Plugins

Resumable JavaScript workflows with native child tasks, shared budgets and worktree isolation.

Teaching-first CTF solving skill: narrates each step's pattern, tool choice and underlying mechanism, then writes a reproducible writeup under solves/<challenge>/ gated by a nine-section check.

Skill Center panel for the current session: lists the visible skills with their provider and source root, renders each SKILL.md, toggles model and user invocation, and creates or soft-deletes skills; ships a skill-authoring skill and the skill_create tool.

Design-first PowerPoint builder: six pptx_* tools turn a deck.json design draft into an editable .pptx with AI backgrounds, cutout illustrations and decoration pieces, run layout and contrast checks, render slide previews, and review pages with a configurable vision model; chat cards and a settings page in the Web UI. Requires DSH Desktop 0.2.1-rc.2+ (pptx_render uses its bundled LibreOffice Kit) and an Agnes or ModelScope API key for image generation.

Export a whole working DSH home — profile, installed plugins with their node_modules, skills, hooks and task boards — into one .dshpkg tar and import it on another machine without network or pnpm; also streams over HTTP or a one-shot LAN link.

Local-first memory and persona plugin for DeepSeek Harness: four file-backed memory layers (pinned, memory, facts, experience), editable SOUL/MOOD persona, zero-LLM session capture, BM25 recall and a themed mood card; no standalone web panel, Python service, vector database, or API key.

Read-only session-log projector (drsc) for DSH: scans ~/.dsh/sessions/**, decodes zstd/tiled-frame logs with a vendored leaf decoder and rewrites per-session projections into its own SQLite (node:sqlite, segments / replaces + FTS5), exposed through a single fenced HTTP route — surface ledger, recall/compression pair accounting and Chinese-capable full-text search. Token counts share the exact DeepSeek-V4 tokenizer and formula as CCI verify, falling back to a labelled chars/4 basis when assets are absent. Never writes session files; all output lands in its own data directory. Serves three consumer plugins: context-compression-improved (surface marking + recall reconciliation), session-steward (search-corpus switch), prime-memory (historical anchor backfill). Hosts 0.1.0-rc.2 .. 0.2.1-rc.2 (17-tag exact engines.dsh enum). npm: dsh-reference-session-collector.

Session recycle bin for DeepSeek Harness: deleting a session from its row menu (or in bulk from the sidebar header) moves it into a recycle bin kept for 15 days by default — 7, 15 or 30 in settings — and expired entries are purged automatically. The bin table shows the days left for each entry, restores it to its original workspace, and can delete an entry for good, one at a time or all at once.

Model-linked characters and a shared world for DSH, with separate editable personas and memories, optional AI diaries and sleep consolidation, Chinese/English controls, task-aware desktop pets, themes and usage statistics; updates preserve user customizations. Supports Windows, Linux and macOS; see the guide for each system's installation requirements. Diaries and consolidation consume tokens. Before installing or updating, we recommend closing visible desktop pets and bubbles; open files may cause installation to fail. Codex and OpenAI API account queries have been user-validated; other sources await user validation and feedback.

Adds one system-prompt section that keeps private words out of formal deliverables and, every few of them, leaves a short note at the end.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.2 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Preview 0.6.0-community.5 with optional Retry is available separately in GitHub Releases. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox. Derived from kyle123740/dsh-zcode-cli-proxy (AGPL-3.0); it registers the same `zcode-cli` provider id, so it cannot be installed alongside the original.

OpenCode Zen free-tier models for DeepSeek Harness with anonymous no-key access, a loopback OpenAI-compatible shim, and real bash/read gate tools.

Use TRAE account model quota in dsh, with multi-account management, daily check-in, rotation, usage statistics, reasoning levels and model visibility. Requires Python 3.10+; the first run downloads Python dependencies.

Genshin Impact white-and-gold skin for the DSH web GUI: a random in-game landscape wallpaper on every page load, the Genshin UI font site-wide, a Paimon-style menu and a running-status element ring, and a switchable Paimon/Phanes assistant persona. The repository ships 262 wallpapers across eight regions at 1920x1080.

DeepSeek Harness plugin for SuperGrok and X Premium subscriptions: device-code sign-in, the xai provider, account-visible chat models with context and per-million-token prices, reasoning efforts read from model capabilities, and subscription usage.

Per-turn tool cost line in the chat stream: after each turn a collapsible row under the reply lists which tools ran, how many times, and how many tokens each tool injected into the context (input plus output), expandable to per-tool detail.

Provider-reported quota snapshots for GLM Coding Plan and GitHub Copilot in DSH: a draggable floating capsule with detail panels for quota windows, reset times, per-model usage and Copilot credits, plus an optional sidebar card hidden by default; credentials are resolved by the DSH host and no quota history is stored.

Per-turn first-token latency and output speed beside the built-in usage pill, folded on the host over the durable event log: first-token time is replayed from each message's compact stream, so historical turns stay exact after a reload rather than showing an estimate.

Finds wasted GitHub Actions runner time and proposes small, reviewable workflow patches, with explicit approval before any edit and a DSH settings page for analysis rules, history limits, storage, and cost estimation.

MCP server and skill management for DeepSeek Harness: a sidebar panel and a plugin-page config section with search, status lights, per-row switches, expandable details, and an add-server form following Codex mcp_servers fields.

Two-pane model picker that replaces the composer model menu with a searchable provider-grouped list on the left and a detail card on the right showing the selected model's context window, output cap, capability tags and reasoning-effort levels, all read from that model's own provider. The npm name dsh-model-picker belongs to another author; install through this GitHub source.

Turns an uploaded picture into a floating desk pet by cutting out its background in the page, with idle animation and a live account-balance bubble.

Icon, Chinese display name and a one-line note for every DSH plugin, organized with folders, favorites, drag or pinyin ordering, list and grid views. Icons are auto-assigned to all installed plugins and can be overridden; import and export cover icons, names, notes, folders and order. Display-only: plugin files and cordis config are never modified; enable switches call the official plugin manager.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.