Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
111 plugins encontrados
dsh-model-radar
chip-g0202/dsh-model-radar
Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.
dsh-artifacts
modusensus/dsh-artifacts
Sidebar artifact shelf that collects the images, videos, files and links sessions deliver, deduplicated by SHA-256 content hash, with five filter tabs and counts, keyword search, video thumbnails, a lightbox, manual link saving, image paste, upload up to 25 MB, one-time backfill of past session logs, and a save_artifact tool the model can call. Copies each collected file into ~/.dsh/artifacts (up to 50 MB per file, 200 MB per video).
dsh-kit (dsh-build-ship)
474885697-alt/dsh-kit
Windows only: runs a build command through cmd.exe, collects the artifacts with sizes and SHA-256 prefixes, verifies expected outputs, and writes a report for each run.
dsh-impeccable-skill
kechao-sgp/dsh-impeccable-skill
DeepSeek Harness port of the Impeccable frontend-design skill: 24 design playbooks covering shaping, critique, audit, polish, layout, typography, motion, accessibility and design-system documentation, driven by the reference files shipped in the skill plus PRODUCT.md / DESIGN.md in the project instead of a downloaded engine binary. Registers the impeccable skill; reads project files and writes design artifacts under .impeccable/. The binary-only features (live browser bridge, pixel measurement, font matching) fall back to static variants, screenshots and explicitly declared manual estimates. Ported from pbakaus/impeccable (Apache-2.0).
dsh-focus-board
yyj-python/dsh-focus-board
Cross-session task ledger for DeepSeek Harness: one item per request with a step chain, an accordion strip above the composer, unfinished items injected into every step, staleness review with artifact fingerprints, clickable choices that learn repeated decisions, a grant ledger whose four-mode control sits inside every authorization-blocked card, blind-work backfill checklists, and a scheduler that re-judges an item only when a new assistant answer mentions it.
dsh-review-outbox
zjukop3/dsh-review-outbox
Evidence-gated acceptance for research reports: claims, citations, data scope and method limits each need a tick plus written evidence before a deliverable can pass, with same-artifact revision history and a standalone SHA-256 receipt that says when the bytes moved.
dsh-artifact-toolkit
windpixy/dsh-artifact-toolkit
Right-click menus on artifact cards and file links: copy the full or short path, show the file in its folder, or open it in its default app.
galadon
lumos-789/galadon
A five-stage engineering loop for agent-built projects — spec, build, verify, ship, learn — with one artifact and one gate per phase, so an agent always knows the single next action. Role policy, project templates and deployment sit behind explicit ports: swap the implementation without rewriting the loop. Its scaffold generator lays out the internal layers of a project — `init --layout {none,webapp,service,plugin} --stack {python,node,none}` — from nine layers sampled out of three unrelated production projects: entry docs, an OpenSpec plan face, a spec truth layer (INDEX, one file per domain, TESTING, CONSTITUTION), a wiki split into knowledge / progress / runbook, the six `.agents/` slots, server+web, scripts/deploy/config, tests+e2e and a gitignored out/. Non-none layouts also gate the directory contract and compile every source root. Ships a Python CLI (init/next/check/ship/new) plus a local command adapter and an SSH/systemd adapter with release directories, an atomic current/previous switch, a deploy lock, a commit-versioned JSON probe and automatic rollback on a failed probe; bootstrap and teardown provision and remove the unit and the reverse-proxy block idempotently and refuse to delete a root they did not create. Includes a runnable example workspace and a skill that keeps the agent on one phase at a time. Requires Python 3.10+ and PyYAML; remote deploys need SSH access, rsync, systemd and Caddy on the target.
artifact-space
majestyjun/artifact-space
Adds an Artifact Space entry to the DSH sidebar that lists the final effective artifacts of each session, grouped by workspace and session, with an editor-style preview, image previews, search across workspaces and sessions, favorites, and provenance for every file.
dsh-not-token-killer
archettosuki/dsh-not-token-killer
本插件仅供娱乐使用,非实用性插件,下载前请自行选择。DeepSeek Harness 非官方社区插件(Token-Reducer?):模拟执行任务,生成 SIMULATED 轨迹与 0 字节产物,不调用真实模型或工具/For entertainment only. Not a practical plugin — download at your own discretion.Unofficial DeepSeek Harness plugin that simulates task execution with SIMULATED traces and zero-byte artifacts.
dsh-task-center
platato-da/dsh-task-center
Scheduled Agent tasks for DSH 0.2.1-rc.5 with per-task models, workspaces, independent or persistent sessions, run history, and file artifacts.
