subagent 96

AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.

DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress

baro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar

Deep reading & summarization for DSH: books/papers/videos/web → structured Markdown notes (Obsidian / Logseq / static sites). Plugin parsers, MapReduce deep-read, JSON Schema-constrained sub-tasks.

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).

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness: continuable children, durable session recovery, per-role product permissions, delegation with a permission ceiling, and a declarative role library.

oh-my-opencode-slim-style specialist subagent delegation preset for DeepSeek Harness — declarative agent preset with orchestrator + six specialist roles, background-first delegation, JSON-driven configuration.

DeepSeek Harness plugin: per-event task-completion and attention sounds for turn-end / approval / question / plan-review / goal-blocked / task-failure, each with its own sound (built-in synth, local audio file) and volume, with a separate subagent channel

dsh「专家团」bundle：一句自然语言组建角色化多智能体「数字员工」团队，按九阶段门控流水线协作交付，实现者直接改代码并产出持久工件；带 live 团队浮层。 · Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out.

OMD 理念的 DeepSeek Harness 插件：模式能力边界 + 按模式配模型 + tier 差异化子代理委派

DeepSeek Harness Web plugin for visualizing, arranging, branching, merging, and summarizing AI agent sessions on an interactive graph canvas

DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph

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

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

dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch and ask_agent follow-ups

DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, test engineer, code engineer, QA, code reviewer, security reviewer, doc reviewer) that talk through files on disk, with the PM as the

DeepSeek Harness 子 Agent 派发插件：按任务为子代理选模型、推理强度与工具范围，常用组合存成命名方案随时复用；内置安全检查、成本估算与节省分析、完整决策台账。

Agent-office dashboard for DeepSeek Harness (DSH): a 6-column sprite office visualizing workspaces, sessions, token usage and subagents — with built-in Agent Mail, Feishu/Lark message feed, meeting schedules, transcripts and an office log tab. One screen

Named subagent library for DeepSeek Harness: a directory-backed roster of role subagents (one YAML file per agent: model + persona + tool filter), exposed to every session through the list_subagents and delegate tools, a /subagent command, and a Settings

为 DeepSeek Harness 子代理配置默认模型：多模型顺序/随机分配、跨供应商连接失败故障转移，并在轨迹/对话视图显示当前供应商与模型，同时以一行真实提示词把当前路由注入子代理上下文。

DeepSeek Harness 智能看板：任务卡片 + 一次性 Worker/Verifier 派发 + 依赖调度 + 管线分档 + Team 模式（歧义上报主窗口裁决）

A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.

ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state

team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.

DeepSeek Harness agent presets whose leader does no work itself: every non-management tool call is denied at the harness boundary and the task goes to a subagent instead, after a one-time research pass over the available subagent models and a per-task mod

Use AItelier as a subagent from DeepSeek Harness: generate, edit, run, export and import SkillFlow pipelines. Client only — requires a running AItelier backend (Docker; see README).

会话生命周期管理：one-shot 完成归档/删除、可续与主会话闲置归档、容量保底、连带清理 projcache——全类型生命周期管理。

DSH plugin: Sisyphus agent orchestration — star topology, single-line blocking, 7 specialist sub-agents (Hermes/Explore/Librarian/Looker/Hephaestus/Prometheus/Oracle) with per-type model binding, go_work/continue/need_help/forward communication tools, Web

Custom reusable Subagent Definitions with a Settings page and one delegate_agent tool for DeepSeek Harness

Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.

DSH Native Cross-Session Collaboration, In-Process Agent Call, and Public Blackboard Plugin

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

DSH Native Cross-Session Collaboration, In-Process Session Call, and Public Blackboard Plugin

Self-organizing multi-agent clusters for DeepSeek Harness: N agents coordinate through a shared append-only log with no orchestrator — as a frozen-snapshot ring/mesh/swarm cluster, or as a blackboard each agent reads and writes on its own schedule. Port o

DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress

AgentTeams 多智能体团队协作（DeepSeek Harness 插件）：自然语言组队、成员与任务依赖 DAG、信箱通信、右侧栏树状监测 —— 上游 NanmiCoder/dsh-agent-teams 的补充版，新增自定义美术目录、十七厂商头像（十个有厂商 × 岗位全套）与厂商商标徽标。

Live parallel execution graph for DeepSeek Harness

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Model-routed subagent delegation for DeepSeek Harness: a `subagent_model` tool with per-call provider/model/max_tokens overrides and a built-in `model: "auto"` routing policy (anchored to the parent's own model by default; task-tier upgrades, failure esca

SOP-driven business Agent Teams for DeepSeek Harness: configurable captain/member agents, human- or agent-defined SOP workflows (nodes, dependencies, quality gates, manual gates), event-driven task scheduling, and a web dashboard (SOP canvas, run board, a

Expert Orchestrator — multi-agent orchestration agent preset for DeepSeek Harness (dsh): triage → PM planning → delegate implementation to domain experts via a merged roster (summon_expert), dependency-DAG taskboard, file message bus, tiered delivery gate

DSH plugin: safe auto-continue-once recovery for native continuable subagents that end with explicit max-tokens termination. No timers, no polling, no private APIs.

DSH Web 任务面板插件：把需求、队列、子 agent 执行、自动复核、验收返工和定时执行做成一个可视化闭环。

Multitask 减震器模式（Agent preset）：主对话只做需求理解、任务下发与结果汇总，读文件/跑命令/构建/搜索等污染性工作全部下放子代理。含协调者窄工具面、四类 worker、只读元数据工具 file_info 与子代理危险操作的审批闸门，零 DSH 源码改动。

并行多角色代码评审小队：/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理（每人可单独指定模型与思考强度），汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped repo

Capability-aware vision for DeepSeek Harness: native image input for multimodal models, with an isolated one-shot vision-route fallback for text-only models.

File-defined subagent roles for DeepSeek Harness: project (.dsh/roles) and global (~/.dsh/roles) role files, a compact role catalog, real per-role tool filtering, and a per-role tool-call budget.

Annotate every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.

DSH Graph Job 多 Subagent 任务图编排器