Plugins

Right-sidebar novel studio that treats a chapter as a pipeline with checkable artefacts instead of one long prompt: scaffold a project, inspect the exact context pack a chapter gets, generate 2-6 parallel candidates and keep the one you pick, then run chapters in sequence with per-chapter progress on disk so it survives an engine restart. Length band, cross-chapter Jaccard and drift ratio are enforced in code rather than by model self-grading; rejections come back as repair evidence for up to two rewrites. AI-fingerprint metrics are reported against a 3956-chapter human baseline but never block, because the distributions overlap. Ships 7 agent tools. The writing engine is a separate Python package that the plugin installs on first use. Needs Python 3.10+ on PATH (or a path set in the plugin settings).

Syncs DSH skills, profile settings and AGENTS.md with a private git repository: status chip, six-section health check, pull, secret redaction, and a snapshot-then-push flow. Dry-run by default, never rebases or force-pushes.

A multi-project todo board inside DSH: capture notes in a global capsule overlay, group them into projects and mind maps, and export a todo into the composer as a task for the agent. Notes and todos are read and written on the author's hosted service (todo.memorymap.cn) after you sign in; set config.apiBase to point it at your own backend. Its HTTP routes have no DSH access check.

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.

Diet, workout and body-metric tracker for DeepSeek Harness: 12 agent tools log meals, sets, water and weigh-ins from plain chat, and a six-tab left-sidebar panel shows the day, the week, sodium/sugar intake, e1RM and the body-weight trend. Local SQLite only, no network, works without any persona plugin.

A fastfetch-style system and DSH panel: one slash command (/fastfetch or /ff) and one simple agent tool render OS, kernel, host, CPU, GPU, memory, every disk and local IP address, plus DSH version, model, session mode, plugin and skill counts into a colored terminal card, with a settings page that edits every field.

Real-time Codex/Claude/Antigravity quota-reset alerts plus AIHOT news digest and agent tools. News comes from the AIHOT public API, which is free for personal non-commercial use only.

Attach extra folders to one sidebar workspace: attached folders become writable for the file tools and the shell, are listed to the agent in its runtime context, and are added or removed from the workspace row context menu or the workspace_folders tool; each workspace keeps its own list.

Tool-surface governance for DeepSeek Harness: six scope-separated deny lists cut each agent's tool visibility through the host tools.restrict() API, unseen tool names wait in a pending gate, and dispatch_composed assembles a minimal surface from capability tags — a tasks array runs subagents in parallel, and a continued subagent keeps its original surface. Every decision goes to an append-only ledger that rotates into dated archives without ever losing history.

Long-term memory ported from the OpenAI Codex memory pipeline: sessions idle for 6 hours are extracted in the background by a chosen model, then merged by a hidden agent into a Markdown memory folder at most every 6 hours; new agents get the memory summary in the system prompt plus four tools to list, read and search memory and save corrections. Models are chosen on a settings page or with /memories; an optional filter keeps a notes folder out of memory.

Bridges a memory-nebula store into DSH: a panel inside the Harness UI to search, edit, pin and forget memories, plus three agent tools to check, search and revise them.

Per-session file tree: every file a conversation touched, laid out left-to-right by turn and split into deliverable, process, input and temp lanes; click a card to preview, reclassify or annotate. Temp files move into a recoverable trash with batch or single-file restore, batch emptying and an optional retention window. Ships a session_files tool so the agent can tidy up itself.

Gives every new conversation its own folder inside the workspace directory, names the folder after the conversation title, moves the agent working directory into it, and adds a session-menu delete action that asks before removing a folder that still contains files. It uses the same npm package name as DieJob/dsh-session-folders and does a similar job, so enable only one of the two; its HTTP routes have no DSH access check.

Wakes a Session after the host restarts: an agent arms its own Session, and after the next boot the plugin delivers one message to it, then unregisters it.

Session management for DeepSeek Harness — an archived-chat list in Settings, permanent deletion from the session menu, and agent tools to list, inspect, create and fork sessions.

Defines named roles that each pair a persona with a bound model and fallback chain, and exposes one delegation tool per role, so subagents are dispatched by role name instead of a provider/model string.

Brings Google Antigravity (agy CLI) models into DSH with streaming, thinking and native tool cards, a manual multi-account pool with quota and proxy controls, and an optional experimental direct transport. Community fork of amlyczz/dsh-agy-link. Google's Antigravity FAQ says personal plans do not support wrapping agy in third-party coding agents, so using it may put your Google account at risk of restriction. Needs Node.js 24 or newer and Google's agy CLI on PATH; the experimental direct mode is off by default.

Unofficial Volcengine Ark Agent Plan provider: registers an `ark-agent-plan` route with a model catalog fetched from the gateway, per-model thinking-effort control, server-side harness tools, and a quota badge with a panel showing remaining plan capacity.

Rewrites a draft prompt against the current project: a composer button, slash command and agent tool ground the rewrite in the workspace stack, structure and conventions.

Desktop dynamic island for DeepSeek Harness showing live agent status, approvals and questions, workspace switching, and usage stats.

UI design knowledge base: 99 filterable design cards with live demos, implementation prompts and per-design usage notes, plus an agent tool that finds and applies them.

Three custom agent presets, one editable character card each, with three built-in personas out of the box; import SillyTavern character-card PNGs or md/txt/json setting files, and the settings section handles naming, editing, and card-image display — edits apply on the next turn with no restart.

Read books inside DSH: import EPUB, TXT, Markdown or HTML into a paginated reader, highlight a passage and ask about it in that book's own agent session; four reading tools stop at unread chapters and everything stays in plain local files. Its routes are mounted with webServer.register and carry no DSH Host/Origin admission check, so a web page open in your browser can create reading sessions and change the library through them.

Grok-bot-style AI organization in the sidebar: a chief-of-staff agent creates departments, roles and per-department group chats, dispatches each task to child agents running on this machine, and reports finished work back as one assistant message. Its HTTP routes have no DSH access check, and they can create agents and dispatch tasks to them.