Continuous agent loop

Skill loulanyue/awesome-claude-notes/docs/zh-CN/skills/continuous-agent-loop

Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.

Install

npx -y skills add loulanyue/awesome-claude-notes --skill continuous-agent-loop

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

具有质量门、评估和恢复控制的连续自主代理循环模式。

SKILL.md

1.3 KB, as published. Nobody here has run it

持续代理循环

这是 v1.8+ 的规范循环技能名称。它在保持一个发布版本的兼容性的同时，取代了 autonomous-loops。

循环选择流程

Start
  |
  +-- 需要严格的 CI/PR 控制？ -- yes --> continuous-pr
  |                                    
  +-- 需要 RFC 分解？ -- yes --> rfc-dag
  |
  +-- 需要探索性并行生成？ -- yes --> infinite
  |
  +-- default --> sequential

组合模式

推荐的生产栈：

RFC 分解 (ralphinho-rfc-pipeline)
质量门 (plankton-code-quality + /quality-gate)
评估循环 (eval-harness)
会话持久化 (nanoclaw-repl)

故障模式

循环空转，没有可衡量的进展
因相同根本原因而重复重试
合并队列停滞
无限制升级导致的成本漂移

恢复

冻结循环
运行 /harness-audit
将范围缩小到失败单元
使用明确的验收标准重放

原文

英文原文