Stats
Actions
Tags
From agent-toolkit
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-toolkit:continuous-agent-loopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This is the v1.8+ canonical loop skill name. It supersedes `autonomous-loops` while keeping compatibility for one release.
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-auditnpx claudepluginhub mmalyska/claude-plugins --plugin agent-toolkitProvides patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use for structured multi-step agent workflows with CI/PR, RFC decomposition, or parallel generation.
Manages continuous autonomous agent loops with quality gates, evaluation harnesses, and recovery controls. Supports loop selection flow (sequential, parallel, RFC decomposition) and combined patterns.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.