实时扫描最新社区关于 DeepSeek Harness 发布的插件

Bring any file into the conversation — stashed to the workspace and referenced by path; zero type rejection

Dub video and audio into 10 languages with voice cloning, from a DeepSeek Harness agent — one tool call, local file or URL

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.

Interactive long-session background agents for DeepSeek Harness: start a durable continuable child agent from any session, watch its progress in the Web UI sidebar, message it any time, and interrupt it — all through the official subagent seam.

Hash-anchored read/edit/batch_edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

DSH book-to-skill plugin: a 5-stage long task (fetch → parse → understand → generate → install) with 3 human gates, host tools for the agent and a browser timeline panel

Playwright-backed browser automation bundle for DeepSeek Harness — drives the installed Microsoft Edge directly (no CDP endpoint, no MCP server) and exposes browser_* tools to the agent.

Browser automation for DeepSeek Harness: Playwright-powered open/click/type/screenshot/eval tools so the agent can drive real web pages.

Shared real browser capability for DeepSeek Harness: a visible browser the human watches and can take over, driven by the agent over CDP (snapshot/execute/content/tab management); host-side seam, provider, and browser_* tools

A personal DSH browser plugin: persistent profile, visible window, human-in-the-loop login, and safe agent browser tools.

browser-use style browser automation for DeepSeek Harness: drives a dedicated Google Chrome instance (independent profile, cookie persistence) via playwright-core — fine-grained browser tools, autonomous tasks with an internal model loop, scheduled runs, dangerous-action confirmation, captcha hand-off, and per-step screenshots.

Transient /btw side questions for DeepSeek Harness: immediate while the main agent is busy, context-sharing, tool-free, one-shot, cache-aware, and invisible to the main session catalog.

Cache-prefix stabilization and evidence-based cache metrics for DeepSeek Harness

DeepSeek Harness Doctor: read-only DSH runtime capability diagnostics for tools, models, skills, workspaces, sessions, plugins, and MCP troubleshooting

DeepSeek Harness profile bundle: Chrome DevTools MCP integration — drives one real Chrome browser through chrome-devtools-mcp via @deepseek-ai/dsh-mcp-client

Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 70 models from one wallet. No accounts, no API keys.

DSH Web 轨迹分类视图插件：「分类」标签页 = 左上角「合计」动作统计（写入/读取/删除/下载/命令/搜索/子代理/其他工具/消息/压缩）+ 思维导图画布（一次一个问题，问题画布标签切换，问题 → 方案 → 工具调用，节点可拖动、线条带惯性）。点击问题/方案收起展开子流程，点击工具查看「做了什么/输出日志/修改内容/参数/错误」。中文分类、中英文工具名匹配，保留原始「轨迹」流程列表。纯浏览器端聚合，零模型请求、零额外 token 消耗。

Native CloakBrowser tools for DeepSeek Harness with per-agent browser sessions and snapshot references.

Text-first browser and background macOS computer use for DSH

Model-agnostic Computer Use capability for DeepSeek Harness: isolated browser first, provider-neutral observation, text planner + third-party vision perception.

A Symphony-compatible issue orchestrator and dashboard for DeepSeek Harness

数据管理 + AI 管家：统一本地数据看板（来源/位置/摘要、回收站删除），并给智能体装上看懂与清理数据的 ledger_* 工具

Transparent image preprocessing route for DeepSeek Harness