Plugins

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Planner/executor delegation with named roles: a strong planner steers, disposable executor sub-agents (per-role routes and prompts) implement. Default role plus per-delegation override, a global reasoning-effort knob in the composer chip, and a settings page for role management.

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

Type @ in the composer to reference another conversation: pick a historical session and inject its compacted context into the current prompt.

WeChat Reading (WeRead) multi-target export for DeepSeek Harness via the official Skills API gateway: browse your bookshelf, export highlights & thoughts to flomo, a local Markdown file, or Notion, optionally reworked by a configurable LLM prompt.

Conversation-map rail down the left edge of the transcript: one tick per user turn, read from the full session log on the host rather than from the rendered page, so long sessions are covered end to end. Hovering fans the neighbouring ticks open by pixel distance and floats a scrollable preview of that turn prompt and its last reply; clicking scrolls to the turn, paging older history in first when it has not been rendered yet; the tick for the visible turn stays highlighted while you scroll.

Adds a Codex-style message navigation rail for quickly locating earlier prompts in long DeepSeek Harness Web UI conversations.

一个可直接链接到 DeepSeek Harness（DSH）Web profile 的独立安全检查插件。在安装或使用不受信任的 Skill 前，先执行浏览器本地粗检，再由用户决定是否调用 DSH 已配置的大模型进行结构化复核。

Appends ambiguity-handling rules to the dsh system prompt so the agent asks clarifying options before guessing.

Injects live time, weather, location, battery, and device context into the DSH system prompt, with a bilingual settings page.

Condenses DSH session titles from a full sentence into a short verb-free phrase, aiming for under five words.

Web composer enhancement: recalls sent prompts across sessions with ArrowUp/ArrowDown, searches them with Ctrl+R, restores rich drafts, and opens a docked /btw or /side conversation.

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

Adds prompt optimization, cancellation, and undo controls to the DeepSeek Harness composer.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

Conversation header badge showing the DeepSeek Harness version, checking npm for the latest release and prompting upgrades.

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

Task-to-skill pairing meta-skill with a laziness ladder for minimal loading, a user-editable routing table, and a quarantine, SkillSpector scan, human-approval install flow.

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.

Rewrites each request against a learned prompt profile and automatically updates habits, anti-hallucination rules, and learning records.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.