Plugins

Adds edit mode to the DSH settings nav for drag-reordering, per-section show/hide and named collapsible drawer grouping saved in the plugin's own settings namespace, plus pinning up to five sections to the main sidebar for one-click access.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

Mounts external skill directories (Claude Code, Codex, ZCode) into DSH as read-only skill providers: frontmatter field mapping, name slug normalization and hot reload.

Lists recent sessions across every workspace in one panel, with time grouping, two sort orders, content search, reveal-in-file-manager, and local notes that offer to insert themselves into the draft.

Browser automation for DSH: the agent fills in forms, scrapes lists and works across tabs in real pages, using the logins you already have. It drives its own visible window on your desktop — minimise it and it keeps working without stealing focus — and a sign-in, CAPTCHA or native dialog stops the run and hands the page back to you: it never confirms on your behalf. Login state persists (own profile plus session-cookie re-injection). 23 Playwright tools (20 always on, 3 gated and off by default), with a URL allowlist, dialog suspension and a CDP method allowlist that are mechanism-level and pinned by tests.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 13 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Shopping assistant for e-commerce: search, compare, pick and recommend products when buying things online, with price comparison, sales, service tags, product images and promotion links from the official Pinduoduo open-platform API, right inside the DSH conversation.

Wishing House theme skin with warm amber glow, live moon phases, meteors, typing sparks, procedural chime audio, and daily fortune slips.

Per-workspace MCP scoping for the DeepSeek Harness — decide which MCP servers a session may see from the directory it was opened in.

Customer-machine access plugin for deepseek-harness-gateway: opens a single outbound WebSocket to the gateway and relays the machine local dsh web UI over that tunnel using pairing-code + HMAC auth, so no inbound port, port mapping, or public IP is needed.

Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.

Reports DeepSeek Harness session activity to a self-hosted cc-monitor server, which surfaces Claude Code and DSH sessions as color-coded state cards in one web dashboard and pings your browser and Android app when a session needs attention.

Import local Codex CLI/Desktop, Claude Code CLI, and Claude Desktop conversations into DSH with project grouping, semantic history, and tool activity; bind an existing or replacement workspace and continue with the DSH Agent.

Smart form skill: structured record-keeping for bills, ledgers and logs with auto-categorization and periodic reports.

Firecrawl-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web)

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Workspace tidy-up plugin: moves stray temp files, render leftovers and generated scripts into a hidden .dsh folder at the end of each turn, keeping the workspace root clean without blocking or deleting anything.

A layered, temporal, self-developing memory engine for DeepSeek Harness

Telegram tools for DSH sessions: list chats, read cached messages, send text, photos, stickers, GIFs and dice, set reactions, forward/edit/delete messages, typing and chat members, plus optional getUpdates polling that receives and caches messages from allow-listed chats only and wakes the target session for them. Bot API only, no MTProto.

Tag manager for DSH: create, search and delete tags, with soft-delete and per-item mappings used by the workbench task, site and storage plugins.

Automatically opens the right sidebar for blank top-level chats on wide screens, skipping saved layouts containing tabs and leaving non-blank chats unchanged.