Provides patterns for continuous autonomous agent loops with loop selection, quality gates, evals, recovery controls, and failure mitigation. Useful for production AI agent workflows.
npx claudepluginhub jevonthompsonx/jsquared_blogThis skill uses the workspace's default tool permissions.
This is the v1.8+ canonical loop skill name. It supersedes `autonomous-loops` while keeping compatibility for one release.
Provides patterns for continuous autonomous agent loops with quality gates, evals, recovery controls, and loop selection flows. Use for reliable production agent workflows avoiding churn and stalls.
Provides patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Useful for production agent workflows to avoid churn, retries, and stalls.
Designs closed-loop prompts with Request-Validate-Resolve structure for reliable agentic workflows, self-validating agents, feedback loops, and test-fix cycles.
Share bugs, ideas, or general feedback.
This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops while keeping compatibility for one release.
Start
|
+-- Need strict CI/PR control? -- yes --> continuous-pr
|
+-- Need RFC decomposition? -- yes --> rfc-dag
|
+-- Need exploratory parallel generation? -- yes --> infinite
|
+-- default --> sequential
Recommended production stack:
ralphinho-rfc-pipeline)plankton-code-quality + /quality-gate)eval-harness)nanoclaw-repl)/harness-audit