Long tasks shouldn't cost like they need a frontier model. Cheap-model long-task engine: reliability in structure (disk state machine + mechanical gates + T3 zero-prose dispatch + multi-brain audit), not in model strength. Pure Python stdlib. DSH skill.
A DeepSeek Harness (dsh) plugin that renders a live dependency-topology graph of the running agent — plugin/service nodes, depends-on / provides / contains / disabled edges, and fiber lifecycle phases.
DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.
Bridge DeepSeek Harness into Feishu / Lark—drive your local coding agent from mobile, group chats, and topics with conversations, tasks, cards, and project workspaces in one collaborative flow.
Deep Structural Analysis — a multi-perspective structural analysis skill for complex social, economic, philosophical, and systemic questions. 16 lenses, 10 structural tools, an attack-loop protocol against analytical priors. Behavior-verified from real usage. MIT licensed.深度结构分析——面向复杂社会、哲学与系统性问题的多学科结构分析技能。16 透镜、10 结构工具、攻击循环协议对抗分析先验。基于实战行为验证。MIT许可。
