Fluxos e automação

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Agent teams: spawn named long-lived teammates, coordinate them with a shared task list, member mailbox, and virtual workspaces, and watch the team live in a team-room tab.

Calendar and hierarchical task workbench: AI-assisted intake clarification, consultation, decomposition, execution with user acceptance, and review, plus reminders and per-task AI session workspaces.

Engineering workflow agent preset for dsh: five gated phases (requirements clarification, plan approval, TDD, parallel subagents, verified finishing) with six workflow skills adapted from obra/superpowers.

TaskSwarm (蜂群, enxame de tarefas) — plugin de orquestração de tarefas multiagente no DeepSeek Harness: execução paralela em waves/lanes, isolamento via git worktree, pacotes de tarefas e revisão entre modelos, recuperação após falhas

Automação de navegador para o DeepSeek Harness: ferramentas open/click/type/screenshot/eval baseadas em Playwright, para que o agente possa controlar páginas web reais

Camada independente de aceitação, somente leitura: cria um verificador somente leitura antes do fechamento de cada turno de nível superior e redireciona lacunas não aprovadas de volta ao agente

Agentes agendados via cron: execute um prompt em um horário programado e receba o resumo onde você já está, com padrões de segurança para sobreposição/execução perdida/timeout

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

Browser Use bridge for DeepSeek Harness: let your dsh agent run real web tasks (open pages, click, type, fill forms, extract data) through the Browser Use Cloud API.

催办风险灯（Urge Risk Light）— 根据流程节点停留时间与 SLA 对比批量判定红/黄/绿催办风险的 DeepSeek Harness 工具插件，含结果卡片与右下角悬浮组件

Typed, read-only DeepSeek Harness tools for installed Kungfu Projects and Work.

Browser-automation tools for DeepSeek Harness (dsh): Chromium via playwright-core behind a security-first navigation policy re-checked on every action

A single project operating map for DeepSeek Harness.

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.

Installs two selectable Agent Presets: a shell-restricted general-purpose agent and a repository-focused coding agent.

Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Interactive canvas for visualizing Agent, Subagent, Workflow, Phase, and tool relationships in DSH Web.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Disk-persisted execution planning for DSH: milestone/step state machines, dependency gating, an audit event stream, and a deterministic completion gate via dsh tools, CLI, or skill.

Collects primary frontier-AI sources and gates reproduction with evidence, rubrics, rollback, and manifests.

Kimi-Code-style swarm: batch-parallel subagent dispatch with adaptive scheduling, a /swarm command, and in-chat live progress rows.

Main-brain orchestration preset: delegation-first persona, root-session execution gate, and portable AI-LAW rule skill.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.