ai-native-sdlc-dsh (sdlc)
hmydk/ai-native-sdlc-dsh
AI-native SDLC as a DeepSeek Harness bundle: task state machine and artifact chain, independent verification with structured verdicts, per-issue rework and re-verification, test freezing, RSI retrospectives, and a read-only dashboard.
dsh-session-artifacts
accoutmissing/dsh-session-artifacts
A right-sidebar tab listing the files DSH Sessions produced, newest first, with the Session in view expanded on top: a click copies a row's full path, a double click previews it in the sidebar, and a file can be pinned in one Session or in all of them.
dsh-owlrunkit
yeemio/dsh-owlrunkit
Oferece a Skill OwlCoda RunKit no catálogo de skills do DSH: objetivos e itens de trabalho do projeto, identidade dos candidatos, comprovantes de verificação, transferências e recuperação ficam nos artefatos do projeto. Instala apenas instruções; o CLI owlrunkit local do projeto exige uma etapa de configuração separada.
delivery-video-plugin
lumos-789/delivery-video-plugin
Transforma um recurso realmente funcional em um vídeo de demonstração confiável: gravações reais da tela, narração edge-tts com legendas sincronizadas por palavra, pipeline ffmpeg autocontido e controle determinístico de qualidade (especificação, áudio, volume, varredura de tela preta/congelada/silêncio) que reprova demos falsas ou quebradas. Inclui pré-verificação e validação dos artefatos. Requer Python 3.9+, ffmpeg/ffprobe no PATH e `pip install edge-tts Pillow`; a narração chama o endpoint público do edge-tts.
dsh-guard-degen
chunqing286/dsh-guard-degen
Detecta e contém fluxos descontrolados de símbolos no limite do modelo do DeepSeek Harness, com ferramentas para reparar artefatos e sessões contaminados.
dsh-plugin-market-selfhosted
yanghongqiang3/dsh-plugin-market-selfhosted
Marketplace de plugins auto-hospedado para DeepSeek Harness com contas, grupos, permissões, armazenamento de artefatos e estatísticas de instalação. Execute o servidor com Docker e instale este bundle de cliente no DSH.
dsh-dual-host-plugin
mogragsigma/dsh-dual-host-plugin
Coordenação de dois hosts para DeepSeek Harness (大肥鱼 bot): transfere tarefas do chat local, executa trabalhos limitados em worker cloud e revisa resultados/aprova próximos passos em um workbench. Onboarding protegido de seis páginas, modelo por tarefa, registro de aprovação e entrega controlada por etapas.
dsh-conversation-overview
lingf/dsh-conversation-overview
Plugin DeepSeek Harness: adiciona a aba Overview ao lado de Chat/Trajectory e um resumo lateral do progresso da sessão (objetivo, TODOs, etapas principais), artefatos e referências. Inclui escopo por turno, prévia da memória OpenViking e navegação rápida.
writing-anything (dsh-writing-viewer)
kw12121212/writing-anything
Painel de escrita somente leitura para projetos com workspace `.writing-anything/`: cartões gerais por trabalho, árvore de unidades, artefatos YAML como cartões semânticos ou fonte destacada, lista de fontes e filas de decisão/revisão. O feedback da revisão no painel é gravado de volta pelo wa-cli.
dsh-outcomes
xinming-chenniang/dsh-outcomes
Registro de entregáveis para DeepSeek Harness: agentes registram artefatos finais (reports, pages, documents, sheets, images, datasets) em uma seção de configurações e página de gerenciamento. Guarda apenas caminhos, nunca cópias, e permite exclusão reversível. Uma CLI independente (add/list/stats/check/remove/restore) lê e audita o mesmo registro fora do app.
artifact-center
lishuo4096/artifact-center
Centro de artefatos entre sessões: ferramentas Agent registram arquivos entregáveis (PDF, Excel, PPT, código, JSON) num diretório compartilhado; painel lateral filtra por categoria, extensão ou palavra-chave.
dsh-open-artifacts
wuuuuu123-32/dsh-open-artifacts
Adiciona ao menu da sessão e à barra de título uma ação para abrir a pasta de artefatos da conversa: lê o log, identifica os diretórios onde ela escreveu arquivos e os abre no Explorer.
dsh-ai-workbench
uid-762/dsh-ai-workbench
Transforma uma solicitação em linguagem natural numa bancada de trabalho ao vivo: um painel lateral faz algumas perguntas, o modelo cria um artefato HTML de arquivo único e o plugin o exibe numa janela flutuante redimensionável ou aba independente. Ações declaradas da janela são registradas como informação no diário do projeto, sem os payloads. Workbenches podem ser importadas, exportadas ou instaladas de um índice de mercado.