dsh-agent-teams
NanmiCoderAgentTeams plugin for DeepSeek Harness
DSH workflow plugins chain steps together in DeepSeek Harness — hooks that fire on events, scheduled runs, multi-stage pipelines, and repeatable task templates.
Repositories with traceable evidence of a DeepSeek Harness relationship. They have not been reviewed, install tested, or security checked — the signal below each one is the whole of what the registry currently knows.
AgentTeams plugin for DeepSeek Harness
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
Safe automatic permissions for DeepSeek Harness.
把Claude Code的UltraCode模式带给DSH,把 DSH 的一次性多 Agent 调度,升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层
A Skill-driven Harness/Loop Engineering Workflow Agent Plugin
DSH 自动化插件:让 Coding 任务按计划在全新 Agent Session 中运行,并由用户或 Agent 创建和管理定时任务。 / Run coding tasks in fresh Agent sessions and manage schedules from DSH Web or an Agent.
为 DeepSeek Harness 提供电脑控制插件:新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入(目前支持macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.
DeepSeek Harness plugin for complete Blender 3D modeling, reconstruction, rendering, validation, and export workflows
Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.
一种类似MC Fabric的hook处理器
Adaptive deep-research orchestrator plugin for DeepSeek Harness (official workflow engine, cybernetics/information-theory design)
可配置子代理 profile 系统,单一 subagent 工具 + profile 参数,含 Web UI 设置/实时进度/子代理树 | Configurable subagent profile system: single subagent tool + profile param, with Web UI settings/real-time progress/subagent tree
AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision workflow into your own agent: OpenClaw, Claude Code, Codex, or DeepSeek Harness.
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
Self-control guard plugin for DeepSeek Harness host exit and restart workflows.
【编排模式】为 DeepSeek Harness 提供多智能体编排模式:主智能体分解分派、worker 全网格互通,支持逐 worker 指定模型与思考强度
DSH 插件:定时循环(/loop 命令 + loop 工具 + 活动状态条)。官方 bundle 插件,dsh plugin --profile web add 安装
Lightweight requirement alignment for DeepSeek Harness — align important decisions before execution without a full spec workflow.
发现问题(checkup) → 修复交付(fix) → 质量复查(review) 的对抗式闭环插件:基于官方 workflow 引擎的检查/修复/复查工具集
为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档,危险或不确定操作仍转人工审批。An auto-approval permission preset between workspace-write and full access for DeepSeek Harness.
为 DeepSeek Harness(DSH)提供的细粒度权限控制插件
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
DeepSeek Harness原生中文文本人工智能痕迹消除与多重审核对抗工作流
A simple popup that can quickly show when Deepseek has finished thinking or is requesting permission during split-screen.
Interactive long-session background agents for DeepSeek Harness: start a durable continuable child agent, watch its progress in the Web UI sidebar, message it any time, and interrupt it - all through the official subagent seam.
DeepSeek Harness (DSH) plugin — a subagent_with_model tool plus a live multi-panel subagent viewer.
Finance and accounting workflows for DeepSeek Harness, adapted from Anthropic Finance
A model-native meta-agent plugin for DeepSeek Harness that uses the underlying model’s reasoning and planning capabilities to synthesize task-specific workflows at runtime and coordinate tools and subagents.
Subagent Director: per-subagent LLM provider/model selection with role templates for DeepSeek Harness (dsh plugin)
Backup DeepSeek Harness user data with one command: /backup, scheduled auto-backup, sha256 checksums and rotation. 一键备份 DSH 数据,支持定时自动备份。
Multi-agent orchestration for DeepSeek Harness
Shared lifecycle admission protocol and reference policy kernel for DeepSeek Harness subagents.
