Discover The Best DSH plugins
27094results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-recent-usage-metricsGeek-mode request metrics for DSH: live TTFT / tok-s / token readout in the composer status row, plus a glass history drawer of the last 10 requests.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hansomgar/dsh-recent-usage-metricsdsh-recheckTrack conclusions and revisit them when evidence files change.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:InInNHD/dsh-recheckdsh-recipeScenario bundles of dsh plugins ('插件界的 dotfiles'): a recipe tool that lists, searches, applies and composes ready-made plugin environments with ordered install sequences
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:863683348/dsh-recipedsh-reckonerDSH plugin: a deterministic calculation engine - values, formulas, dimensional analysis and a step-by-step record
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:curtainsmall/dsh-reckonerdsh-reclaimAudit DeepSeek Harness disk usage (sessions, attachments, rebuildable caches), classify it by risk, and move anything you choose to delete into the plugin's own recoverable trash. The model can query, never delete.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gankudadiz/dsh-reclaimdsh-reconnectSafe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrbeandev/dsh-reconnectdsh-record-replayRecord & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use session in the browser (getDisplayMedia -> webm + sampled frames), replay it, and have an agent analyze the frames and install a generated SKILL.md into ~/.dsh/skills. Hot-pluggable - mounted via the profile patch layer, no dsh source changes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kangshifu1/dsh-record-replaydsh-recovery-centerSavepoints for DeepSeek Harness before plugin updates break it, with offline rollback and a rescue UI that still opens when DSH will not load.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:supery0ung/dsh-recovery-centerdsh-recruit-tools猎头工作台工具插件：候选人/职位/推荐流水线（本地 JSON 落盘，领域模型参考 md-agent headhunter 模板）
dsh-rectangle矩形计算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-rectangledsh-recycle-bin回收站：把工作区会话移入回收站，保留 14 天后自动永久删除，也可立即手动删除或恢复。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EnhydraLutristus/dsh-recycle-bindsh-recycle-binDSH recycle bin plugin: move archived conversations to a recoverable trash, batch restore or permanently purge, with cross-platform safe file handling.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qwertyuiop314/dsh-recycle-bindsh-recycle-binDelete DSH sessions into a restorable recycle bin — subagent sessions follow their parent as one tree, and only purge destroys bytes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WangLemna/dsh-recycle-bindsh-red-packet红包礼仪
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-red-packetdsh-red-team红队渗透辅助插件：侦察/枚举/指纹/CVE 匹配/敏感路径（8 工具，仅限授权测试）
dsh-redactionMonorepo root for the dsh-redaction packages. Never published; it exists so plugin catalogues can discover the bundles below.
dsh-redis-pluginDeepSeek Harness (dsh) Redis plugin: connection, codec, thread-pool governance, query operations, distributed lock with watchdog, and model-visible tools.
dsh-redoEdit or retry an already-sent user message and regenerate in place: rewinds the model context to that message without leaving the session
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Imzl-zl/dsh-redodsh-redstone-musicMinecraft redstone-music toolkit: renders SoundFont samples with onset alignment, and compiles a song plus lane table into a scheduled mcfunction datapack (optionally deployed over RCON).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:19north/dsh-redstone-musicdsh-reduce-effectsWeb UI switch that turns off DSH frontend animations, blur, shadows, gradients and JS motion by category to cut browser rendering cost
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:azazo1/dsh-reduce-effectsdsh-reeditDouble-click any of your own messages to rewrite it and resend from that point; the original conversation is untouched.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Arbeiter-bit/dsh-reeditdsh-reelMedia library for the dsh web UI: browse configured local directories as a grid or list, open images in a viewer, and play videos in a page-fullscreen player with swipe navigation, order/random playlists and a fullscreen wallpaper.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lsjspl/dsh-reeldsh-reel-studiodsh-reel-studio: turn a DSH plugin repo into a deterministic promo video and promo image (host tools + Remotion studio).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Eileenes/dsh-reeldsh-reelsmakerDeepSeek Harness plugin: turn lines of narration into a finished vertical reel. Free neural voice-over, burned-in captions, no API keys.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aayan-cloud/dsh-reelsmakerUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.