Swallow100/gpt-5.6-stop-overengineering
Skill Codex
Keep GPT-5.6 and other coding-agent work proportional to the request by locking scope, choosing the smallest sufficient implementation, matching verification to risk, and stopping when success is proven. Use for implementations, bug fixes, refactors, reviews, or maintenance where scope creep, speculative abstractions…
not rated 4 2mo ago A 84 tokens
original MIT