Plugins

Connects WeChat, QQ, DingTalk, Lark, and Telegram to DeepSeek Harness with unified configuration, private-chat and group access controls, and channel-side Agent chat and session commands.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

Reverse-engineering preset for DeepSeek Harness: domain skills live inside one "reverse mode" and the model routes by target type (web/JS, Android, iOS). The JS domain ships three skills (AST deobfuscation, controlled iv8 execution, JSVMP recovery) and mounts the js-reverse-mcp browser forensics server as mcp__js-reverse__* tools.

A character who lives on her own phone: the plugin installs and runs her Android phone, and any app notification can wake her; she installs apps herself and browses, likes and comments in apps such as Xiaoheihe or Bilibili; she has her own QQ (NapCat / SnowLuma, multi-part replies, stickers); memory with people cards, a daily diary at 23:30 and automatic recall before each wake (local embeddings by default, SiliconFlow / DashScope optional); a life between conversations (after HDS-Interlude); and an optional microVM computer with approval gates. Sidebar tabs show her phone, her computer and a dot panel; personal settings live in ~/.dsh/dsh-dot.json, and each of the six components can be turned off. Only the QQ number set with /qq owner counts as you; other people's messages are treated as untrusted notifications.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Browse every message you sent in the current session: full-history listing with newest-first sort, text filter, one-click copy, and jump to a message (auto-loads earlier history when the target is not yet loaded).

Local task board for DeepSeek Harness. Triage session requests, group related sessions, review deliverables and continue work from a shared task card.

Personal Agent Skills and /init plugins for pi, DeepSeek Harness, Cline, Grok Build, goose, and Aider

Offline schematic review for EasyEDA Pro, exposed to dsh as four tools — one-shot checkup reports, architecture skeletons, an install doctor, and a live-editor bridge that prefers read-only actions, all driven by the local boardwise CLI.

Multi-agent orchestration agent preset for DeepSeek Harness: one chief orchestrator that never implements itself — it triages every request, has a PM expert plan the work, and delegates implementation to domain experts via a merged expert roster (list and summon tools), scheduling parallel work through a dependency-DAG taskboard and a file-based message bus, with delivery gated by an independent review. Ships 11 core experts; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification. Published on npm as dsh-expert-orchestrator (requires DSH >= 0.1.7-alpha.2).

Three Zhihu tools for DSH — in-site search, Zhihu's global web index with domain and date filters, and Zhida answers — with a native settings card and source-cited results.

Cache-stable progressive tool discovery: a fixed tool_search and tool_dispatch surface on every request, in-memory catalog search, nested dispatch through the Harness pipeline, and a byte-stable native tool list across discovery.

Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.

Multi-dimensional quality scoring for DeepSeek Harness plugins that scores a repo or npm package across install success, maintenance activity, documentation completeness, security scan, and protocol compliance using real CLI evidence, and produces a JSON or Markdown leaderboard report.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

MiniMax multimodal bridge: one `mmx_bridge` tool covers image understanding/generation, video, TTS, music, cover, web search and quota; optional `web_search`/`read_image` takeover; inline players/image previews right in the Web GUI (npm: `dsh-mmx-bridge`).

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

Registers the justSkill design skill in DSH, adds a workbench that lists design files across workspaces, and opens a file's live canvas in the session's right sidebar. The agent edits a validated HTML file one operation at a time while the user reviews and adjusts on the canvas.

Registers two MCP servers that drive the installed AutoCAD and SolidWorks desktop apps over COM, plus two on-demand skills. Windows only, Python 3.11+; the pinned upstream servers install themselves on first load, and only the sides whose CAD application is registered get a row. Each server advertises two meta-tools instead of its full catalog (a discovery shim here for SolidWorks, upstream DISCOVERY_MODE=search for AutoCAD), taking the schemas loaded before the first request from 23,404 to 256 tokens and from 83,732 to 365 respectively.

Domain-identity layer for long-running agent sessions — declaration-first domain addressing, a session factory, four-level pause, and model dispatch for coordinating multiple top-level sessions.

One-command VPS deployment for DeepSeek Harness: a zero-dependency login gateway with automatic HTTPS that proxies the native web UI, a token-protected setup wizard, and one-click DSH upgrades with automatic rollback; as a plugin it adds Settings → VPS Deploy to install DSH on (or remove it from) a VPS over SSH from a form, plus version, upgrade, gateway status and a QR code to add DSH to a phone's home screen.

Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.