Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
544 plugin trovati
dsh-sidebar-shelves
yl404/dsh-sidebar-shelves
Two-line session cards for the sidebar: per-workspace project tiles (monogram, emoji, color or image), pinning, hand or timed archiving with a collapsible archived shelf, running and waiting status markers, per-session background-job and subagent counts, and newest-input-first sorting. Web GUI; requires DSH 0.2.1-rc.5 or later.
deepseek-harness-plugins (dsh-runaway-watchdog)
codenestra/deepseek-harness-plugins
Repeated tool-call detection, error and spend circuit breakers, subagent limits, and audit records.
dsh-superagent
littlechenliya/dsh-superagent
Runs one goal as parallel subtasks and merges the reports into one answer; the run survives a host restart, spending is capped, and the cost is printed. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-sidechat
yuhhhong/dsh-sidechat
Temporary right-sidebar conversations seeded from the latest completed main turn, using on-demand managed subagents with attachments, skills, and live model and permission selection, without automatically sending replies back to the main conversation.
dsh-pmo-button (dsh-pmo-button)
suifei/dsh-pmo-button
Adds a persistent PMO reviewer subagent to a session: every turn is reviewed and the loop advances with whole-line STATUS: CONTINUE, DONE or NEED_HUMAN verdicts.
dsh-pmo-button
suifei/dsh-pmo-button
PMO 审查循环按钮 —— 为 AI 会话挂载一位“资深项目总监”。持久审查子代理 + 双线路 + STATUS 协议(CONTINUE/DONE/NEED_HUMAN)自动循环(DeepSeek Harness 插件)
super-dsh (better-dsh)
pgmi-builds/super-dsh
Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.
dsh-session-bell
11ze/dsh-session-bell
Raises one desktop notification when a turn stops, a question waits, or an approval waits. Each event has its own switch; subagent Sessions stay quiet; a click opens the Session. Uses the page's own Notification API, so there is no helper app or install-time registration.
dsh-delegate (plugin)
zzm1234560621-prog/dsh-delegate
Wires Claude Desktop, Claude Code and Codex to a local DeepSeek Harness over MCP, and adds a status panel to the DSH web UI.
dsh-session-prompts
gznofeng/dsh-session-prompts
Session-scoped system prompts: maintain a library of prompts in a settings page and tick them above the composer to inject into the current session only (subagent child sessions inherit via parentSession; empty tick list opts out), plus quick prompts that paste their text into the composer draft on click.
dsh-perch
wjinxuan/dsh-perch
A Dynamic-Island-style status panel that lives in the macOS notch and lists running turns, background jobs and subagents, with a completion banner and a spoken reminder.
dsh-depth-tool-gate
ddl095/dsh-depth-tool-gate
Tool-surface governance for DeepSeek Harness: scope-separated deny lists cut each agent's tool visibility through the host tools.restrict() API, unseen tool names wait in a pending gate, and dispatch_composed assembles a minimal surface from capability tags — a tasks array runs subagents in parallel, and a continued subagent keeps its original surface. Every tool also gets an auto-written one-line purpose note, so agents can look up what a tool actually does instead of guessing from a truncated summary, and a read-only explain_gate reports what was cut and by which rule. Every decision goes to an append-only ledger that rotates into dated archives without ever losing history.
dsh-plugin-turn-cost
jerodji/dsh-plugin-turn-cost
Shows each conversation turn's cost, including subagent spend, and the running session cost in CNY or USD, with a session budget pill in the composer, balance reminders, an all-session billing dashboard and Excel export.
dsh-agent-team-policy
mr-pounds/dsh-agent-team-policy
Adds one system-prompt section that limits delegation to subagents and teammates to two cases: adversarial review of freshly produced output, and one-shot context reading that returns a summary.
dsh-reply-language
waldemarpng/dsh-reply-language
🌐 A DeepSeek Harness plugin: pick the language beside the model selector and every reply — sessions, subagents, teammates, side chats — follows. Auto releases the pin.
dsh-subagent-agy
michael-ly/dsh-subagent-agy
Run Google Antigravity CLI (agy) as DeepSeek Harness subagents, with Gemini web Deep Research and parallel/team modes.
deepseek-harness-gateway
weifengze/deepseek-harness-gateway
HTTP API for DeepSeek Harness: agents / sessions / event timeline / SSE streams / steering / messages / runs / files / questions / subagents, with archived run manifests, per-key metering and tenant isolation.
dsh-sound-alerts
zaykoff/dsh-sound-alerts
Sound cues played by the host operating system, not the browser: three bundled WAV files fire through the machine's own audio (SoundPlayer on Windows, afplay on macOS, paplay/aplay on Linux) when an agent's turn completes, when the context is compacted and when the agent is waiting for your answer; subagent turns can be included, cues fired closer than a configurable interval are skipped, and each bundled sound can be replaced with your own file via plugin config.
dsh-plugins (dsh-360)
feahter/dsh-plugins
Health check for a DSH profile: scores skills and agent instruction files, subagent definitions and presets on one shared 18-bucket S–E grade scale, with a sidebar panel, four dsh360_* tools, and a backup with undo for every write.
dsh-session-trash
wangxiaocuo/dsh-session-trash
Session trash for DeepSeek Harness: move cold sessions out of the sidebar into a recoverable trash, restore them within the retention window (30 days by default), or delete their logs permanently. A trashed subagent tree moves and restores as a whole, a shared DSH toast offers undo, and the settings page supports search, sorting, multi-select batch restore and emptying the whole trash.
dsh-session-export
cnhenaihui/dsh-session-export
Export a DSH session tree (lead plus subagent fleet) to two Markdown files from one frozen snapshot: a readable narrative summary and a complete raw archive. Target directories are checked against the session file policy, and a blocked location falls back to the workspace exports folder.
dsh-delete-session
chichi233/dsh-delete-session
Adds a "Delete session" item to the sidebar session menu that moves the session transcript directory to the Windows Recycle Bin, or to a plugin trash folder under ~/.dsh/plugin-data when that is unavailable (restorable either way), and deletes its spill files and projection cache in one request, detaching a live session first and cascading to its subagent sessions. A setting switches the confirmation step off so deleting takes one click; duplicate delete items registered by other plugins are collapsed so only one remains.
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-chinese-thinking-mode
qiao-fang/dsh-chinese-thinking-mode
Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.