Agent Loop

Structured Read→Plan→Execute→Verify→Report protocol for any task with side effects. Prevents false "done" reports, blind retries, and scope creep. Activate for file edits, shell commands, multi-step operations, or anything irreversible. Skip for pure Q&A. Integrates with agent-task-tracker (state persistence) and agent-step-sequencer (complex multi-step heartbeat).

dvcrn Updated 32 repo stars

File contents

dvcrn/openclaw-skills-marketplace/tree/main/plugins/cycy2xxx--agent-loop/skills/agent-loop commit 5268e401b9

Frequently asked questions

npx skillmds@latest add dvcrn/agent-loop