Codex Knowledge Base
Codex CLI Hooks: Complete Guide to Events, Policy Engines and Production Patterns
The definitive reference for Codex CLI hooks -- architecture, all five hook event types (SessionStart, PreToolUse, PostToolUse, UserPromptSubmit, Stop), the JSON wire protocol, policy-engine patterns, production examples for gates, auditing,...
The Desktop Superapp War: Codex Scratchpad vs Claude Code Epitaxy
The terminal is no longer enough. As of mid-April 2026, both OpenAI and Anthropic are racing to consolidate their fragmented tool ecosystems into unified.
Context Compaction Deep Dive: How Codex CLI, Claude Code, and OpenCode Manage Long Sessions
Long-running agentic coding sessions inevitably hit the context window ceiling. When a session's accumulated messages — prompts, tool calls, file reads.
Codex CLI for Documentation at Scale: How Dagster Labs Turned Docs into a Feedback Loop
Documentation is the perennial grind of open-source maintenance. It rots faster than code, scales worse than tests, and nobody volunteers to write it.
Claude Code Routines: Autonomous Scheduled Agent Runs on Anthropic Cloud
Anthropic launched Claude Code Routines on 14 April 2026 — saved Claude Code configurations (a prompt, one or more repositories.
The Axios Supply Chain Attack: How a North Korean Compromise Reached Codex CLI's macOS Signing Pipeline
On March 31, 2026, a North Korean threat actor compromised Axios — the JavaScript HTTP client with over 70 million weekly npm downloads.
What the ETH Zurich Paper Gets Wrong (and Right) About AGENTS.md
In February 2026, researchers at ETH Zurich published a paper that sent shockwaves through the AI-assisted development community: Evaluating AGENTS.md.
Testing Codex CLI Skills: The Official Eval Pipeline with codex exec, JSONL Traces, and Skillgrade
Skills are becoming the primary unit of reusable workflow in Codex CLI. But a skill without evaluation is a guess — you have no idea whether a SKILL.md.
MCP Security in Codex CLI: CVE Lessons, Config Hardening, and Enterprise Trust Boundaries
The Model Context Protocol has become the connective tissue of agentic coding — and its attack surface has grown accordingly. Between January and February.
Docker Sandboxes for Codex CLI: MicroVM Isolation, the sbx CLI, and When to Use External Sandboxing
Codex CLI ships with one of the strongest built-in sandboxes in the AI coding agent space — Landlock plus seccomp on Linux, Seatbelt on macOS, restricted.