DeepSeek Harness (DSH) plugin: edit sent messages and resend (stop an in-flight reply, edit, resend), plus branch-based edit / reroll / retry and a version timeline.
A manual Terminal tab for the DeepSeek Harness (dsh) web UI — run commands on the host machine, persistent cwd, sudo password prompt, command history.现在可以在web界面内直接执行命令行了
Tiered auto-review for DeepSeek Harness: static-rule safety net + LLM reviewer + human fallback — auto-allow safe actions, deny irreversible ones, ask a human for the rest.
Every skill you already have — Claude Code, Codex, Cursor, Gemini CLI — works in DSH: Agent Skills SKILL.md discovery, Tier-2 conversions, find_skill search, and a skills doctor
VS Code-style file explorer for DeepSeek Harness: sidebar file tree + multi-tab preview (code/image/PDF/audio/video/zip), search, sort, split view. Install: dsh plugin --profile web add github:ZrSiO4-y/dsh-explorer
DeepSeek Harness task-protection plugin: preflight scanner (catches missing inject declarations that crash the host), loop detection, recursion guard, and interruption awareness with a safe-restart helper. Never terminates tasks.
Stop AI coding agents from guessing. MCP server + Claude Code plugin that enforces intent alignment BEFORE coding: PRD → intent-confidence gate → Mermaid contracts (state machines / sequence diagrams / decision tables) → mechanical lint with zero CRITICAL → then code. Human-in-the-loop, file-persisted, zero-config.
DSH web plugin: check DeepSeek Harness updates from Settings (dsh --version vs npm latest/next) ｜ DSH Web 插件：在设置页自检 DeepSeek Harness 是否有新版本（本地版本 vs npm 最新版）
Turn-atomic message editing, retry, reroll and version-tree navigation for DeepSeek Harness conversations — the restart-safe successor to dsh-message-edit
Cross-session persistent cost ledger for DeepSeek Harness: logs every LLM token usage to SQLite and exposes record/query/budget tools. Built-in DeepSeek pricing, overridable via config.
