플러그인

Background stream listeners that wake the DeepSeek Harness agent — put a watch on a command or file and receive new lines as in-session notices. Ships a daemon host so a watcher can run unattended for weeks.

兰亭 CLI 命令工具化 + L0 守卫：记忆面 9 工具 + 质量面 6 工具（defineTool 注册，spawn venv _cli.py）+ 直写/直调守卫

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Turns coding into an RPG: finished turns, tool calls and completed todos earn XP, with 27+ achievement badges, levels, titles and seasons. Event-driven scoring with a pure-function engine — the work itself is the game.

Evidence-first guard: warns the agent when it claims success without a matching tool-execution record in recent context.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Multi-platform IM gateway for DSH: Feishu (Lark) WebSocket long connection (no public URL), WeCom AES-encrypted callbacks, and Telegram long polling — per-chat agent sessions, whitelist access, and a visual settings card in the web GUI.

Four GitHub workflow skills for PR triage, review feedback, GitHub Actions diagnosis, and safe draft-PR publishing, reusing existing DSH capabilities with gh/git fallbacks.

Folio (兰亭) @nyantused/folio-dsh-tools: 15 schema-validated tools (memory + quality gates) plus an L0 guard of the consulting document-generation engine; pair with @nyantused/folio-dsh-events for the full session protocol.

Folio (兰亭) @nyantused/folio-dsh-events: session-protocol events — auto session-start reminder + auto-save on session close; pair with @nyantused/folio-dsh-tools.

Multi-agent math problem-solving & verification framework: brainstorm → solver iteration → multi-verifier debate → Verified knowledge base, with checkpoint resume and manual/auto intervention (also ships as an agent preset).

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.

Overleaf-style LaTeX paper workbench: annotate any text in the rendered PDF and let a dsh agent revise the sources with compile checks and git history.

CloakBrowser-powered native browser tools with per-agent isolated sessions, bounded snapshots, ref-based interaction, screenshots, and safe routing.

Docker tools for agents: ps/images/logs/inspect/exec/manage with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

Evidence-bound negative-knowledge ledger: persists disproven paths (command_failed, file_missing) with their outcome and precondition evidence, then warns or blocks repeat attempts until the evidence changes.

Incognito sessions: a standalone ephemeral sub-agent with its own preset (no parent context) and full toolset, draggable floating window, burned to zero traces on close.

Per-subagent LLM provider/model selection with role templates.

Adds a Desktop card to the settings page that detects the DeepSeek Harness Desktop app and launches it with one click.

LiangShen (梁神) agent preset for the dsh web GUI: a two-phase anchored-standard preset.

Runs open-mcp-apps inside DSH: every MCP app gets its own sidebar container with a separate workspace, session, and App mode, an agent status strip under the app, and inline app rendering in ordinary chats.

다운로드 진행 패널: URL 다운로더, 에이전트 셸/SSH 전송 추적, 워크스페이스 블랙박스 파일 증가량 모니터링, 실시간 바이트/속도/퍼센트/예상 완료 시간을 보여주는 드래그 가능한 플로팅 패널로 표시

4개 모듈로 구성된 세션 컴패니언: 스마트 대화 내보내기(Markdown/PDF/JSON/PNG 롱 이미지, 개인정보 마스킹 및 일괄 ZIP), 템플릿 저장/가져오기가 가능한 컨텍스트 핸드오프 요약, API 비용 최적화(실시간 공식 가격, 피크/오프피크 스케줄링, 일/월 예산, 모델 라우팅), Ctrl+F 채팅 내 검색(CSS Custom Highlight API)을 포함한 전역 대화 검색

DeepSeek Harness의 서드파티 API가 낮음/중간/높음 등의 사고 강도를 지원하도록 하며, 서브에이전트 호출마다 모델을 선택할 수 있게 합니다.