跳转至

dsh-plans

类型 工作流 分类 工作流
星数 ⭐11 状态 ✅ 活跃
能力 workflow, multi-agent 更新时间 2026-08-14

📖 项目简介

Human-in-the-loop planning preset for the [DeepSeek Harness] (DSH): researched, refined Markdown plans before any code changes, then goal-driven execution after an explicit handoff. Turn a rough repository-change request into a traceable plan under ./dsh-plans/, refine that plan with reviewer or criticizer subagent rounds, and hand the accepted plan to a persistent DSH goal that drives implementation until the plan's Verifier Checklist passes. Everything runs on DSH's native mechanisms — `ask_

✨ 核心特性

  • Per workspace, the language setting is asked once before the first planning question, and persisted.
  • Per role, the model for reviewer / criticizer / executor is asked once, at that role's first actual use, and persisted. Reviewer and critici
  • One planning question at a time; the final scope confirmation gates PLAN_v1.md.
  • After every plan version, a refinement mode question — a reviewer or criticizer never runs without it.

📦 安装

mkdir -p ~/.dsh/.agent-presets
git clone https://github.com/Optim-Agent/dsh-plans.git ~/.dsh/.agent-presets/dsh-plans

🚀 快速开始

Create a plan for <your change>

🔗 链接