Unrolling the Codex agent loop

kept by eddie jan 26

OpenAI explains the architecture of Codex CLI's agent loop, detailing how it orchestrates model inference, tool calls, and context management using the Responses API.

GPT-5.1-Codex-Max Prompting Guide
OpenAI recommends migrating to the Codex-Max agentic model using the codex-cli prompt, compacted context, and specific tools for best performance on complex coding tasks.
also on Responses API, codex-cli, OpenAI, #open-source, #ai-coding, #developer-tools
Skills in OpenAI API
OpenAI introduces Skills, a reusable bundle of instructions, scripts, and assets mounted into shell environments, enabling versioned, conditionally invoked workflows that keep system prompts lean.
also on Responses API, OpenAI, #software-engineering, #developer-tools
OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI
OpenAI is adopting Anthropic's 'skills' approach into ChatGPT and Codex CLI, using markdown files for context management and subagent orchestration.
also on codex-cli, #cli, OpenAI, #ai-coding, #developer-tools
State of CLI Coding Agents, Mid-2026
The CLI coding agent market in mid-2026 is crowded with 35+ tools, and this piece systematically compares them across model labs, platform CLIs, and open-source harnesses.
also on codex-cli, #cli, #open-source, #ai-coding, #software-engineering, #developer-tools