Плагины

Zhihu inside DeepSeek Harness: hot, recommendation and follow lanes plus in-site search, formatted question and column bodies, a per-item discussion that runs as a real Session, and one-key export to Obsidian through its REST API. Reads with your own signed-in cookie, kept in the credentials service.

Read-only disk usage scan and interactive HTML cleanup report for Windows and macOS. Needs Python 3 on the machine; the bundled scan scripts run offline as child processes.

Adds 17 barotrauma_* tools to DeepSeek Harness for making Barotrauma mods: environment probing, mod skeleton, item and weapon XML, afflictions, creatures, random events, Lua and C# script scaffolding, localization, validation, icon generation, zip packaging and Steam Workshop publish notes. barotrauma_gen_icon sends your prompt to image.pollinations.ai and writes the returned image into the mod folder; on Windows the Steam install path is read with reg query.

A manual screenshot button for the DeepSeek Harness composer that captures a screen region and sends it to the model as an image attachment. Windows only.

SMTP/IMAP email bridge with five tools: send, list, read, download attachments, and list folders. Needs Python; the send tool sends real email from your account, and the mailbox authorization code is kept in the profile's cordis.patch.yml.

On-demand MCP tool loading. Only the mcp__* tools listed in the coreTools whitelist (max 5) stay in a session's tool set; every other MCP tool definition is actually removed from the request through the session-scoped tools.restrict() API and comes back only after the model calls lazy_load_tool. A tools/pre-execute gate turns calls to unloaded tools into a load-it-first error, and activation resets when the session ends.

Paste a Douyin video link (easy to copy from the Douyin PC app) and the plugin downloads the video, transcribes the speech offline into timed Chinese text, and imports it into Obsidian as a Markdown note. Built for DeepSeek Harness and for beginners building a personal knowledge base. Needs Python 3.10+ with playwright (it drives Edge), PyAV, sherpa-onnx and numpy installed, plus a SenseVoice model placed under %USERPROFILE%\.dsh\douyin-kb\models.

Zotero bridge: search, read, add, update and trash items in a local Zotero library, read PDF annotations and notes, pull indexed full text, and find related papers by DOI. Needs Zotero 7 or later with its local API enabled; the first write triggers a Zotero authorization prompt (the key is stored in plugin-data/dsh-zotero/auth.json) and permanent deletion asks for confirmation. Finding and adding items query OpenAlex, Crossref, arXiv, PubMed and Open Library. Uses the same package name (dsh-zotero) as Vncntvx/dsh-zotero, so only one of the two can be installed per profile.

Download only a time range of a video (yt-dlp segments; long videos fall back to HLS when the DASH URL cannot be seeked), verify the cut with ffprobe and sampled frame contact sheets, and serve the clip over a temporary LAN HTTP link with byte-range support. Exposes video_clip_download, video_clip_verify and file_share tools plus a video-clip skill; requires ffmpeg/ffprobe. Installs yt-dlp with pip into $DSH_HOME/cache/video-clip when it is missing; file_share serves a file or directory over unauthenticated HTTP bound to 0.0.0.0 (visible on the LAN) for 30 minutes by default.

Learn from Bilibili videos, web pages, local files and live streams: local ASR, on-screen OCR and extractive digests add up to about 1.5KB of text per source, so the model reads a summary instead of a full transcript.

Registers the REA reverse-engineering toolset in DSH and manages its Node and REA runtime, with a global tool switch, a live composer status indicator and in-place runtime upgrades. On first start it downloads a pinned Node and REA runtime (from nodejs.org and npm) into a managed location and registers REA's full tool catalogue as mcp__rea__*; optional analyzers are set up only on request.

Manual context compaction for DSH Agent Teams, adding a scoped compact_context tool and the /compact-agent command.

Drive the DOTV infinite canvas from DeepSeek Harness: the agent lists your canvases and their nodes, adds text nodes, and runs image/video/audio generations — over DOTV's public API, with no runtime dependencies and no build step. It reuses the `dotv` CLI login on the machine, or takes an API key in the plugin settings. Generations consume credits on your account, exactly as they do in the app.

Detects repetitive loops in an agent's reasoning output and records, nudges, or cuts them, with a history report. Defaults to a nudge (a reminder injected into the next request); cutting and auto-resuming is opt-in, and should not be combined with another plugin's cutting such as dsh-loop-rescue. Needs DSH 0.2.1+ and Node.js 22.15+.

Ren'Py localization toolkit that generates a full translation skeleton from compiled games, ports existing translations, and validates them.

Merges every folder's videos into one file per folder, matching the first clip's resolution, frame rate, and codec; clips with identical specs are concatenated losslessly, while mismatched clips can be normalized first.

Daily chronicle for DeepSeek Harness: collects session events, closes the previous calendar day after midnight into a Markdown week file (LLM scoring adds a daily summary; rule scoring does not), and extracts durable facts — decisions, conventions, pitfalls — that merge across days and can be superseded. 10 tools, a read-only sidebar panel, rule export, and a standalone Obsidian vault; zero third-party dependencies.

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

Daily session digest that grows a user profile and a companion personality, gated by evidence, and injects both into every prompt. Runs daily at 17:00 by default over up to 20 sessions per run on the host model (deepseek-v4-pro), applies the results automatically, and injects up to 1200 characters of profile and persona into every prompt. Its package name, dsh-persona-memory, is also used by other listed entries, so install only one of them.

Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.

Native DSH support for context-mode (mksglu/context-mode), intercepting large tool outputs with SQLite FTS5 indexing, BM25+RRF search, and session continuity. On by default: tool outputs over 4 KB are replaced with a short preview while the full text is indexed into ~/.context-mode/context.db, and a section is added to the system prompt. Its ctx_execute and ctx_batch tools run shell, Node, Python, PowerShell or cmd commands with DSH's own permissions and environment (not sandboxed), and ctx_index reads any local file path or fetches any http(s) URL it is given.

Local jot-down notes for DSH: one Markdown file per note, stored under ~/dsh随手笔记 by default (portable home path, no drive-letter assumption). Redesigned card UI, trash bin (deletions restorable for 30 days), custom tag management with stable per-tag colors (create tags ahead of use, delete one everywhere), compact/comfortable density, adjustable font size and line width, flat quick-scan list, full-text search, Markdown preview, autosave, batch deletion, zero-dependency Office text extraction, and AI write-back from conversations. Heavily reworked from dsh-knowledge-lite; pick the old library via the in-app root picker to migrate.

Local long-term memory core for DeepSeek Harness with plain-text notes, a bounded index, five tools, optional host-model consolidation and auditable evidence. It appends every user and assistant message under 32,000 characters to ~/.companion/cold/<date>.jsonl in plain text, with no built-in cleanup, and adds a short index of its notes to every system prompt; the optional model-based consolidation is off by default and, once on, sends those messages to the session's model.

Adds a recoverable trash bin for DeepSeek Harness sessions: right-click delete, restore, permanent purge, configurable retention with automatic expiry, batch restore and purge, capacity stats for bin / archived / active sessions, archive takeover that can unarchive or move archived sessions into the bin, and 10 agent tools. Entries are deleted permanently after 30 days by default, and the agent tools can purge entries or empty the bin.