dsh-ultramath：UltraMath 数学建模竞赛多 Agent 求解插件
dsh-ultramath 是面向数学建模竞赛的 DeepSeek Harness 多 Agent 求解插件，由 Andiii208 开发并采用 MIT 许可证。该插件通过原生 Agent 预设和技能包，将数模求解流程标准化为“读题、框架、推导、编码、验算、论文、审稿”七个阶段，解决了单轮提示词流程破碎的问题。 核心功能包括：提供 UltraMath 主控及数学家、工程师等四个单阶段角色预设；内置 33 篇模型库及论文模板，实现自包含安装，数据幂等同步至本地；设置严格的质量门禁，涵盖独立验算、审稿阻断项、盲评机制及学术诚信七类门控，任一违规即一票否决。此外，引入“数字冻结”机制确保论文数据与代
Read MoreOne Command to Launch Agent Teams: Getting Started with DeepSeek Harness Plugin dsh-agent-teams
dsh-agent-teams is a DeepSeek Harness workflow plugin maintained by NanmiCoder that transforms the current session into a leader, creating resumable sub-agent teams. It splits tasks based on dependencies and automatically schedules them, complemented by a web activity panel. This article verifies the installation commands, core capabilities, and usage boundaries based on the SkillHub directory page and the official GitHub README, making it suitable for DSH users who need multi-agent collaboration without building a custom workflow engine.
Read MoreUsing dsh_workflow to make DSH's one-time multi-Agent scheduling into a recoverable workflow
`dsh_workflow` is a DeepSeek Harness workflow plugin maintained by icetomoyo (MIT license, package name: `@dsh-external/workflow`). Instead of replacing DSH's front-end one-off workflow tool, it supplements a process layer that supports generation, saving, governance, observation and recovery: including named capsules, persistent run storage, pause and resume execution, and QuickJS isolated execution. This article verifies the installation commands, slash usage and permission boundaries in accordance with the community directory page and GitHub repository.
Read MoreCursor Multi-Agent Swarm Rebuilds SQLite for $1339: Planner/Worker Hierarchy Is the Economics of Agents
In July 2026, Cursor released the Agent Swarm research: relying solely on 835 pages of SQLite documentation, without source code or network access, the multi-agent swarm rebuilt SQLite in Rust and passed all sqllogictest tests. The total cost of the hybrid solution planned by Opus 4.8 plus executed by Composer 2.5 is approximately $1,339, while the cost of the single-model GPT-5.5 solution is about $10,565. This article sorts out the Planner/Worker layered architecture, the new harness coordination mechanism, experimental data and the open-source minisqlite product, and analyzes the cost advantage of the multi-agent approach of "using strong models for planning and weak models for execution" as well as its enlightenment to engineering practice.
Read MoreCursor 3 Multi-Agent Architecture: Planner/Worker Division Reduces Costs by Up to 15 Times
In July 2026, Cursor unveiled its upgraded Agent Swarm: the cutting-edge Planner model splits tasks and formulates plans, while the low-cost Composer 2.5 Worker is responsible for execution. In a closed benchmark where it replicated a database from scratch using only the SQLite manual, all configurations of the new architecture achieved a 100% pass rate in sqllogictest. The total cost of the Opus+Composer combination was approximately $1,339, nearly 15 times lower than the roughly $10,565 cost of a single GPT-5.5 model; the Opus configuration’s code volume was reduced by about 85% compared to the old Swarm. This article outlines the tree-shaped division of labor, self-developed VCS, failure mode governance and model economics, and notes that while this result represents a Cursor self-developed experiment, caution is still needed for its deployment in production.
Read More