Skip to content
Back to skills

Continuous Agent Loop

ASecurity

具有质量门、评估和恢复控制的连续自主代理循环模式。

  • 272 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 29, 2026
ai-agents

Security analysis

A100/100

Scanned September 29, 2026

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

Installs into .claude/skills of the current project.

Are you the author of Continuous Agent Loop?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Continuous Agent Loop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/loulanyue-continuous-agent-loop-a3e07613/badge)](https://www.skillsdirectory.com/skills/loulanyue-continuous-agent-loop-a3e07613)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: continuous-agent-loop
description: 具有质量门、评估和恢复控制的连续自主代理循环模式。
source_path: skills/continuous-agent-loop/SKILL.md
origin: ECC
---

# 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

```text
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:

1. RFC 分解 (`ralphinho-rfc-pipeline`)
2. 质量门 (`plankton-code-quality` + `/quality-gate`)
3. 评估循环 (`eval-harness`)
4. 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](../../../../skills/continuous-agent-loop/SKILL.md)

## 导航
- [中文文档导航](../../README.md)
- [贡献指南](../../../../CONTRIBUTING.md)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…