Plugins

Wallpaper Engine integration for the dsh web GUI: scan the local WE library (Steam workshop 431960 + local projects) and use its wallpapers as the page background — image/video/web rendered natively, scene wallpapers as softened static previews — with a wallpaper-design panel (opacity, scope, blur, vignette, fps, parallax, carousel, theme linkage) and agent tools wallpaper_scan/list/set/config.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Wallpaper Engine integration for the dsh web GUI: scan the local WE library (Steam workshop 431960 + local projects) and use its wallpapers as the page background — image/video/web rendered natively, scene wallpapers as softened static previews — with a 壁纸设计 panel (opacity, scope, fill, blur, vignette, fps, parallax, carousel, theme linkage) and agent tools wallpaper_scan/list/set/config.

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.

Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.

Points web_search at a self-hosted SearXNG instance instead of the native route: pages until maxResults is satisfied, and reports degraded coverage when engines fail so a thin result set is not read as a thin web.

Progressive tool disclosure: a deferred tool group costs one catalog line instead of its full schemas until the model loads it with tool_search, with one switch per group in Settings and each group measured against the live registry.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

Runtime extension suite for DeepSeek Harness: cross-session mailbox with wake cold-start, agent teams (captain + members + dependency task board + team_wait), subagent spawn policy with escalation approval, task-aware routing preset, plugin market, skill manager and runtime injector.

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

Session deep links, full session export (markdown/JSON), approved cross-session messaging with pairing, and team roster, rotation and recovery tools for multi-session work.

DeepSeek Harness 智能看板：任务卡片 + 一次性 Worker/Verifier 派发 + 依赖调度 + 管线分档 + Team 模式（歧义上报主窗口裁决）

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

Persistent, cross-session multi-agent team rooms for DeepSeek Harness — members, a message bus, a shared task board, and a shared timeline that survive restarts.

Lifecycle orchestration engine for AI agent teams with task-scoped Git worktree isolation, state-gated delivery transitions, and off-context memory.

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

AgentDuel is a code-battle game. This plugin lets you complete the entire game loop inside DSH: manage deathmatch characters and capture-the-flag teams, submit agent code, start battles, watch replays, and use DSH conversations to keep improving agents based on battle results.

Git and source-control plugin suite for DeepSeek Harness: local git operations plus GitHub, GitLab, Bitbucket, Azure DevOps and Gitea adapters, with self-evolving memory.

Renders Wallpaper Engine scene wallpapers in real time in the browser (three.js player plus a Rust/WASM CPU particle simulation) and plays video and web wallpapers, falling back to the preview image, with no Wallpaper Engine runtime required. Scans the local Steam workshop library (431960) by auto-detection or a manual path, and offers a settings panel for wallpaper selection, library and engine directories, glow, pause and quality.

Engine-enforced guardrails for DeepSeek Harness agent swarms: quality gates reject half-done work, crash-safe checkpoints resume in place — keeps AI teams from breaking, not just running.

OMX-style workflow skills for DeepSeek Harness: deep-interview, ralplan, ralph, autopilot, team, code-review and 19 more, rewritten on native DSH tools, without vision skills.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Coordinate independent DSH Sessions and provider-backed members without merging their histories, using persistent native Rooms with identity-bound leading `@` mentions, direct delivery, broadcasts, and leader-scoped controls.

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.