Plugins

Verifiable research-report engine for DeepSeek Harness: a content-addressed evidence ledger (claim ↔ snapshot binding, tamper-evident) plus versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory

Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers

dsh-qa QA Workbench: a local software testing workbench plugin for DeepSeek Harness. Project/iteration dual-mode, full-flow requirements / test cases / defects / milestones / reports, native QA preset, themes, kanban and calendar.

DSH Web 桌宠插件：浏览器里养一只随会话状态换表情的桌宠（内置 demo/remiel），支持随时切换或替换宠物形象；自带设置面板、一键更新与反馈入口

Adds a Restart DSH button to DSH Desktop Settings → General (通用设置).

Anspire AI Search plugin for DeepSeek Harness (dsh) — 全网搜索 + 垂域结构化数据

Explicit model input-modality selection for the DeepSeek Harness Web UI

A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.

An independent todo board for DeepSeek Harness: list/board/calendar/week/project views, AI tools (todolist / todolist_suggest), and a self-contained storage backend. Registers a top-level Todos tab; registers a right-sidebar Today tab when dsh-better-side

DeepSeek Harness (dsh) plugin that snapshots your workspace at every turn into a shadow git repository, so you can restore the files to any earlier turn. Your own .git is never touched, and plain directories work too.

DSH 图片插件：ask_user_choice 图片/图文混合选项（Web GUI 渲染图片选择卡，可放大查看）+ show_images 在回复中内嵌图片（图片与文字混排）。图片来源支持本地路径 / http(s) URL / base64 data URI。纯插件实现，不改核心包。

A dependency-free live wallpaper and theme center for the DeepSeek Harness Web UI.

Local-first usage, cost, quota, account, and forecast analytics for DeepSeek Harness Web, with coding-subscription OAuth sign-in (Grok Build, Codex, Kimi Code, Claude Code), an optional loopback API gateway, and opt-in local auth/usage monitoring

Role-play conversations with character cards, in-chat character-card authoring and editing, and image generation through configurable backends.

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Runtime governor for DeepSeek Harness: zero-progress steering, generation-bound verification evidence, evidence-aware completion guarding, and task-profile tool restriction.

Registers the DeepSeek Harness web server (dsh web) as an auto-start, self-healing background service — LaunchAgent / systemd / cron plus a 30s health-check watchdog — with seven dsh_daemon_* tools (install/uninstall/reinstall/status/start/stop/update).

Capybara secretary for DSH: desktop pet notifications with ding sound, alert inbox API, session-aware alerts (turn done / approval needed / turn blocked), check scripts, and daily high-star plugin recommendations.

macOS system notifications for DeepSeek Harness: aborted, max-tokens, blocked, interrupted and error events, pending questions and approvals, and completion or subagent-end via terminal-notifier; clicking a banner opens a configured app and returning to the page auto-dismisses them.

Auto-continue an interrupted dsh session after a web restart by injecting a "continue" follow-up; one-shot per process, no duplicate-injection loops.

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Verification gate for DSH agents: every acceptance criterion must be backed by server-stamped real tool evidence before the completion gate lets a goal through (advisory audit, enforce gate, durable permits).

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.