Plugins

Orchestrates durable multi-agent teams from one DSH session: a captain spawns member subagents, drives a dependency-aware task DAG with quality gates, and coordinates through persistent mailboxes, with a live activity panel.

Unit conversion toolbox covering 20 categories — length, mass, temperature, area, volume (incl. US cooking units), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration incl. g-force, illumination (lux / foot-candle), pressure, energy, angle, frequency, power incl. three horsepower definitions, force, torque, typography (px/pt/em/rem), and fuel economy (mpg ↔ L/100km). Two tools — convert_unit and list_units — zero runtime dependencies, pure arithmetic; each result includes the formula applied.

Connects DeepSeek Harness to a local SiYuan (思源笔记) desktop app: registers its note tools as mcp__siyuan__<tool>, exposes the AI configured in SiYuan together with its agent loop as one more tool, ships a notes skill, and enforces a readonly/authoring/full profile on every call while keeping the tool list available when the app is closed.

Workspace-wide sticky notes on an infinite canvas: notes are plain Markdown files, created manually, captured from conversations, or distilled by the AI, and can be handed back as context; ships 12 model tools and 5 bundled skills for creating, tagging, arranging, comparing and merging notes.

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy authentication, and dynamic model discovery.

A NieR:Automata / YoRHa-inspired industrial terminal theme for DeepSeek Harness Web with sand-and-charcoal palettes, square geometry, and interface-wide styling.

Shows OpenCode Go subscription usage (rolling, weekly and monthly used and remaining percentage with reset times) in a floating panel anchored to the bottom-left of the session window.

Notched reasoning-effort slider grouped with the model picker in the composer, with theme variables and English, French and Chinese labels.

Cherry Studio-style paste: multi-line/indented/fenced text or code pasted into the DSH Web composer collapses into a bordered, collapsible, language-tagged card and is restored as a fenced code block on send.

Select text in the dsh web conversation to attach it as an annotation to your next message. The source text keeps a dashed highlight with an ordinal badge in place, and the composer summary lists, edits and jumps back to each annotation.

Records real clicks, inputs, navigation and network traffic in a user-guided browser session for DSH, then generates a Markdown timeline report (report.md + events.jsonl) to build API-level skills.

Compresses DSH time-context from ~280 chars to 46 chars by injecting a compact date line into the runtime-context snapshot; zero runtime dependencies.

After official llm-retry (n/5) gives up, keep retrying transient API failures (timeout, transport, rate-limit, 5xx, dropped SSE) on the same open step until success, cancel, or pause; AUTH, QUOTA, and user Stop are never retried.

Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Discord-first adapter for DeepSeek Harness

Expert manager: manage ntd-format experts and expert teams (plugin.json + Agent MD + skill sets), browse and install from a built-in market of 50+ experts, and run tasks in an expert persona via /expert-<name> without consuming model directory tokens.

Plays a chime and speaks a Chinese voice alert when an approval, question, or plan-review popup appears in the DSH web GUI, so you never miss a request.

Review tab for DeepSeek Harness sessions: workspace changes versus HEAD or any two refs as a filterable file tree with side-by-side diffs, a lane commit graph with blame and file history, three-scope search, line comments back to the composer, and guarded stage/commit/branch/tag/stash/conflict operations.

Goal mode and autonomous execution plugin for DeepSeek Harness: a sticky top banner keeps the current goal visible across turns while the agent works toward it autonomously.

Adobe Lightroom Classic as native dsh tools through the lightroom-py MCP server: read the catalog, apply develop settings and presets, export JPEG/TIFF/PSD/DNG, and write ratings, labels, keywords and IPTC — 15 tools driving the Lightroom Classic installed on the local machine, no cloud round-trip; the Python package is on PyPI and the Lightroom plugin installs with one command.

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

One-click desktop launcher for DSH Web: creates a Windows .lnk with a WPF-style startup popup (progress + timeout), then opens the authenticated browser; plus a floating shutdown button that exits dsh gracefully via ctx.appExit.

Xianxia desktop pets linked to live agent sessions: MC pixel-style companions appear when subagents spawn (up to 3 on screen), with storage-bag collection, a right-click artifact menu, a pet gallery picker, and export to the Codex desktop-pet format.