Plugins

DeepSeek Harness 的跨会话引用(cue)插件

Bridges session images to configurable vision providers and returns text-only analysis to eligible DeepSeek Harness model routes.

Local Markdown user and project memory for DSH: pinned preferences, keyword search, soft invalidation, history and archive, and JSON migration with preview, backup and rollback.

DeepSeek Harness plugin bundle: graphlint dead-code detection tools for agents (graphlint_query / graphlint_build / graphlint_config + graphlint skill).

Plugin store: npm authoritative catalog + awesome curated list (550+ plugins, 11 categories), dsh-field quality verification, official `dsh plugin add/remove` one-click install, sidebar + settings entry.

Per-route video input for DSH: native video on capable routes, a storyboard fallback for image-only routes, and explicit failures otherwise, without registering another provider.

Configurable template-based session titles with a type vocabulary, AGENTS naming guidance, historical backfill, and explicit rename and refresh tools.

AI 搜索模式：答疑 / 百科 / 浏览三模式，联网检索、广告过滤、AI 排序摘要与百科词条，支持结果语言、百科档位、浏览三指标权重、页面状态保留与搜索历史；兼容 dsh-better-sidebar（侧边栏页签多开、引擎栏、自定义搜索引擎）。

Adds permanent delete to the session menu: removes the session log files from disk, or deletes a whole workspace together with all of its sessions through the host registry. Also ships a /purge command. Unrelated to the prompt-patching dsh-purge plugins also listed here, but it uses the same dsh-purge row id and /purge command, so do not install both.

Mistral subscription for DeepSeek Harness: model route, multi-account failover, and a composer usage panel.

Inline diff cards for every edit, write and str_replace_editor call: old/new line numbers, character-level highlighting, 57-language detection with a red/green-safe syntax palette, a side-by-side viewer, Read-row line ranges, and a settings page for display style and highlighting.

DeepSeek Harness session stats dashboard: token usage, cost, composition, ranking and runtime health.

Todo plugin that records when each task is created and completed, with table, kanban, gantt and calendar views over the same data, categories, priority and type, @workspace-file links, JSON/CSV import and export, and a todo_time_log agent tool with /todo commands.

Redacts secrets, cookies and personal data in every model request at the host process undici dispatcher and restores the placeholders in the reply, so one interception covers every provider, adapters that plugins add included; per-kind actions mask / warn / block, an optional same-shape fake key, records written to disk by the day and a statistics card.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Local long-term memory for DSH sessions: archives older turns under context pressure, with a turn-summary index for faster turn lists, statistics, window probing and archive planning (rebuilt automatically when unavailable, with a manual full verification), four tiered hot-memory boards, project documents with enabled/disabled/archived filters and optional owner-controlled family sharing, project hot memory, dual user/assistant turn previews, memory families with editable names and root transfer, root-abdication recovery, orphan-family takeover, summary keyword locator with segment-level candidates and paging, manual injection, 20K segmented reads, and tag-related retrieval. Includes staged recall cues, automatic compatibility with older memory layouts, and post-install version verification. Off in each new session until you turn it on with `/palace on` or the Memory Palace tab. All data stays in the workspace.

DeepSeek Harness (DSH) plugin — connects DSH to JLCEDA Pro (EasyEDA Pro) via a local MCP bridge and draws schematics through the JLCEDA extension API.

Keep a multi-PR effort on one board you can trust at a glance: the hub agent keeps a tree of steps, each linked to its issue, PR, branch and worktree, through four board tools, and you see what is done, what is blocked and what needs you in a right-sidebar Board tab and a progress strip above the composer. Each board is one plain JSON file your scripts can read, and an optional drift command you configure flags steps whose status no longer matches their work.

Keep your automation tasks in files you can version and review: write each task's schedule, prompt, model, permission and working folder in YAML, JSON or JS, and DSH's own Schedule is kept exactly in line, creating, updating, disabling and deleting tasks within a second of a save. Each task runs in its own conversation, persistent or fresh per run; /automations syncs on demand and names any file mistake; and a sync that finds no tasks never wipes the Schedule.

Roleplay companion memory for DeepSeek Harness: per-conversation editable persona documents (1-100 weight per entry, AI may refine them in small story-driven steps), per-speaker favorability and bond in multi-person chats, active memories with AI-scored vectors, a nine-emotion table updated every turn, an AI self-evolution ledger, recent 48-hour transcript search, companion-style conversation compression, sleep-time compute that pre-guesses the next topics while a conversation is idle, per-conversation tone cards learned from its own past replies, a habit-hint small-model bridge that writes the user habits it extracts into this conversation memory, a date-archived local knowledge base with auto-packing by turns or tokens, and a unified integrations page that lists curated plugins and downloads their GitHub releases.

Ask about one sentence without derailing the chat: select a passage in a Web conversation, comment, and the session's own model answers in a small thread beside it while the main chat stays untouched. The replier can read the session, the working directory and, if you turn it on, the web, but changes nothing. Commented passages stay highlighted with a badge that shows unread replies, and Send to chat hands a thread to the agent when you want it acted on.

Show the model exactly which part you mean: select passages in a Web conversation and they go into your next message as composer chips, each with an optional note you can edit. Quoted passages stay highlighted until you send, hovering a chip shows the full quote, and the sent message shows each quote as a card.

Get back what you typed and walked away from: a new Web conversation you leave before sending never appears in the sidebar, so its draft is out of reach. This plugin lists those drafts above the composer of the next new conversation, newest first, with their workspace and time; Open takes you back with the text and chips in place, and Discard drops one, with Undo.

Lead-mode agent preset plus two runtime skills for the official Agent Teams runtime: a delegate-wait-verify working method, and a wrap-up digest that merges several members' output into one file. Ships no team runtime of its own.