Codex Agent Loop

Understand and apply how the Codex agent loop works, including request assembly (`instructions`, `tools`, `input`), thread/turn/item mental models, tool iteration, prompt growth, caching, compaction, and where `model_instructions_file` and `AGENTS.md` enter. Keep the local references for the durable conceptual model, but fetch current official docs via `openaiDeveloperDocs` for exact config, prompt-loading, and other evolving Codex behavior.

wisdom-in-a-nutshell Updated

File contents

wisdom-in-a-nutshell/agents commit 81fb795033

Frequently asked questions

npx get-skill add wisdom-in-a-nutshell/codex-agent-loop