Plugins

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Webnovel Writer：DSH 长篇网文写作工作台

DeepSeek Harness plugin: the claude-slides skill from baoyu-design. The agent writes editable slide decks as files and opens them in a local slide editor.

Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.

Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.

Runs project OMA checks before and after tool execution and when a turn tries to finish. Installs its OMA CLI dependency and initializes unconfigured projects on first use. Requires Node.js 22+; initial setup needs network access and project write access.

Let your DSH agent browse Bilibili on its own, read subtitles, write a daily digest, and @ you when it finds something worth your attention.

TongFlow film-crew studio for image, voice, music and video production: the agent writes per-asset TongFlow workflow files (.tongflow.json) that run through TongFlow plugins, with an embedded workflow canvas, a shot/character/take project layout and a manga-drama template; sessions starting with @tongflow open the Studio view.

Novel-writing workbench for DSH with an authoring preset, outline and character management, manuscript annotations, review workflows, and a managed local Python backend.

A Bilibili companion that keeps its own schedule. A 60-second tick in the plugin host wakes a dedicated agent session at a random moment inside the configured time windows (opting out of a day is a configurable chance), then hands it a bundled CLI of 38 subcommands — feed, subtitles, danmaku, comments, ffmpeg frame grabs, and two diaries. Shares at most N items a day by commenting on them and @-mentioning the owner (default 3, enforced from a written quota log, and it stops on rate-limit or captcha signals). Also polls comment replies, direct messages and live-room danmaku; replies to anyone but the owner are queued for approval in Settings. Settings → 养鱼 writes ~/.dsh/bili-whale.config.json; cookies live separately in ~/.bili-ai/credentials.json and are never echoed back. The HTTP routes are loopback-only behind DSH's trust fence. Needs Node 18+ and ffmpeg on PATH for frame extraction.

Workbench plugin for the DeepSeek Harness web UI: collects your own projects and mounted plugin entries with rename, icon, sort, show/hide, project-to-session binding and a per-project file cabinet, adds a split-pane workspace engine with draggable panes, tabbed windows and built-in Explorer, terminal, browser, animation and custom panes, and auto-mounts an agent output into the matching window when it writes widget-result.json.

Puts the agent on QQ as a persona character through SnowLuma (OneBot v11): private and group chat, voice notes, stickers, Qzone diary, Bilibili browsing, song covers, image generation, long-term memory and mood. Every feature is a module you can switch off, replace or extend locally — hot-reloaded modules can also rewrite group-reply decisions, prompts, outgoing messages and per-chat model choice. Safe by default (master switch off, dry run on).

Agent skill for DeepSeek Harness: rewrites Russian text to remove 64 markers of AI generation (bureaucratese, calques, ChatGPT fingerprints), with a corpus-calibrated scanner, audit mode and author-voice calibration.

Adds one button beside the composer that rewrites the draft into a more complete prompt in place, with no preview step, plus undo, a stop action, and optional conversation context.

Puts the agent on QQ as a persona character through SnowLuma (OneBot v11): private and group chat, voice notes, stickers, Qzone diary, Bilibili browsing, song covers, image generation, long-term memory and mood. Every feature is a module you can switch off, replace or extend locally — hot-reloaded modules can also rewrite group-reply decisions, prompts, outgoing messages and per-chat model choice. Safe by default (master switch off, dry run on).

Rotates the dsh turn-status label through 1059 bilingual phrases with typewriter output, an animated rainbow gradient, danmaku, 12 toggleable theme packs, live placeholders and tab-title rotation. Two star packs ship disabled by default; the stargazer pack carries one phrase per stargazer, refreshed weekly by a workflow.

Let the AI connect to databases and write SQL for you.

Full-screen 550C boot intro for DSH: a 4-second simple cut and a 16-second rewrite sequence, skippable by click or Esc, with four phosphor palettes. The host half injects the opening frame while the document is still parsing, so the built-in loading card never shows; the desktop caption strip turns transparent, so those window buttons float on the animation.

Multi-device remote access for DeepSeek Harness: continue an active session from your phone, tablet, browser, or another computer over an end-to-end encrypted channel (Noise IK + adaptive relay/WebRTC transport), with device authorization, ApiProxy-only remote capabilities, and read-only file preview via dsh-file-viewer — no shell, remote desktop, or write access.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file. Every step the `MEMORY.md` index (the project store if there is one, plus a global store under `$DSH_HOME`) goes into the runtime context, so recall does not wait for a file read. The index has a hard cap, 200 lines / 25 KB by default, enforced by `ctx.tools.guard()`: a write that grows an over-cap index is denied, a rewrite that shrinks it passes. A read-only sidebar Memory page lists the notes by type. The plugin never writes memories on its own. An experimental companion mode adds note types for a persona's own life. The same store also works with Claude Code, Codex, Kiro and OpenClaw.

Let the model connect to databases and write SQL.

Let Claude Code or Codex do the thinking: understand the request, write a clear prompt for DeepSeek Harness to do the work, and review the result. dsh-baton runs your tests itself, lists what changed, and has a sub-agent check every requirement, so your main model only reads the result and decides. Codex waits in one call of up to 59 minutes, with no hook to trust and nothing to poll; you can change the request while it runs, and name the Harness model for a task. On big jobs it saves most of your plan's quota.