Plugins

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

OrgX MCP tools, Work Ledger access, and a Sovereign Execution peer for DeepSeek Harness.

Record & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use

Control your DeepSeek Harness agent from Feishu/Lark: DM a task, a DSH agent runs it with your LLM, and the answer comes back to the chat. Image understanding, image generation round-trip, feishu_send tools, resident launcher. Powered by lark-cli.

Developer quick-reference toolbox for DSH: 12 themed categories (195 entries) plus zero-dependency tools — regex tester, JSON formatter, timestamp converter, Base64/URL codec, cron generator and line diff, in a searchable settings panel.

DeepSeek Harness community Bundle for the BeforeDone evidence gate

Sparkles finance evidence tools with a host-native DeepSeek Harness shell and browser client

Delegate work to external coding agents (Claude Code / Codex CLI / Grok CLI) from DeepSeek Harness: a model-facing harness_call tool, @claude/@codex/@grok mentions, live progress cards with a thinking/tool timeline, and a details side panel.

Git development workbench for DeepSeek Harness: captures branch, status, worktrees, stashes and recent commits, with commands, tools and a settings UI.

A friendly status and context-pressure companion for DeepSeek Harness Web

Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness

A DeepL-style translation surface for dsh: replaces the shell's root frame with a two-pane translator driven by a tool-less agent preset, keeping the shipped settings panel (models, providers, plugins) intact

Project knowledge base plugin for DeepSeek Harness: Open Knowledge Format (OKF) bundles per project, agent search/read tools, a Web UI browser/editor, and a bundled OKF authoring skill

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).

dsh plugin: launch the dsh-desktop Windows shell (region screenshot, tray, session manager) from the DSH conversation via a desktop_launch tool.

DeepSeek Harness bundle that exposes Model Context Protocol (MCP) servers — stdio, streamable HTTP and legacy SSE — as native Harness tools, with a settings UI, live status, auto-reconnect, and backup/restore via local files or WebDAV.

Typed, read-only DeepSeek Harness tools for installed Kungfu Projects and Work.

Browser-automation tools for DeepSeek Harness (dsh): Chromium via playwright-core behind a security-first navigation policy re-checked on every action

Data-loss-prevention plugin for DeepSeek Harness: a non-configurable tool guard floor, tool-result redaction, and fail-closed telemetry redaction

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.