Plugins

Skill studio for DeepSeek Harness: visualize every agent skill (name, description, source, nested flag, model/user invocation), view and edit the full SKILL.md body, toggle model/user invocation, and mine DSH session logs to extract reusable personal skills that the agent auto-loads — from the web settings panel and via skillmgr_* / skillmgr_extract_* tools.

Windows desktop shortcut and system-tray launcher for DSH running in WSL, with fully hidden startup, tray open/restart/exit menu, and a plugin-configuration card to manage the shortcut.

Self-hosted crypto portfolio dashboard: BTC, EVM (73 chains via DeBank), Solana, Dogecoin, Cardano, Hyperliquid L1, five exchanges (Binance, Bybit, Backpack, OKX, Bitget) and tokenised equities in one view, with multi-provider failover, custom asset labels, a tunable asset-health report, a shareable PNG card, per-source connection tests, multi-profile configs, scheduled refresh and zero-dependency charts (Python stdlib + vanilla JS, no CDN).

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

Sidebar session-search toggle between title and content: title filters by session title, content searches historical messages through DSH's built-in full-text index, grouped per session with the strongest snippet and message-type tags.

Visual theme customizer for the DeepSeek Harness web UI — backgrounds, text colors, borders and details, all adjustable visually, with presets you can import and export, persisted across restarts.

DSH Skill Manager: browse, enable/disable, import from Codex/Claude Code/ZCode/WorkBuddy/QCoderWork, auto-discover skills with symlink support.

OLED burn-in care for the Web GUI with pure-black surfaces, gamma-aware text dimming on an idle/focus ladder, a true-black nap screensaver with live agent status, and slow accent-hue rotation.

Adds a capsule split-button to the conversation header: launch VS Code, terminal, or File Explorer at the current workspace directory in one click.

Codex-style temporary side conversations for DeepSeek Harness.

Daily news digest from 46 curated RSS sources, edited by the model already configured in dsh, delivered to your IM via webhook, and broadcast in the chat like a regular model reply with zero context cost.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Sidebar skill picker: lists installed skills with Global and repo badges, session checks plus persistent auto-start, optional Guard, Codex/Grok/Hermes user skills, and /skill injection.

AIEO (GEO/AEO) delivery method as one isolated skill provider: AI-visibility diagnosis on a 0-9 score, positioning, search-term mining restricted to whitelisted platform exports, periodic monitoring and an HTML monitoring dashboard, chained by one shared question library, plus a landing-page cloner.

Context7 MCP bridge: gives the model up-to-date, version-specific library documentation and code examples through the Context7 MCP server, keyless by default.

Tavily Search API as a web search provider (settings toggle with DeepSeek fallback, keyless search) plus a Tavily MCP bridge: keyless search and extract tools, crawl and map with an API key.

Per-execution HTTP/SOCKS5 proxy routing for Agent fetches, LLM providers, and shell commands, with settings-backed hot reload, approval-gated controls, and credential-safe status.

A sidebar assistant plugin for the Web interface, allows users to select any text, displays the model’s reasoning process and final answer in a floating panel.

Text viewer and editor for the dock workbench: undo/redo, Ctrl+S save, unsaved-change confirmation and binary detection, registered as the default file viewer.

Adds an x_search tool for X/Twitter search to DeepSeek Harness, authenticated through a separate SuperGrok OAuth account so it does not consume the session provider quota.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

Export and import DeepSeek Harness configuration across machines as same-OS .dshmig archives, with credential redaction, verification and rollback.

Markdown sidebar preview and source editor for dsh-better-sidebar, with block- and text-range annotations that can be sent to the conversation as structured revision requests.

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.