AGENT SKILL
continuous-agent-loop
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
使用场景Skill与智能体开发
- License 许可
- MIT
- 最近更新
- 2026-06-24
- Stars
- ★ 67
- Forks
- 24
01 前言 Front Matter
- name
- continuous-agent-loop
- origin
- ECC
- description
- Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
02 资源文件 4
- 参考文档agents/openai.yaml276 B
- 参考文档references/adaptation-and-anti-simplification.md4.2 KB
- 参考文档references/compact-checklist.md799 B
- 参考文档references/review-passes.md8.9 KB
03 SKILL.md 正文
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
