Plugins

Daily brief for DeepSeek Harness. Every day at a fixed hour it ranks the plugin market by real install counts and stars, cross-checks it against your own agent memory and working conventions, and proposes two kinds of item: concrete deltas on the plugins people actually use (original does A, the proposal does B) and directions nobody has built yet. The popularity numbers come from the catalog the market itself publishes and are quoted into the prompt rather than guessed; an entry the market has not measured is shown as unmeasured, never as zero. Approving an item opens a new session named after it and hands that session a fixed delivery contract — implement independently, never fork, test green before publishing. Rejected sources are remembered so they stop coming back.

Daily and weekly task manager: startup popup reminder, a marquee strip above the composer, one-click circle completion, editable task cards, and a Sunday AI weekly summary, plus a sidebar DeepSeek API usage widget with balance card, today/cumulative tokens and cost, per-model breakdown and a 7-day chart. Persists as JSON under $DSH_HOME.

Multi-agent delivery workflow for dsh: a commander dispatches to fixed and temporary agents through a persisted task state machine, with a canvas and roster in the right sidebar.

Live skill provider that reads every Xiaomi MiMo (MiMo Desktop / MiMoCode) skill into the DSH session catalog: the engine-bundled skills under engine-config (unpacked from app.asar when that directory is absent), the MiMoCode global and project roots, extension-contributed skill directories declared in extensions.json, and the brand compatibility roots MiMo's own skillPathCompat setting enables.

Scans the skills DSH can load into one browsable catalog organized as collection, category and command, with a sidebar panel, click-to-insert into the composer, and custom categories and per-command notes saved outside the plugin directory.

Forces ASD-STE100 Simplified Technical English on every reply and every document. Commands: /asd100 on, /asd100 off, /asd100.

Push-to-talk dictation for the Web composer: hold a hotkey to record and the transcript is written into the draft through DSH's own speech Remote (local SenseVoice), with an optional auto-send.

Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any OpenAI-compatible image and video endpoint: switchable config profiles with separate endpoint, API key, model, path and size for each side, free-form extra request parameters, a connectivity test that does not spend generation quota, and three model-visible tools — generate_image, generate_video and check_video — with async video tasks that survive restarts.

Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable first line (`PIXEL_CHANGED=true|false`, greppable as an assertion), then the difference ratio, per-region bounding boxes, maximum channel delta and mean absolute error, plus a self-contained HTML comparison page. An ignore-region list with absolute or fractional coordinates excludes clocks, cursors and other per-render noise. It deliberately does no content recognition: it answers only "did this change", which is the part that can be made deterministic. Entirely local — no model call, no network, no upload.

Adds a right-column panel that compares a set of images the user picks from the workspace — 1/2/3/4/6 per page, per-image zoom and pan, the zoom and viewed position of one image synced onto the whole set, and a reorderable filmstrip. The browser loads every image, so none of it reaches the model.

OpenAI-compatible web search provider for the built-in web_search tool: one baseURL/apiKey/model config powers Qwen Token Plan, OpenAI and any Responses API gateway.

Open the extension side panel and it takes over the page you are browsing right now. On top of upstream it adds: hover, coordinate clicks, drag, batched action chains, whole-page screenshots, local file upload, image listing, and switching between several connected browsers. Pages reach the model as structured text with a numbered element list; actions wait for your approval and sensitive fields stay masked. Ships as the bridge plugin, with the extension in the same release. This project is a fork of omdsh-dev/dsh-browser: https://github.com/omdsh-dev/dsh-browser

Annotate pages inside the existing Harness Browser: click or drag to select, comment or ask, then send marked screenshots or DOM location details to the current session. While enabled it replaces the official Browser, Chat and Layout providers; targets Harness 0.2.1-alpha.2.

