Design Agent Loop

Design a reusable agent loop as a graph before running it. Take a TASK and COMPLETION CRITERIA, draw the node graph (input, plan, act, verify, retry or escalate, done), specify context, tools, expected output, and evidence per node, label every transition trigger, set max retries, budget ceilings, and human approval gates, keep unverifiable steps manual, design five eval cases with a pass or fail scorecard, and pick the single biggest bottleneck to automate first. Two-step handshake, design only until the user says execute now, then run one test case and improve the loop. Use when the user invokes /design-agent-loop or asks to design an agent loop, routine, workflow graph, or state machine for repeated agent work.

emaraschio Updated 9 repo stars
A felt-lined case of identical steel dies beside a linen booklet closed with an unmarked wax seal. Caption: a contract behind every slash command.

File contents

emaraschio/cursor-commands commit 3e42054fbd

Frequently asked questions

npx get-skill add emaraschio/design-agent-loop-2