Plugins

Per-conversation persona / master prompt plugin: create, edit, switch and delete persona templates from the composer toolbar, with highest-priority system-prompt injection, fixed interaction guardrails, subagent inheritance, new-conversation default, and local JSON persistence.

Native DSH plugin that renders structured data as inline charts directly inside the conversation, with zero runtime dependencies.

A DeepSeek Harness (DSH) plugin that pings you on Windows the instant an agent operation awaits approval. DSH（DeepSeek Harness）插件：agent 操作需要审批的瞬间，在 Windows 上弹出带 DSH 黑鲸鱼 logo 的深色通知卡片。

Per-conversation subagent model selection for DeepSeek Harness Desktop.

跨平台 AI Skills 统一管理器：以 ~/.agents/skills 为中心技能库，通过系统符号链接把同一份技能一键安装/卸载到 Claude Code、Cursor、Codex、Gemini CLI、Trae、Windsurf 等多个 Agent 工具，仅展示本机已安装的平台，统一管理本地技能目录与只读平台展示。支持 Windows / macOS / Linux。DeepSeek Harness plugin.

Lenovo laptop diagnostics for DSH: battery health on macOS and Windows, plus Windows device, performance, storage, app and Wi-Fi checks, user-confirmed maintenance actions, and battery warranty, parts, store and appointment helpers.

密码本 for the DeepSeek Harness: an end-to-end encrypted personal secrets book on a private gist (age format, node:crypto only), with a browser page for people and value-free tools for the agent.

Automatic, bounded type context and edit diagnostics for DeepSeek Harness

Harness AI brand occupants for the dsh web client's brand slots plus the Harness theme

Self-contained vocabulary flashcards for DeepSeek Harness web sessions

Agent-curated long-horizon memory (ctx.memory) for DeepSeek Harness: durable project-scoped memory banks with a provider registry and a shipped local backend — a standalone plugin with no upstream harness changes required.

Per-session workspace visibility scopes for DeepSeek Harness.

Zero-config per-turn git checkpoints: after every completed agent turn in a git workspace, stages all changes into one tagged \[turnsnap] commit (serialized queue, sandbox-policy aware), so any turn is a rollback point.

Agentic git plumbing for DeepSeek Harness: the host ctx.git service (diff capture/parsing, hunk staging, commit/push/log over the subprocess seam) backing the commit and review tools in @hy-sde-org/dsh-tool-git — a standalone plugin with no upstream harne

Agentic browser plumbing for DeepSeek Harness: the host ctx.browser service (launch with stealth, CDP-attach, and a local relay + companion Chrome extension driving the user's own tabs) backing the browser tool in @hy-sde-org/dsh-tool-browser — a standalo

Deterministic fault injection, recovery, and side-effect auditing for DeepSeek Harness agents.

Sleev routing observability for DeepSeek Harness

DeepSeek Harness provider plugin that delegates ChatGPT subscription access and agent execution to the locally authenticated Codex app server.

Task dispatcher for DeepSeek Harness: use TickTick (滴答清单) 5️⃣AI as the daily task dispatcher — a cordis timer pulls today's due tasks each morning, writes them to the workspace task file, and notifies (flomo + macOS) so the agent works through them and wr

Exports the agent loop to GreptimeDB as OpenTelemetry traces, metrics and logs, with seven Grafana dashboards covering token usage, cost, session outcomes and per-turn latency.

AICQ End-to-end Encrypted Chat plugin for DeepSeek Harness (DSH) — registers aicq_* chat/friend/file/group tools and drives the agent from inbound AICQ messages

MySQL connector for DeepSeek Harness: configure multiple connections in the settings page with per-connection table allowlist and write permission, switch the active connection from the composer, and expose mysql_query / mysql_tables / mysql_execute tools to every agent preset.

Registers the local flowix-cli MCP server so the agent can search, read, create, and edit Flowix memos and mind-map artifacts.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.