Plugins

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Anime Garden for DSH: search anime torrent resources from 動漫花園, 蜜柑计划, 萌番组 and ANi inside DSH — via chat, a sidebar panel with fansub and type filters, a seasonal calendar, and an in-app floating player.

A purely plugin-based implementation that brings "cross-session long-term memory + background self-evolution" capabilities to DeepSeek Harness: five-track memory · git branch awareness · in-turn self-review · skill self-evolution and skill manager · four-track to-do · COI scheduling · session broadcast · session search · prompt manager · temporary info notes—zero core modifications, zero runtime dependencies, ready to use upon installation and completely removable upon uninstallation.

Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

Cross-session long-term memory + background self-evolution (5-track memory/git-branch awareness/skill evolution).

Tracks DeepSeek token usage, per-call and session costs, and account balance with cache-aware charge animations in the DSH Web UI.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model and tool policies. By default the lead Agent completes simple work itself and delegates only when the saved squad is needed; delegated work runs as a bounded DAG with optional review and repair. Run Center tracks retries and per-member tokens from official Harness usage events.

Drags the official reasoning-effort row into a continuous track: blue-to-violet fill, a starfield on the higher levels, and the official value text tinted to the current level. Off stays gray; no official text is rewritten.

Multi-provider usage dashboard with provider/model token breakdowns, calendar drill-downs, account balances, and OpenCode Go / Z.ai subscription quota tracking.

Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness

Browses Douyin in a dedicated browser with daily viewing limits, shared local persona and interests, native settings, diagnostics, usage tracking, and reports. Replies and shares use selected conversations; group replies require a mention or configured name. Public comments require separate opt-in.

DeepSeek Harness control center for official balance monitoring, per-session costs and tokens, third-party token totals, completion alerts, official recharge, flexible layouts, and agent-assisted session controls.

A draggable Live2D desktop pet for the DSH web GUI that tracks the pointer, changes motion, expression and outfit with the session phase, and opens a right-click control panel.

Bottom info bar for the DSH Web UI: provider/model, live balance, peak/off-peak pricing with countdown, and real persisted per-session spend in a single line.

Trace Compare & Live Maze: draw the agent's real exploration — main path, failed or dead-end detours, backtracks, and subagent branches — on one wall-clock timeline; upload 1–2 session logs for a same-axis compare, or watch it grow live in a session tab.

Paper reading workbench: library + PDF reader + tutor-style companion. Answers cite clickable page numbers that jump back and flash the exact passage; select-to-ask without leaving the paper; bundled strict-tutor preset (reading plan, section coaching, graded quizzes tracked across sessions). With MinerU configured (self-hosted, no signup / mineru.net cloud token): scanned PDFs become readable, formulas become click-citable (one click sends the LaTeX source into the chat) and searchable (QK^T hits directly), plus a per-page formula panel; optional embeddings endpoint adds semantic recall for plain-language questions. Rename/delete topics and papers — deletes go to a recoverable .trash with a batch-clear flow for non-empty topics; reader with scroll/single-page modes, rightbar-fullscreen safe, one-click path copy and translated-PDF export; in-place original ↔ Chinese toggle (babeldoc, zero preinstall). Transcription and search run locally by default — documents never leave your machine; only when cloud MinerU, an embeddings endpoint, or a translation endpoint is enabled does the corresponding text go to the service you configure.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.

Per-round cache billing inside the composer context-meter popover: what the current call spends on cache hits, misses, and output in CNY, with automatic official peak/off-peak and per-model pricing; hidden on non-official DeepSeek routes.

In-GUI skill hub for DeepSeek Harness: browse, search, toggle, inspect, diagnose and scaffold local skills from the official ctx.skills registry, plus a skill market with tracked source sync and one-click update-all. It uses the same package name (dsh-skill-hub) and mount id (skill-hub) as hoshino114/dsh-skill-hub and amd47802574/dsh-skill-hub, so only one of the three can be installed.

Interactive K-line analysis for DeepSeek Harness with multi-market quotes, technical indicators, news, and fundamentals.

Syncs the wallpaper currently applied in Wallpaper Engine to the DSH Web UI background through a local bridge: preview/capture/full render modes, monitor lock, a wallpaper library panel for local and market content, focus lens with eye tracking, immersive mode, and a Windows app launcher that installs software from direct links or a cloud-drive share link and starts it with one click.

Agent audio studio for DeepSeek Harness: compose from note-level scores, narrate, add sound effects and mix, then fine-tune every track on an editable timeline where each generated sound arrives as its own clip. Speech uses Edge TTS (Microsoft's public endpoint, needs ffmpeg) by default, or MiMo-V2.5-TTS with your own API key; needs Node.js 22.19+.