Oracle

Escalate to GPT-5.5 with high reasoning effort for problems requiring deeper analysis. Use for:

• Complex debugging with elusive bugs
• Architectural decisions and tradeoffs
• Security audits and vulnerability analysis
• Code review requiring deep reasoning

Main command

Run Codex with GPT-5.5 in non-interactive mode with high reasoning:

codex exec -m gpt-5.5 --sandbox read-only -c model_reasoning_effort='"high"' "$PROMPT"

Where $PROMPT is your analysis request. Codex bundles relevant context from your repo automatically.

Reasoning effort