Plugins

Read-only Excel analysis toolkit for dsh (DeepSeek Harness). Streaming xlsx reader (yauzl + sax), describe / filter / pivot tools, big-file safe.

Model-facing MS Word (.docx) tools: read documents as Markdown or structured blocks, create documents from Markdown, and edit documents round-trip; ships binary fs providers (writeBytes, incl. a sandbox-preserving one) for hosts without it

Desktop-grade DeepSeek Harness plugin: native notifications for user questions/approvals, a floating attention HUD, a screen-capture tool, and a multi-agent tiling canvas.

DeepSeek Harness (dsh) Web plugin: open workspaces in VSCode from the sidebar, and jump chat-referenced files straight into VSCode with line/column support

DeepSeek Harness plugin: a deployment deny list of filesystem roots the model may never touch - fences read, write, search, and shell tool calls at tools/pre-execute

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

DSH plugin: dsh-repo-map

DSH plugin: dsh-evidence-task-board (npm package: @mkaliezz/dsh-task-board)

DSH plugin: dsh-dev-server

DSH plugin: dsh-api-client

DSH plugin: dsh-error-explainer

DSH plugin: dsh-test-normalizer (npm package: @mkaliezz/dsh-test-runner)

DSH plugin: dsh-docs

Hardening guard for mcp__omni__parse in DeepSeek Harness: a tools/pre-execute listener that denies private/reserved host URLs (SSRF), enforces an allow-list or ask (consent), and is fail-closed when allowedRoots is empty.

Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.

Minimal snippet and command toolbox for DSH: five tools over a single human-editable JSONL file, zero UI, zero database, zero network, explicit save-only memory.

Cue Omni Reader for DeepSeek Harness: registers the audited omni-reader-mcp MCP server so its URL/file parse tools surface as mcp__omni__ (parse, get_parse_status, read_result, read_outline, save_result, discard_result, cancel_parse).

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Enhances the DSH web session view — one-click collapse of reasoning and tool chains, numbered history quick-jump, Markdown export, AI avatars.

Diagnose and safely repair corrupted DSH session history: raw zstd/JSONL validation, tool-call ID repair, single-slot pre-repair backup, restore, and an audit trail.

Vision browser tool: drives real Chrome over CDP with browser-use and reads the page with deepseek-v4-flash-vision-exp, so canvas text, text baked into images and values in rendered charts are readable; returns JSON validated against a caller-supplied schema and reports per-run token cost.

MiMo (Xiaomi) tools as a DSH profile plugin: web search, image/audio/video understanding, ASR transcription, TTS, voice design and voice cloning — native agent tools with a Settings page for the API key.

SolidForge on the DeepSeek Harness — the globally installed plugin face: five skills in every session's catalog plus /solidforge:<skill> colon-gesture injection and the /solidforge, /arm-tools commands.

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.