Agent Skills
› NeverSight/learn-skills.dev
› continuous-agent-loop
continuous-agent-loop
GitHub提供持续自主代理循环的模式，包含质量门控、评估和恢复控制。涵盖循环选择流程、生产环境组合模式及故障恢复策略，适用于需要严格控制和自我修复的自动化工作流。
Trigger Scenarios
需要构建持续自主代理循环
需要配置质量门控与评估机制
处理代理循环中的失败模式与恢复
Install
npx skills add NeverSight/learn-skills.dev --skill continuous-agent-loop -g -y
SKILL.md
Frontmatter
{
"name": "continuous-agent-loop",
"origin": "ECC",
"description": "Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls."
}
Continuous Agent Loop
This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops while keeping compatibility for one release.
Loop Selection Flow
Start
|
+-- Need strict CI/PR control? -- yes --> continuous-pr
|
+-- Need RFC decomposition? -- yes --> rfc-dag
|
+-- Need exploratory parallel generation? -- yes --> infinite
|
+-- default --> sequential
Combined Pattern
Recommended production stack:
- RFC decomposition (
ralphinho-rfc-pipeline) - quality gates (
plankton-code-quality+/quality-gate) - eval loop (
eval-harness) - session persistence (
nanoclaw-repl)
Failure Modes
- loop churn without measurable progress
- repeated retries with same root cause
- merge queue stalls
- cost drift from unbounded escalation
Recovery
- freeze loop
- run
/harness-audit - reduce scope to failing unit
- replay with explicit acceptance criteria
Version History
- e0220ca Current 2026-07-05 23:52
