Codex Knowledge Base
Eval-Driven Development with Codex CLI: Building Promptfoo Test Suites for AI Applications
Most teams building AI applications still rely on manual spot-checking to validate prompt changes.
The Agentic Pricing Wars: OpenAI's Enterprise Migration Offer, Anthropic's Quota Expansion, and the Real Cost of Switching
On 13 May 2026, OpenAI launched a 30-day Switch to Codex promotion offering two months of free enterprise usage for organisations transitioning from.
Codex CLI for Day-Two Operations: Runbooks, Drift Detection, and Platform Engineering Automation
Most Codex CLI coverage focuses on writing and reviewing code. But senior platform engineers and SREs have a different problem: the grind of day-two.
Tokenmaxxing with Codex CLI: Multi-Agent Operator Stacks, Parallel Harnesses, and the End of Single-Tool Identity
In May 2026, four independent signals converged on the same pattern in a single news cycle: YCs Lightcone podcast coined the term tokenmaxxing.
The Official OpenAI Skills Catalogue: System, Curated, and Experimental Skills for Codex CLI
OpenAI maintains a public skills catalogue at openai/skills — a repository of packaged agent instructions, scripts, and resources that extend Codex CLI with.
GPT-5.3-Codex Deep Dive: Benchmarks, CLI Configuration, and Interactive Coding Workflows
GPT-5.3-Codex landed on 5 February 2026 as OpenAI's flagship coding model, promising industry-leading agentic performance alongside a 25 % speed improvement.
Inside the Codex Windows Sandbox: Restricted Tokens, Synthetic SIDs, and the Four-Layer Execution Architecture
On 13 May 2026 OpenAI published an engineering deep-dive titled Building a safe, effective sandbox to enable Codex on Windows .
Codex CLI for ML Research: Agent-Driven Experimentation and the Parameter Golf Effect
OpenAI's Parameter Golf competition — train the best language model that fits in 16 MB and completes training in under ten minutes on 8×H100s — drew over.
Codex CLI for Kubernetes Operator Development: Scaffolding CRDs, Writing Reconciliation Loops, and Testing with envtest
Building a Kubernetes operator is one of the most structurally demanding tasks in cloud-native Go development. You need a Custom Resource Definition that.
Codex CLI Inside VS Code's Multi-Agent Architecture: Agent Sessions, Model Selection, and the Unified Development Experience
For months, terminal-native developers ran Codex CLI in one window, Claude Code in another, and kept Copilot humming in VS Code — three separate tools.