プラグイン

Local-first HTML review and annotation workspace for coding agents: opens an isolated copy of a file in a browser editor, collects text edits, format changes and element/area comments, and returns a durable handoff the agent can claim and resolve.

“What should we build next?” There’s a skill for that.

External Agent control plane for Codex, Claude Code, Cursor Agent, and Antigravity adapters with settings and background job visibility.

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

Like Codex/Claude Code: drag any file or folder (no format limit) onto the DSH web page and its real absolute path is inserted into the composer instantly — no typing paths by hand. Workspace-first smart lookup, size checks, same-name picker, batch and clipboard paste support, Windows/macOS.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

CodeAct agent loop for the DeepSeek Harness: a persistent IPython session as the model's action space, with harness tools bridged in as a virtual `__dsh__.tools` module.

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

Data-provider MCP server for football: results, stats, odds, standings, form and head-to-head for 18 European leagues (1993-94 →) and 8 cup competitions, for any MCP client. Also a DeepSeek Harness (dsh) plugin.

Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

DSH plugin: auto-import local AI CLI conversations (Claude Code, Codex CLI, Cursor Agent) as real DSH sessions

DSH plugin: auto-upload conversation progress to Tencent IMA (daily note + Work knowledge base), mirroring the local Claude Code ima-upload workflow

Loads Claude-style plugins into DeepSeek Harness (dsh): discovers skills, commands and optional SessionStart hooks from Claude plugin directories, with hot command reload and uninstall cleanup.

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Cross-agent monitoring board for local AI agent sessions (cursor-ide, claude, codex, copilot, kimi and dsh itself) with session timelines, and message injection behind a default-off two-phase confirmation gate.

Scans MCP servers configured in Claude Code, Codex and CodeBuddy and probes real connectivity via stdio and streamable-http initialize handshakes, with enable/disable toggles and a /mcp control panel.

Subagent delegation provider that runs any Claude-compatible CLI binary pointed at by a configurable executablePath field.

Discovers Codex and Claude project directories and registers them as shared DeepSeek Harness workspaces.

Adds a model-aware reasoning effort slider with native and animated modes, light and dark palettes, and per-model colors.

Exposes the DSH dynamic-Cordis toolset to Claude Code over MCP (streamable HTTP on the existing web port, no new listener): ten tools to list, inspect, define, run, stop and permanently remove dynamic plugins in a live DSH session, with the same approval flow the GUI uses for packages that ship a client half. Bearer auth is mandatory — the token is configured on a DSH settings page, the endpoint answers 503 rather than serve without one, accepts loopback only and never emits CORS headers.

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

像 Claude Code 一样，DeepSeek Harness 现在也允许您自定义等待 AI 回复时的状态提示语。您可以根据不同轮次或场景，灵活替换占位文案，让开发助手在“思考”时也能传递您想要的信息。