Plugins

🐳 DeepSeek official 3D particle whale plugin for DeepSeek Harness / DSH Desktop (Three.js WebGL)

Expose the DSH Web GUI over IPv6 or IPv4 from WSL2 through a reverse proxy (Lucky): /wan up sets up the socat relay, Windows portproxy, firewall, and trusted-host fence, with a Settings card plus commands to configure the domain and ports.

Person-of-Interest skin for DeepSeek Harness: THE MACHINE surveillance-HUD theme (dark, cyan-on-black). Token override layer + HUD chrome + live telemetry panel for the dsh web UI.

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key.

Anthropic Model Context Protocol (MCP) client bridge plugin for DeepSeek Harness (dsh).

搞定看板 (gdkanban) — a DSH web GUI task board with custom categories, per-task workspace binding, and dual list/kanban views. Tasks execute for real through dsh sessions (session.prompt). Hot-pluggable, no dsh source changes.

Browser Use cloud bridge for dsh: run real web tasks — open pages, click, type, fill forms, and extract data — through the Browser Use API.

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

Browser-automation tools for DeepSeek Harness (dsh): Chromium via playwright-core behind a security-first navigation policy re-checked on every action

技能创作器：教 agent 按 agentskills.io 规范编写高质量 SKILL.md 技能（frontmatter、渐进式披露、触发描述）。改编自 Anthropic 官方 skill-creator（Apache-2.0）。

前端设计技能：指导 agent 产出高质量 Web 前端设计（视觉层级、配色、排版、组件、响应式、无障碍）。改编自 Anthropic 官方 frontend-design（Apache-2.0）。

DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ templates built in.

Skill for packaging DeepSeek Harness into a Tauri 2 desktop app (macOS + Windows): dual-platform install playbook, China mirror bootstrap with a subagent timeout sentinel, admin-free Windows toolchain recipe (no VS Build Tools), and three-path acceptance checklists.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.