Plugins

Suggested next-step prompts under every finished agent turn in the DeepSeek Harness chat: the model proposes a few followup prompts at the end of each turn, they render as clickable cards under that turn, and clicking one sends it verbatim as your next message. Each card stays attached to the turn that produced it across reloads and restarts, the generation language can be chosen from 15 languages or follow the conversation, and a settings page in the dsh settings covers the language, how many suggestions per turn, the header and the in-app update check. Requires DeepSeek Harness 0.2.x (web profile) and Node.js 20+.

Real session deletion for DSH: trash by default, plan before delete, audit log, residue receipt

Visual review for the harness browser: pick any element to comment on it, adjust styles live with rollback, sketch on a free-form annotation canvas, and send everything as structured context attached to the next message, with a cropped screenshot per pin or the whole visible viewport composited with the drawings.

DSH Feishu Client. 1) Users (humans) access remote agents through the UI provided by this plugin; 2) The local DSH accesses remote agents by calling the tools provided by this plugin. Supported remote agents include but are not limited to DSH, OpenClaw, WorkBuddy, Weknora, etc.

A project lead for DeepSeek Harness. Opening a session with the dsh-master preset in a folder makes it that project's master: it splits your requests into tasks, dispatches them to member sessions over plugin-delivered messages, collects structured reports and stops at every gate for review. Members ask you only through the master, as clickable cards on a native side-panel board. A tagged devlog is pushed back into context before related files are touched. Guards keep agents off the plugin's state and git index, and a quiet patrol plus a safety-net schedule watch for stalls. One-click pause per project; all state stays local. Requires DSH 0.2.1 or 0.2.2, has only been tested on macOS, and the UI is Chinese-only.

Manage Claude Code, Codex and Grok CLIs inside dsh and dispatch tasks to them as headless subagents, with dsh models, skills and tools bridged into each task, resumable CLI subsessions, and a hierarchical task board in the right sidebar (the board tab requires the separate DSH-better-sidebar plugin; without it the tab is not registered).

PortWrench panel for DSH: view local listening ports, see which app owns each one, and close the target process tree. Requires PortWrench (Windows) to be installed and running.

Build presets for DSH Agents: package personas, prompts, skills, tools and runtime contexts into reusable capability bundles. Each task loads only the components it requires.

Adds next-message prediction, inline draft completion, and prompt optimization to the DSH composer, with a call budget, request stats, and glossary protection in Settings. A fork of Somnus678/dsh-input-assistant; both put their controls on the same composer, so do not install the two together.

System Duo for DeepSeek Harness. Make your agent think fast and slow: System One decision models triage, guard, shield, mask and check your agent loop beside System Two (vllm-sr/auto), with a free app.vllm-sr.ai key.

Show workflow stages and subagents on a timeline, configure model and concurrency for each stage, and reopen subagent conversations from the panel. Run names and stage settings persist under ~/.dsh.

Configurable serial agent-team workflows with a Manager, role Actors, an independent Judge, and a visual workflow editor.

Scans a repository with its bundled Python 3.12+ tools and scaffolds one Markdown outline per source directory, then publishes the index with a hash manifest that proves the documents match the code; the bundled reader verifies that manifest before serving an overview or one document. The project root needs a project_docs/ directory and a CLAUDE.md entry point.

Renders WorkBuddy SOUL, USER, MEMORY and topic Markdown files from an existing ~/.workbuddy/user-*-personal directory into the DeepSeek Harness system prompt, with a byte budget and a settings page; the profile's AGENTS.md loader must be disabled first.

Batch-manage DSH sessions: sidebar multi-select, a dashboard tree of main sessions and subagents with token/cache/context stats, bulk archive and cascade delete, and recall of ungrouped sessions into re-added workspaces.

Recap a session from dsh, Claude Code, Codex or OpenCode saved on this machine: the intent, key decisions and why, what changed, open threads and where to resume. Adds the session_recap tool, the /recap command and a right-sidebar panel that lists a project's sessions across agents. Uses the session's own model route, removes keys and tokens from transcripts before sending, and caches recaps locally. Needs python3 and zstd.

Delegates mechanical text work (translate, summarize, extract, classify, rewrite) to an Ollama-native or OpenAI-compatible endpoint by file path, so the source text never enters the main model's context. Registers local_transform, local_batch and local_health; per-workspace local-AI levels (none/light/default/high/max) add a local_worker subagent and a plan-only mode; an opt-in SlaveAgentTeams switch discovers mounted model routes, runs parallel child agents with node-level failover, and registers the endpoint chain as llm-pi-ai routes. Configured from the Web GUI; requires a reachable endpoint.

AI team with a pixel-art office showing each teammate's status and daily trail. A lead runs project sessions; daily caps per teammate. DSH Desktop, macOS only.

Claude Code's auto memory in DeepSeek Harness: the index in every request, and tools to write and edit it

Requirement-to-delivery workbench: paste or upload a requirement, and a plan-dispatch-verify loop delivers it with child agents and test evidence.

Bridge DSH sessions, prompts, tool calls and approvals to CodeIsland's macOS notch, including the latest reply on Stop.

Session-header environment and branch chips: Local git-switches the checkout; Worktree creates an isolated git worktree under .agents/worktrees, registers it as a workspace, and offers merge, squash, delete, and auto-cleanup.

Connects DSH to timestamped video reading, shared queues/history and Scroll personal Bilibili workflows through an existing Video Reader installation. Windows x64 only: install the core and set VIDEO_READER_ROOT before starting DSH; the bundle does not install Python, FFmpeg, models or Bilibili credentials.

Route table assigning provider, model, and reasoning effort to subagents by workspace directory prefix; supports global default policy and in-composer session popover.