Plugin

Track releases and stars of any public GitHub repository from inside dsh agents — no API key needed.

Surveys local code and GitHub/npm for reusable implementations before development, evaluates reuse versus rewrite, and checks architecture coupling.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Playwright MCP browser control for AI agents: drive a real, visible Chrome (navigate/click/type/snapshot + ~80 browser_* tools), with a live screenshot panel embedded in the GUI that refreshes after every action.

Give agents access to files on the machine where the browser runs: user authorizes a local directory via File System Access, tool calls relay over the plugin's own WebSocket; read-only compat mode for mobile/insecure contexts.

Database tools for agents: list/query/exec/schema across SQLite/MySQL/PostgreSQL, with lexer-grade read-only protection, row caps and an approval-gated write path.

Lets sandboxed agents reach the web through your local proxy: net_fetch fetches pages, net_proxy_status reports proxy status.

Browse every message you sent in the current session: full-history listing with newest-first sort, text filter, one-click copy, and jump to a message (auto-loads earlier history when the target is not yet loaded).

Organize DeepSeek Harness workspace sessions by renaming them as 类别｜主题 and reporting archive, rename, and review suggestions.

Bind your ChatGPT account via official OAuth and chat with ChatGPT models inside DSH, using your Plus/Pro subscription quota.

Diagnostica, sblocca e leggi le sessioni DSH: elenca le sessioni con lo stato dell'agente, leggi le conversazioni, diagnostica gli agenti bloccati, recuperali con cancel+keepInbox e invia messaggi ad altre sessioni

Collega gli agenti DeepSeek Harness a sessioni autenticate del Codex App Server

Esegui le estensioni Pi come plugin DeepSeek Harness con ambito agente

Un orchestratore di task multi-provider compatibile con Symphony e dashboard per DeepSeek Harness

Un plugin meta-agente nativo del modello per DeepSeek Harness: il modello sintetizza a runtime flussi di lavoro specifici per il task a partire da cinque pattern di workflow agentici (concatenazione di prompt, worker paralleli, router, supervisore, ciclo di valutazione) e coordina strumenti e subagent

Livello di compatibilità con Claude Code per DeepSeek Harness: carica skill/comandi/agenti .claude e installa i plugin dai marketplace di Claude Code come skill dsh native

Generazione PPTX stabile e modificabile per agenti IA — IR semantica in ingresso, DrawingML nativo in uscita

Pre-flight plugin-library check for DSH agents: task-type requests trigger a Top-K hint of suitable plugins with use_when/not_for capability declarations, making plugin usage predictable instead of opportunistic.

Read-only Claude Code compatibility bridge for DeepSeek Harness: Skills, Rules, command Hooks, and Agents from .claude as SSOT.

OpenSpec 流程的 Agent Team：面向实施阶段的多 Agent 工作流编排。