Plugins

Per-session document ledger in the DSH sidebar (Windows only, Chinese-language UI): which documents a session read, created or modified, with time ordering, type grouping, search, two preview modes and a cross-session view.

Scans a repository with its bundled Python 3.12+ tools and scaffolds one Markdown outline per source directory, then publishes the index with a hash manifest that proves the documents match the code; the bundled reader verifies that manifest before serving an overview or one document. The project root needs a project_docs/ directory and a CLAUDE.md entry point.

Output gallery in the DSH sidebar, built to fix DSH reporting produced files only after a task ends: it watches your on-disk output folders and shows files as they appear, so you can verify and intervene mid-task instead of after. Auto-refreshing image thumbnails with zoom and pan, documents, code, data, archives and links that open in DSH native preview, per-conversation filtering, and multi-folder support for sessions whose cwd is outside the default output folder. Zero dependencies.

Registers one tool, report_health, that answers whether a scheduled report job actually ran. It judges by side effects rather than exit codes: how old the newest report folder is, how many documents it holds, whether more than one report category is present, whether the audit ledger was synced recently, and how long ago the last log was written. Exits nothing, calls no model, and reads only local paths you can override by config or environment variable.

Material library for dsh: collect a folder, file or note from a conversation, keep it in real folders with tags, browse it Finder-style, reopen the source chat's output in one click. Ships a materials_archive tool plus auto-filing rules: file a task's deliverable once, and every later scheduled run files the new documents by itself.

SolidWorks for DeepSeek Harness: model parts, build assemblies, create drawings, inspect, export and photograph SOLIDWORKS documents from the chat.

Read PDF, DOCX, XLSX, PPTX and text documents as agent tools, and OCR scanned PDFs or images locally with tesseract.js. Exposes doc_read, pdf_read, xlsx_read, doc_meta and doc_ocr.

Local knowledge base for DeepSeek Harness: distills workspace and chat-attached PDF, Word, Excel, Markdown, TXT, CSV and HTML documents into Markdown notes, with a VS Code-style viewer, per-workspace access grants and agent tools to search, read and add notes.

A local-first sidebar knowledge base for a DSH workspace: indexes projects, documents and plugins, classifies entries automatically, and provides search, file previews and editable notes. Data stays in the workspace.

Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.

Provides a specification-driven engineering workbench with versioned requirements and documents, isolated Git workspaces, independent review, verification, and explicit human acceptance. Requires Node.js 24+ and Git.

Search the documents and pictures in your Quberi knowledge base, browse its spaces and documents, save notes to it, and upload files into it with your approval for each one, from DeepSeek Harness over OAuth.

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

A dsh bundle plugin: preview local Markdown/HTML documents per workspace in the Web GUI via a /docs route on ctx.webServer + ctx.workspaceRegistry.

Attach tables and documents (xlsx, csv, pdf, zip…) to the DSH composer via paste or drag-and-drop: files are saved into the session workspace and an @reference is inserted.

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

Local semantic index over workspace documents (MD/PDF/DOCX/TXT): FTS5 BM25 + local embedding hybrid retrieval, hit citations with line numbers, and incremental updates.

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

Registers 36 bundled agent skills (research writing, LaTeX, experiments, design review, office documents, animation, Windows shell and dsh plugin conventions) as one host-only skill provider with no UI, no network calls and no telemetry of its own; skill scripts run with the user's permissions only when invoked, local skills of the same name take priority, and uninstall removes all 36.

Translates .hwp/.hwpx (Hangul) and .docx documents into the language the session model writes - Chinese is the common case, but Korean to English or English to Korean works the same way - keeping tables, bullets, indentation and font size, and writes the result beside the original as *_zh. hwp_extract returns the document segments as JSON (50 per page by default, 200 max, next_offset for pagination); hwp_apply takes {segment id: translation} and returns the output path with applied and missing counts. The plugin never calls an API and accepts no API key; its bundled 10 MB translator only reads and writes the file locally. Windows only: .hwpx and .docx are parsed in pure Python, while legacy .hwp drives the installed Hangul over COM and requires allow_hangul.

Writes engineering decisions down the way DSH documents its own — every non-trivial change leaves a Markdown note under .agents/notes/<lifecycle>/<class>/ holding the problem, the decision, the rejected alternatives and the consequences, committed to git and reviewable like code. It supplies the workflow for that: five tools (note_search, note_read, note_write, note_verify, note_skip), an end-of-turn hook that asks a code-changing turn to either write a note or record an explicit skip, the tree/format/archived checks, and the write-notes-like-deepseek skill bundled in the package and mounted by the plugin. A sidebar board that renders the notes into four views (architecture baseline, timeline, rejected proposals, decision list) comes with it; the notes themselves stay plain Markdown.

Security guard for DeepSeek Harness (Cordis): reviews every tool call in pre-execute against SlowMist agent-security rules, denying or flagging risky commands, MCP servers and skill loads, external URLs and repositories, untrusted documents, and EVM or Solana addresses; scans tool results for prompt injection after execution and ships a slowmist_scan audit tool plus an injected security policy prompt. Rules follow the open-source SlowMist Agent Security Skill (MIT).

Session-archive layer for DSH. It injects one per-workspace Markdown file into the system prompt on every turn, searches past session transcripts with AND keywords, an optional time window and a workspace filter, and recovers the images and documents those past sessions carried by returning their original local paths or copying them to a chosen directory. It also reports index health: version, entry count, cache usage, frequent sessions and sessions stored in an archive format it does not recognise. Keyword search only, no embedding service.