플러그인

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

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

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.

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.

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

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

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

LLM 요청이 계속 실패할 때(재시도 소진, 인증, 할당량, 속도 제한) DeepSeek Harness 에이전트를 위한 자동 프로바이더/모델 폴백 체인입니다.

dsh-subagent-tools를 확장해 서브에이전트별 cwd를 호출마다 지정 가능하게 하며, 필요한 두 개의 인프로세스 provider 패치를 함께 제공

핸드오프 노트가 포함된 세션 간 작업 큐: 세션과 서브에이전트가 공유 파일 기반 큐에서 작업을 push/claim/complete/cancel하고, 다음 담당자를 위한 핸드오프 요약을 남김

Compares coding agents in isolated Git worktrees with deterministic validation, scoring, and explicit winner application.

Feishu (Lark) private-chat frontend for DeepSeek Harness: drive, monitor, and approve local agents from Feishu, sharing sessions with the Web GUI

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.

Digimon-style raising game: hatch an egg that feeds on real work (turns, tool calls, errors) and evolves along four branching lines shaped by how you work; zero tokens, invisible to the model.

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.