team-memory / examples
AGENTS.md2 starsChanged 22 days agoMITView on GitHub
下面是一个典型项目 AGENTS.md 的样子:上半部分是普通的项目规则, 下半部分是 team-memory 的协议段落。协议段落由 skill 初始化时自动写入, 不装 skill 也可以手动粘进去。
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- team-digestSkill
- team-memorySkill
The file
Files
示例:某 Web 项目的 AGENTS.md(节选)
下面是一个典型项目 AGENTS.md 的样子:上半部分是普通的项目规则,
下半部分是 team-memory 的协议段落。协议段落由 skill 初始化时自动写入,
不装 skill 也可以手动粘进去。
# 项目规则
构建:mvn -q package;测试:mvn test(改动后必跑)。
src/core/ 目录重构前先问维护者。
所有金额字段一律用分(int)表示,禁止浮点。
## Agent 记忆协议(每个会话必做)
开工前:
1. 读 .memory/STATE.md(必读,很短)
2. 仅当任务需要历史细节时,再查 .memory/LOG.md 和 git log --oneline -15
收工前(阶段性工作结束):
1. 更新 .memory/STATE.md:完成项移出"正在做",更新"下一步"
2. 在 .memory/LOG.md 顶部追加一条记录(日期/agent 名/结论/改动文件/遗留),≤ 10 行
纪律:STATE.md 直接改写不追加;LOG.md 只追加;细节写进 commit message;
「正在做」两周没动就更新或回退;不把密钥、token 等敏感信息写入记忆文件。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
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.

