Plugins

Lets the agent drive the Chrome tab you @-mention — 13 tools for tabs, snapshots, clicking, typing, keys, scrolling, dragging and screenshots, with input sent as real CDP events so pages see isTrusted true and a pointer drawn inside the page. Needs the bundled Manifest V3 extension loaded by hand in Chrome (developer mode; it requests the debugger and all-URLs permissions), talks to it over a WebSocket on 127.0.0.1 ports 30795-30805, and saves screenshots under ~/.dsh/chrome-tab-shots; the macOS native input channel also needs Accessibility permission and the Xcode command-line tools.

Configuration bundle that connects Microsoft's official @playwright/mcp to your running Chrome through the Playwright extension, so the agent can drive your logged-in tabs. Install from a local copy: put your extension token in cordis.patch.yml first (with the token, connections skip the extension's approval prompt, so keep it private). Needs Node.js and the Playwright Chrome extension; the default command is the Windows form (cmd.exe /c npx), so change it to npx on macOS or Linux. It starts @playwright/mcp@latest through npx.

Postman-style HTTP workbench in the Harness Web GUI: collections and environments with {{var}} substitution, a request builder covering method, params, headers, body and auth, a response inspector, cURL import and export, and a CDN origin probe that fetches the same URL twice so a deleted file can be told apart from an edge cache. It also exposes an http_request_desktop agent tool that shares the panel send path, so a request debugged in the panel can be replayed by the agent. Zero runtime dependencies; state lives in $DSH_HOME/postman-desktop/store.json.

Gives the desktop agent one whole screen, or one half of a single screen. It lists windows whose center is inside, snapshots that rectangle, and left-clicks or replaces a control value. These tools do not move the system mouse, but the package also registers desktop_step, which drives the real mouse and keyboard across the whole virtual desktop (up to 20 actions per call, including key combinations such as Alt+F4 and typed text), plus get_screen_metrics; asking before acting is only in the tool description, not enforced. Windows only; compiles a C# helper with csc on first use; its tool names match dsh-desktop-tools-plugin, so do not enable both.

Lets the agent read the app, title, URL and text of the window in front through the macOS Accessibility API, with opt-in on-device screen memory it can search.

Add-on layer over the official QQ bot plugin @tencent-connect/dsh-qqbot: gates group messages before they reach the agent (probability, debounce with backlog, invalid-message filtering, admin approval before reading attachments), greets idle private chats, and adds emoji stickers via dsh-meme, TTS/ASR voice replies, image generation and one settings page. Needs the official QQ bot plugin installed (plus dsh-meme for stickers). Group gating defaults to a 25% chance and only applies when mentions are not required; the private-chat greeting is on by default (22:00-08:00, at most 3 a night, only to chats that wrote first); voice and image generation call endpoints you configure; with no admins configured nobody can approve attachments.

InfluxDB 2.x client for DeepSeek Harness: six agent tools and a side panel run Flux queries, inspect schemas and buckets, manage connections, and write line protocol.

Offline A-share checkups as four agent tools: valuation percentile (PE/PB/PS history, with negative-PE exclusion for loss-makers and a sample-length floor) and financial-statement review (three-statement reconciliation, DuPont decomposition, red flags, peer percentiles). Bring your own data; the plugin never fetches quotes and ships no data source. Needs Python 3.8 or later (standard library only).

TransProof translation proofreader for DeepSeek Harness: full web UI (AI translation needs your own model API key or a local Ollama endpoint) plus a local, non-networked run-local-check agent tool.

Manual context compaction for DSH Agent Teams, adding a scoped compact_context tool and the /compact-agent command.

Drive the DOTV infinite canvas from DeepSeek Harness: the agent lists your canvases and their nodes, adds text nodes, and runs image/video/audio generations — over DOTV's public API, with no runtime dependencies and no build step. It reuses the `dotv` CLI login on the machine, or takes an API key in the plugin settings. Generations consume credits on your account, exactly as they do in the app.

Detects repetitive loops in an agent's reasoning output and records, nudges, or cuts them, with a history report. Defaults to a nudge (a reminder injected into the next request); cutting and auto-resuming is opt-in, and should not be combined with another plugin's cutting such as dsh-loop-rescue. Needs DSH 0.2.1+ and Node.js 22.15+.

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.

Adds a recoverable trash bin for DeepSeek Harness sessions: right-click delete, restore, permanent purge, configurable retention with automatic expiry, batch restore and purge, capacity stats for bin / archived / active sessions, archive takeover that can unarchive or move archived sessions into the bin, and 10 agent tools. Entries are deleted permanently after 30 days by default, and the agent tools can purge entries or empty the bin.

Wakes a DSH conversation on demand and hands work to it: pick one or more sessions to auto-wake when DSH starts, give each session its own provider, model and reasoning effort, and let the agent call another conversation with the session_task tool — it wakes that session, delivers the content, waits for it to finish and brings the answer back. Also ships list_sessions and wake_session tools plus a settings page titled 会话唤醒; no QQ or bridge dependency. The three tools are available to every agent and can reach any session in the profile; the auto-wake list is empty by default, a session's boot prompt is delivered at every DSH start, and session_task waits up to 300 seconds by default.

Session trash for DeepSeek Harness: move cold sessions out of the sidebar into a recoverable trash, restore them within the retention window (30 days by default), or delete their logs permanently. A trashed subagent tree moves and restores as a whole, a shared DSH toast offers undo, and the settings page supports search, sorting, multi-select batch restore and emptying the whole trash.

Dispatch a task to a real DSH session by workspace path or session id; results land in a persistent task ledger that can be queried without triggering the model. It serves HTTP on 127.0.0.1:7391 and requires a bearer token it generates on first run (kept in ~/.dsh/relay/token), rejects non-loopback Host and foreign Origin, and stores task results as JSON files under ~/.dsh/relay/tasks; an optional notifyUrl receives each finished result.

Pause or resume the running task from a 28 px button beside the DSH composer: safe pause lets the current step finish, holds the next agent/pre-step boundary, and resumes the same turn without a continuation message; force pause cancels immediately, and the default granularity is configurable in Settings.

Adds a Q&A agent preset that answers each new question from a clean context: earlier exchanges leave the model input via a surface replacement, with no extra model call and no summary residue. A /qa follow command and a composer toggle switch to follow-up mode, and /clear archives the session and opens a fresh one under the same preset.

Keeps a root turn open until progressing child agents and the current-turn background jobs it started settle, then asks for one self-contained final answer in that same turn. Idle children that still have parked input do not delay closing. It observes job settlement without consuming job output, never cancels children, and does not decide task success. Verified on DSH 0.2.2-rc.2 only; on any other host version it stays inactive, logs one warning, and turns close natively. Each batch of results that arrives after a reply costs one extra model call; ordinary questions add none.

Collapse older messages in long conversations and permanently delete sessions you no longer need.

Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.

Export a DSH session tree (lead plus subagent fleet) to two Markdown files from one frozen snapshot: a readable narrative summary and a complete raw archive. Target directories are checked against the session file policy, and a blocked location falls back to the workspace exports folder.