Setup Agent Loops

Scaffold the per-repo configuration that loop-engineering skills assume:

• Verification — commands the agent runs after every change to know pass/fail
• Stop rules — when to quit iterating (caps, no-progress, forbidden actions)
• Scope — which paths the agent may edit during a loop

This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.

Process

1. Explore

Look at the current repo to understand its starting state. Read whatever exists; don't assume: