@mstar-harness/dsh
Morning Star harness dsh (DeepSeek Harness) cordis function plugin — in-process engine gates (status/dispatch/lease) with hard refusal channels.
57 results
Morning Star harness dsh (DeepSeek Harness) cordis function plugin — in-process engine gates (status/dispatch/lease) with hard refusal channels.
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
VCP 视觉通感协议插件 v2(官方 Slot API 版):AI 正文直接输出裸 HTML,前端以 conversation.chat.node 的 assistant-step 替换渲染器接入 + 复用 v1 渲染引擎(assets/vendor/vcp-engine-v1.js,流式/字体锁权/作用域化/KaTeX·Mermaid 零重写)渲染 vcp-root 卡片,零 bundle 补丁,兼容 rc 与 alpha 全版本线;内置 IO 热窗(可视+预取渲染、远离降级占位)防历史卡累积卡顿;内置开源精选字体 + 设计规范注入
Delivery quality gate for DeepSeek Harness: grill the requirements, test the implementation, prove the delivery, and gate the handoff with a deliverable/rework decision.
Multi-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
DeepSeek Harness (DSH) bundle porting Matt Pocock's 'Engineering for Real Engineers' + 'Productivity' Claude-Code skills (SKILL.md set) into a native DSH skill plugin. Same skill bodies, DSH skill discovery.
Feature-Sliced Design scaffold for building maintainable dsh (DeepSeek Harness) Cordis plugins: host three-layer slices, mirrored single-file client bundle, and a full engineering gate suite (lint, type-check, coverage, bundle verification).
ECC (227k-star operator system) skills for DeepSeek Harness — progressive port of 274 curated single-file skills (agentic engineering, evaluation, testing, patterns, vertical domains, docs). Adapted from affaan-m/ECC (MIT)
DSH prompt 工具箱:预制 + 自定义 prompt 模板,点击即插入当前对话输入框(v1 常规模式 + v1.1 智能模式悬浮卡) | Prompt toolbox for DeepSeek Harness: preset + custom prompt templates, one-click insert into the conversation.
A DeepSeek Harness skill plugin distilled from Qian Xuesen (钱学森)'s Engineering Cybernetics (《工程控制论》) — a methodology framework for projects, engineering and research.
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Web-switchable agent loop engine selection for the DeepSeek Harness - out-of-tree plugin (Claude Code / Codex / Pi / Kimi Code drivers) maintained by @kuun993, zero main-repo changes
DSH 插件配装引擎:任务 → 双检索(规则+LLM) → 组合评分(协同/冲突/成本/信任) → 配装建议。区别于目录/搜索:按任务自动配整套插件,含冲突检测与安装命令导出。
Reproducible multi-source release evidence for DeepSeek Harness
把中文场景描述转成 Anima/Anima Base 的英文自然语言 prompt:7 槽位、11 条 P 规则、负面三层、互斥自检;正负面分开输出直接复制,不输出 Params
Content-aware tool output compression for DeepSeek Harness.
One-click DSH background switcher backed by local Wallpaper Engine images/videos (WE Web API first, Steam workshop/myprojects directory scan fallback)
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
需求锻造:需求澄清、提示词提炼与经验沉淀。把模糊的编程需求锻造成可执行规格,并在每次任务完成后沉淀为可自动复用的个人提示词模板库。
上下文工程:按层级(规则文件→规格→源码→错误输出→对话历史)主动策划 agent 看到的信息,提升输出质量。受 addyosmani/agent-skills(88k★ MIT)启发。
按 Anima3 v3.0 模板把中文场景转为英文提示词:槽位顺序/互斥检查/自检/标签库(读取本地模板文件)
Cordis-native, evidence-driven full-stack engineering discipline for DeepSeek Harness agents