init-long-run
Skill92 starsChanged 55 days agoMITView on GitHub
用户要把需求拆成可跨会话的任务清单、初始化长任务、或第一次铺 features.json 时使用。只摸底、写清单,不开始大改代码。
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- continue-long-runSkill
- plan-then-actSkill
- tether-uiSkill
- tether-uiSkill
The file
Files
初始化跨会话任务
只在用户明确要跨会话做、或点了「拆成可跨会话的任务清单」时使用。普通问答不要跑。
- 只读:当前工作目录、README、
AGENTS.md/CLAUDE.md、相关入口。不要 write / edit / patch 业务代码。 - 按用户目标写出
.agents/features.json:JSON 数组,每项{ "id", "description", "passes": false }。条目要能单独验收,不要一项里塞整盘改造。 - 写出
.agents/progress.md,第一段写:摸了什么、清单在哪、下一轮该做哪一条。 - 若已有 git 仓库,做一次提交,说明是初始化任务清单。没有 git 就跳过。
- 停。告诉用户下一轮用 continue-long-run,一次只做一条。
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.

