Safe Long-Run Mode (GPT-5.4 + Claude)

Use this skill for tasks that may run long, span multiple systems, or risk losing progress if interrupted.

Core rule

Do not run long tasks as one monolithic attempt. Split into phases, write checkpoints, and keep the work resumable.

Model selection

Use GPT-5.4 for:

• coding
• docs
• research
• file-heavy transformations
• multi-agent delegated work
• repetitive build tasks
• long internal work where cost and throughput matter