Project-level change routing and reuse governance for AI coding agents. Helps Codex and Claude Code find the right capability boundary, avoid duplicate implementations, respect write constraints, and calibrate routing decisions for large full-stack repositories.
Scopes MCP tool injection per workspace directory in the DeepSeek Harness: a session opened in a project sees only the MCP servers that project needs — removed from the model's tool list and refused at call time. Plus per-session switches in the composer to narrow or widen the session you are in, temporarily.
DSH plugin: agent-managed procedural memory — a skill_manage tool that lets the agent write, patch, disable and delete its own skills at runtime (user + project scope), with hot-reload and layered delete guards.
FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.
dsh-pm is the ChunSun × DeepSeek Harness reference plugin: an AI-native project-delivery loop driven by ChunSun. Requirements / Runs / Steps / acceptance scenarios & cases / work-memory, a session delivery panel, and 28 chunsun_* model tools — with the platform as the single source of truth. MIT.
A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.
See at a glance what DeepSeek did, and when. 📅 A beautiful usage calendar for DeepSeek Harness — every project and task's execution time, 🎡 in day / 7-day / month / year views, with recurring reminders, animations, and full theme awareness.✨
面向各类 AI 编程代理的保守代码修改守则 Skill，用于约束代理在已有项目中进行最小必要改动，避免无关重构，保护公共基础代码，并在支持深色模式的项目中优先使用动态颜色资源 An agent skill for keeping code changes small, scoped, and project-safe. Works with any AI coding tool that supports skills
