agentleFS
TTflyskyTTflysky/sirenhuisuo/AGENTS.md

sirenhuisuo

AGENTS.md4 starsChanged 3 months agoMITView on GitHub

太极要成为目标驱动、能观察、行动、验证、反思、重规划并主持团队的自主智能体平台,不是套着聊天界面的固定工作流。状态机、任务图和审批只能约束安全边界,不能替模型替用户预先规定所有项目的执行顺序。

The file

Files
AGENTS.md

太极开发上下文

最高目标

太极要成为目标驱动、能观察、行动、验证、反思、重规划并主持团队的自主智能体平台,不是套着聊天界面的固定工作流。状态机、任务图和审批只能约束安全边界,不能替模型替用户预先规定所有项目的执行顺序。

每次开始工作前

  1. 先读取 handoff.md 顶部的当前交接。
  2. 再读取 docs/TAIJI_V5_AUTONOMOUS_AGENT_ROADMAP.md 的总目标、边界和当前阶段。
  3. 检查当前改动与路线是否一致,记录本阶段目标、非目标和验证证据。
  4. 完成后把结果、测试、未决问题和下一步写回 handoff.md,不要只留在聊天里。

不可偏离的边界

  • 新聊天默认独立 conversation/project/workspace;只有用户明确要求继承才跨项目关联。
  • 任务、团队提案、成员、产物、文件、证据和记忆必须有稳定 ID 与项目边界。
  • 旧提案可替代、取消和审计,不能在用户纠正后继续作为有效审批。
  • 成员通知不等于完成;必须有真实子任务、回应、状态和证据。
  • 普通读取、搜索、写入和验证由智能体自主完成;敏感外部操作才请求用户确认。
  • 不为单个项目添加关键词特例,不用加长提示词冒充内核能力。

当前界面约束

  • 应用升级检查、下载和安装入口只在“设置 -> 诊断中心”,首页不放升级按钮。
  • 诊断中心的升级状态必须从真实 Electron 更新事件读取,并能恢复最近状态。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.