Chat with the DeepSeek web app (chat.deepseek.com) in a native DSH panel — a real browser drives the site on your existing web login, with streaming replies, deep-thinking and smart-search toggles, and image or document attachments. Conversations can be recovered from the web side, exported as Markdown, and distilled or replayed into a harness session, and the agent reaches the same web chat through six tools (dschat_status, dschat_send, dschat_stop, dschat_recover, dschat_import, dschat_transfer).

DeepSeek API billing-period chip in the composer dock: shows whether the current time is peak or off-peak with a countdown to the next rate switch, opens the peak/off-peak window rules on click, and during peak hours intercepts sending to ask for confirmation first.

Attach files and folders in the composer via clipboard paste, a native file/folder picker, and @-mention path search; folders are converted to paged Markdown for the agent to read page by page. macOS only (clipboard and picker go through osascript).

Turn-level file undo for tool writes and edits: each file is snapshotted before the write lands, and the model (an undo tool), the human (a /undo command) or a button in the assistant message action row can roll back every file a turn changed. Snapshots are written in-process rather than by shelling out, so it needs no extra sandbox permission in sessions confined to workspace-write.

Reads Claude Code and Codex plugin configurations to discover and preflight MCP servers and slash commands, with opt-in registration in DeepSeek Harness.

E-commerce plugin for DeepSeek Harness — product search, comparison and checkout across Taobao/JD/Pinduoduo, via the yuantoutao Streamable HTTP MCP server.

Folder time machine for DeepSeek Harness: snapshot any folder, browse its timeline, roll back with one click — Git-like history without needing Git, for folders that never had a repo (game saves, app config dirs, loose documents). Snapshots are content-addressed and deduplicated, and unchanged files are not re-hashed. Automatic snapshots come in two modes: realtime (fs.watch — one version ~8s after the last change, so a save-all or a build counts once) and timed (checks every N minutes, stores only when something actually changed; identical content never adds an empty version). Empty folders are recorded and recreated on restore. Every restore takes a safety snapshot first, so a rollback is itself undoable, and exact-mode cleanup only removes files and empty folders — a non-empty folder is never deleted. Ships a folder_timemachine model tool (status/history/diff need no approval; writes ask first) plus a floating panel with the timeline, one-click restore and mode switching. Pure JS, zero runtime dependencies, 110 tests included.

Use the free AtomGit quota already signed in on this machine to have AtomCode run an independent code review: the model calls the atomcode_ask tool on its own, and you can also use the /atomcode-review command to review uncommitted changes, a branch or a PR in one click. The plugin reads no API key; a usage pill below the input box shows the CodingPlan quota.

A shareable delivery receipt for a project hand-off. The `ship_receipt` tool measures what it can and records what it was told, then sorts every line into three zones: verified (evidence this run produced and that reproduces elsewhere — a command that actually ran with its exit code, a file hash for a file that is under version control, a scan that found files, a git ref present in the recorded remote), local-only (true on this machine alone — uncommitted changes, unpushed commits, an artifact no one else can see), and unverified (no evidence, including every sentence a human typed). A claim with no evidence keeps its label and leaves the body blank rather than printing the claim; declares the commit and branch, artifact byte sizes and sha256 with PNG dimensions, and the three pre-push checks.

A delivery receipt panel for a project hand-off. One trigger collects the branch and commit, the test and build results, screenshot dimensions with sha256, and the secret-scan verdict, then assigns every line to one of three zones by evidence alone — verified, local-only, or unverified. A claim in the unverified zone keeps its label and prints an explicitly empty slot instead of the claim itself, because a confidently worded sentence with nothing behind it is the exact thing the receipt exists to catch. Test failures and secret-scan hits are still evidence, so they land in the verified zone with a red tone rather than being quietly dropped.

Generate images and videos directly in chat and deliver them to the conversation: generate_image / generate_video / send_media tools, a built-in Agnes free tier plus any OpenAI-compatible backend, background jobs that auto-push finished media, and inline gallery and video cards with download, lightbox, and native open.