subagent 39

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

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

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 (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

Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval

DeepSeek Harness bundle: oh-my-opencode-slim style Orchestrator agent preset with model-pinned specialist subagents (explorer/oracle/librarian/designer/fixer/council).

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

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

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

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.

Dispatch one-shot subtasks to derived subagents with per-task overrides (preset/model/provider/reasoningEffort/persona/tool whitelist), a runtime-derived cost guard, a subagent-profiles service, observability metadata, and a web-GUI settings page plus a d

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

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.

Configure default model routes for DeepSeek Harness subagents, with single-model, round-robin, random, and per-route reasoning-effort options.

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

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

Live parallel execution graph for DeepSeek Harness

AgentTeams for DeepSeek Harness: durable teammates, task DAG, read-only role isolation

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

A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.

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

DeepSeek Harness bundle that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.

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

Named subagent library for DeepSeek Harness: a settings-driven roster of role subagents (model + persona + tool filter), exposed to every session through the list_subagents and delegate tools, a /subagent command, and a Settings page.

dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.

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。

Declarative task-DAG orchestration plugin for DeepSeek Harness workflows

Vision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool

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

Deterministic fault injection, recovery, and side-effect auditing for DeepSeek Harness agents.

Controlled one-shot executor subagents with persona, tool allowlist, timeout and cancellation. 受控一次性执行层子代理（persona + 工具白名单 + 超时取消）

DeepSeek Harness plugin: subagents with their own model and reasoning effort 闂?GUI settings card (plugin-owned config file), config defaults, and a parent-model-controlled delegation tool (subagent_select).

GUI settings card for dsh-subagent-effort: choose the subagent model and reasoning effort in Settings 鈥?no config files to edit.

DSH plugin: deliver the real failure reason (e.g. RATE_LIMIT 429) to the parent agent when a background subagent fails, instead of an empty "Its closing message:"

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