Plugins

A local-first todo board for the DSH sidebar with Todo/Doing/Done columns organised by project, storing everything in one Markdown file inside a folder you pick on first run. Cards carry due dates down to the minute, a colour stripe, a private blur that hides the title until you reveal it, notes and per-project roles, and can be dragged between columns or onto another project. The agent also gets a kanban tool that reads and edits every card, masked ones included. On macOS it installs three launchd jobs that run /usr/bin/python3 and post system notifications (a 09:00 digest, a check every 30 minutes for cards due within 2 hours, a Monday weekly review), which you can retime or disable in the in-panel Automations tab.

Fork of SheepofSheep/dsh-doyourweb that puts the browser on another machine: the MV3 extension dials out to this plugin over TLS, so DSH reads and acts on a remote Chrome or Edge rather than a local one. It also generates ready-paired extension packages for the current configuration, adds tab open and close tools, writes annotation detail to a file instead of pasting it into the chat, and shows a checklist naming which part of a remote setup is misconfigured. Interfaces with no DOM at all are reachable too: canvas games, canvas maps and hand-drawn widgets take coordinate clicks, drags and wheel input that glide, pause and hold like a person's, and the viewport is checked before every action so a stale coordinate is refused rather than clicked blindly. It reuses the same browser-tabs plugin id as the upstream, so do not install both in the same profile. Requires Chrome or Edge 125+ and an unpacked MV3 extension loaded manually on the browser machine; the plugin does not install the extension. With tls: true, trust the generated ca.crt as a root certificate there. The extension gives the model access to the tabs and signed-in sessions of the browser it is paired with. The bridge listens on 127.0.0.1 by default; a non-loopback bind needs remote: true, and the extension pairs with a token confirmed by the user.

Lightweight local visual grounding engine exposed as agent tools

Aggregated MCP market for DeepSeek Harness: 26 curated presets plus the official MCP Registry and user-added JSON sources, with search, source filters, connectivity tests and one-click install into the profile.

Reads a Windows app's window list, UI text and single-window pixels without screen capture, focus stealing or cursor movement.

Mail automation for DSH: IMAP IDLE sync, a follow-up queue, agent summaries through DSH sessions, approval-gated sending, and per-account HTML signatures with inline images. Windows only: mailbox passwords are encrypted with Windows DPAPI, and the credential store refuses to operate on other platforms.

Loopback HTTP bridge that lets a peer machine ping this PC and run shell commands, with an optional ssh reverse-tunnel supervisor.

A fact layer for daily heartbeat turns: diffs the curated plugin market for newly published entries and the Chinese education SRC calendars (EDUSRC rounds, Beijing education SRC seasons, the standing vulnerability-hunting exercise) for new items. Reports deltas only — the first call seeds a baseline and stays quiet.

Exposes Chrome DevTools Protocol to the agent through 17 tools for page summaries, element locators, activity timelines, console, network, storage and downloads, reading either a browser the plugin launches on its own or the tab the user is currently browsing through a small browser extension.

Native macOS tools for DeepSeek Harness agents, with 21 local tools for notifications, clipboard, screenshots, speech, keep-awake, dark mode, Spotlight, Shortcuts, AppleScript and Safari tabs. Zero dependencies.

Wraps the separately installed agent-desktop CLI (`npm i -g agent-desktop`) as nine DSH tools (ad_status, ad_list_windows, ad_snapshot, ad_find, ad_click, ad_type, ad_press, ad_launch, ad_close_app) so an agent can list windows, read an accessibility tree, click a snapshot ref, type text, send keys, launch an app and close it gracefully. The plugin adds no automation logic of its own: it validates arguments, calls the CLI and returns the parsed JSON envelope, and asks the caller to take a fresh snapshot instead of retrying a stale ref, so a click never lands on a shifted target.

Runs a local command, an HTTP request or a log entry on DSH lifecycle events (startup, session start/idle/end, user messages, tool results) or on a daily or interval schedule; a left-rail panel and five agent tools manage the same rule set.

DeepSeek Harness 插件：闲置会话自动归档、回到会话自动取消归档，带设置卡片与归档历史。

Reusable report automation skill with target-template and AI-generated standard-report flows

Optional external HTTP API for DSH Desktop, off by default, bound to localhost unless widened, and authenticated with a Bearer token.

Scheduled prompts that open a fresh conversation for every run, with cron, one-time and manual triggers, a per-task working directory, and run history kept out of the sidebar.

Control tower tools: dispatch a task to a role agent, read its report, verify and accept or send it back. Requires the separate agent-control-tower Python CLI (tower; it is not on PyPI — install it with pip install -e from the same repo) on the DSH process's PATH plus a tower init-ed workspace; without it every tool call fails with ENOENT.

Registers bundled full-stack, frontend-design and browser-automation skill documents as four read-only tools; a focus argument selects which reference file is returned alongside the skill body.

Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.

Codex-inspired lifecycle command hooks for DSH, with explicit tool-input sharing, pre-tool deny policies, notifications, and local audit examples.

Event-source plugin for DeepSeek Harness: cron, webhook, file watch, and deterministic procedures, with a ledger, console, and concurrency limits.

Sidebar node canvas for DSH where each node is an agent task and each link a dataflow dependency. One deterministic import (no model calls) produces both a task pipeline and a file-level module graph; file nodes carry a coupling score, and every run is snapshotted so it can be undone as a whole.

Scheduled Agent tasks for DSH 0.2.1-rc.5 with per-task models, workspaces, independent or persistent sessions, run history, and file artifacts.