플러그인

명세 산출물, 스킬, 명령어, 목표 기반 구현, 작업 진행 컨텍스트 추가

CBDC 권한 게이팅이 적용된 제한적 로컬 메모리: SQLite + FTS5 클레임, 설명 가능한 use/verify/ignore 판단이 포함된 범위 기반 회상과 전체 감사 추적, /memory 명령어, 호출당 최대 3개 클레임/1200자 삽입, 추가 모델 호출 없음

`session_export` 도구와 슬래시 명령으로 현재 세션을 이식 가능한 스키마 버전 관리 Markdown 및 JSON 파일로 내보내며, 크로스 플랫폼에 안전한 파일명을 사용합니다.

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens

Git-style conversation branching: adopt the current session as a branch, fork branches at any turn via /branch commands or the branch tab, and squash a branch back into another branch.

VSCode-style workbench shell for the DSH Web UI: activity bar, side bar, editor area, panel and status bar, with a registry service (ctx.workbench) for mounting panels, views and commands.

Developer tools panel for the DSH web UI: file browser with preview, edit, and path-only file mentions; multi-tab terminals with quick commands; Git panel with commit, push, pull, and branch switching; and background job management. UI ported from pi-web-ui.

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.

Unified IM channel for DeepSeek Harness: Feishu, Telegram, DingTalk, Slack, Discord — persistent conversations, true streaming replies, 40 MCP Feishu tools, slash commands, and an IM-bot status tab in the plugin settings.

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).

Discord-native remote controller for DeepSeek Harness: drive persisted coding-agent sessions from DMs, mention-gated guild channels, and threads, with slash commands, progress updates, approvals, structured questions, and image and text attachments.

Unified messaging gateway for DeepSeek Harness: 27 IM platforms (Telegram, QQ, WeChat, Discord, WhatsApp, Feishu and more) in one plugin, with QR scan-to-authorize, per-platform workspaces, slash commands, and a web setup dialog.

SSH remote ops for DSH: pair servers over SSH or a one-time-code remote-hostd, then run commands, manage background jobs, and read or write remote files with reviewable changes (host_pair/host_bash/host_jobs/host_read_file/host_write_file/host_review_changes).

DeepSeek Harness용 Claude Code 호환 레이어: .claude 스킬/명령어/에이전트를 로드하고, Claude Code 마켓플레이스의 플러그인을 네이티브 dsh 스킬로 설치

Claude Code 스타일 생명주기 훅: 모델 도구 호출 전후에 stdin으로 JSON 페이로드를 전달받아 설정된 셸 명령을 실행; pre-tool 명령이 0이 아닌 값으로 종료되면 호출을 차단

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.

Install suites from any Claude Code, Codex, Cursor, Kimi or agent-plugins.org git marketplace repo — skills, MCP servers, hooks and slash commands are injected into DSH sessions at runtime, with a market page in the Web GUI.

pi-style terminal UI for DeepSeek Harness (dsh) — pi-tui look & feel, dsh slash commands, GitHub light/dark themes, powerline footer

A 轨迹解读 (trajectory interpretation) tab that summarizes each user round — what was wanted, how the assistant thought and executed, files/commands/errors — via a rules engine plus optional LLM narrative; user messages stay verbatim.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

Mention a server with @ in a DeepSeek Harness session and run commands on it over SSH, behind a two-tier approval gate that fails closed.

Map dsh workspaces onto Discord — watch every session live, drive and steer agents, and reach the harness's own commands from anywhere, with no inbound port.