DSH plugin: auto-rotating UI wallpapers for DeepSeek Harness with crossfade transitions, a built-in SVG wallpaper set, and readability controls (frosted glass, dimming, text shadow). Install via dsh plugin add.DSH 壁纸轮换插件:定时轮换应用背景壁纸(交叉淡化动效)、内置壁纸集、毛玻璃/压暗/文字阴影可读性调节。dsh plugin add 一键安装。
DeepSeek Harness subagent delegation enhancement
DSH (DeepSeek Harness) 专家模式 agent preset — 首席协调官 + 11 位领域专家子代理 Expert-mode preset for DeepSeek Harness
A reusable DeepSeek Harness bundle for evidence-driven memory, orchestration, benchmark operations, and plugin release workflows.
Local multi-agent collaboration relay for DeepSeek Harness — HMAC-authenticated loopback message broker for dsh, Codex, Claude Code & Hermes.
Trusted Auto: a middle permission tier for DeepSeek Harness between workspace-write and danger-full-access, auto-approving harmless commands and trusted-area targets
DeepSeek Harness 多智能体编排模式 — 灵感来自 oh-my-opencode-slim
画布式多智能体协作插件 | Canvas-based multi-agent cooperation plugin for DeepSeek Harness
Persistent live DAG visualization for DeepSeek Harness subagents and workflows
Local-first full-duplex voice for DeepSeek Harness, orchestrated by Muxiva
Trust pipeline for deepseek-harness plugins: deterministic static scan (11 rules) + LLM-driven audit protocol + two-part scorecard, with optional runtime guard (T1 sentinel / T2 fs & child_process hooks) and honeypot decoys. Monitor-and-alert only — vet never blocks or kills on its own.
DeepSeek Harness(DSH)定时任务 + 状态监控插件:按 cron 时间表自动触发 Agent 执行任务,/status 与设置页仪表盘查看系统与 harness 综合状态。Scheduled tasks (cron) + status monitoring plugin for DeepSeek Harness.
Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.
小说创作模式:一个统筹队长统领全局,5 个专职子代理各司其职——架构世界、策划剧情、管理人物、执笔写文、质检复核——协同写作。
Captain plugin for DeepSeek Harness: GPT planning, DeepSeek workers, independent review, adaptive multi-agent orchestration
Scheduled tasks plugin for DeepSeek Harness Web Profile
Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents.
DSH 定时任务插件:标准 cron 5 段式调度 + shell/通知触发动作 + Web 侧边栏管理面板。by MyDSH 社区 (mydsh.dev)
DSH 插件:开发前自动进入 plan mode(plan-first development workflow)
dsh-delegate: model-aware subagent delegation for DeepSeek Harness — per-call models, depends_on dependency gating, per-child personas, a durable run roster, audit events, and conversation-flow tool cards. | 给 DeepSeek Harness 的子代理委派加上:按次选模型、依赖门控、角色人设、任务花名册。
100% AI-native product delivery workflow plugin for DeepSeek Harness: full product-to-release pipeline (research → PRD → OpenSpec → parallel multi-agent → review loops → tests → release audit) with loop closure. 产品交付工作流插件:从产品到发布全流程,自带闭环,100% AI 原生,睡前启动醒来收货。
DeepSeek Harness subagent delegation enhancement
DeepSeek Harness adapter for the public Falsify CLI. Adjudicator receipt, not a second-opinion workflow.
DSH auto-and-safety permission preset: full file access but no delete without user approval
Multi-CoT plugin for DeepSeek Harness: multi-sampled test-time compute, internal voting, and a plan/execute/review workflow
把 DeepSeek Harness 完整搬进 JetBrains IDE:智能体对话、工具审批、目标与计划、子智能体与 Workflow。装插件、配一次 API Key,即可对话。DeepSeek Harness — agent chat, tool approvals, goals, subagents & workflows — embedded in your JetBrains IDE. Install, set your API key once, and chat.
分组工作流看板插件:每个分好组的 workflow 在 DSH Web GUI 有独立标签页实时展示状态/阶段/子agent/日志