JavaScript never ran means something different from one that rendered. Content is chosen by scoring candidate subtrees on prose density rather than on tag names, so a container loses to the article inside it instead of winning by containing more of the document.
DSH-Plugin_awl
awl-mc2/dsh-plugin_awl
Wallpaper-aware readability repair for the DSH Web GUI: it lifts the three low-contrast secondary text tokens with color-mix plus an adjustable text halo, adds content rules (bold, permanently underlined or recoloured links, tinted headings and body text) scoped to conversation Markdown only, offers adjustable rainbow-edge and gradient-fill heading effects, loads custom fonts from the plugin folder or the DSH home, and ships a draggable WYSIWYG preview with a WCAG contrast badge.
dsh-lorebooklike-prompt-tool
erlingmijiang/dsh-lorebooklike-prompt-tool
SillyTavern-style prompt rules for DSH: layered system-prompt anchors, constant/keyword entries, reproducible probability gates and regex rewriting.
dsh-openai-live
travizm/dsh-openai-live
Full-duplex voice for DeepSeek Harness: a realtime capability seam, a GPT-Live-1 adapter, and a keyless replay backend.
dsh-health
laa1991/dsh-health
Turns declared health readings — source, criterion, verdict — into one read-only verdict; an unreadable source is reported as `unknown`, never as healthy.
dsh-think-flow
yfwu2020/dsh-think-flow
Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.