poteto@poteto

人很容易掉进一个坑：去微操你的 agent，而不是去修正塑造它行为的环境。 pstack 0.15.9 现在带了一个新的 /correct 技能：如果你老是因为同样的错误去纠正 agent，它会找出规律，然后用架构、类型和检查把问题修掉。 我喜欢把飞快涌进代码库的 commit 想象成一棵盆景树，想往哪长就往哪长，长得飞快。你要做的不是向混乱投降，而是用对的约束有意识地驯服它 0.15.9 还改进了： • /architect：现在包含如何设计对 agent 友好的架构的说明 • 新增 /benchmark-checklist 技能，基于 @brendangregg 的基准测试清单 这里有个 prompt，你可以丢给 grok bot，用 pstack 开始给代码库搭一个更好的架构： /poteto-mode 创建一个新的 Project agent 来重构并重新设计我的 repo 的架构，让它对 agent 更友好。它要同时用 /correct 和 /architect 技能去翻过去的 commit，找出 agent 最常踩的坑，不管是代码质量、性能还是 bug。如果相关，也可以用 /recall 技能找过去的对话作为上下文。它要做一个高层计划给我审。它也应该通过做原型来回答自己的开放问题，而不是推给我。带着有真实数据支撑的计划回来找我。等我批准计划后，用 stack 或 full autopilot playbook（问我要哪个）去执行

it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9 now ships a new /correct skill: if you keep correcting agents for the same mistakes, it finds the pattern and fixes it with architecture, types, and checks. i like to imagine that commits rapidly flowing into the codebase are like a bonsai tree rapidly growing in whatever direction it pleases. what you want to do is not to give in to the chaos, but tame it intentionally with the right constraints 0.15.9 also has improvements to: • /architect: now includes instructions on designing agent friendly architecture • a new /benchmark-checklist skill based on @brendangregg's benchmarking checklist here's a prompt you can give to grok bot to start architecting a better codebase with pstack: /poteto-mode create a new Project agent to refactor and rearchitect my repo so that our architecture is more agent friendly. it should use both the /correct and /architect skill to look through past commits and find the most common pitfalls that agents fall into, whether its with code quality, performance, or bugs. if relevant you can also use the /recall skill to find past conversations for context. it should make a high level plan for me to review. it should also answer its own open questions by prototyping rather than defer to me. come back to me with a plan backed by real data. once i approve the plan, use either the stack or full autopilot playbook (ask me which i want) to execute