Codex Knowledge Base
Reasoning Effort Tuning: Minimal to xhigh for Cost and Speed
Codex CLI's reasoning engine has a single knob that dramatically affects cost, speed, and quality: model_reasoning_effort.
The Proof of Work Principle: Why Agents Need to Show Their Working
There is a habit that developers have fallen into when working with autonomous coding agents: they read the diff, nod, and merge. The code arrived from.
Planning Mode in Practice: When to Use It and When to Skip It
Most developers activate planning mode once, see an agent propose a numbered list, and then leave it on permanently — or switch it off after a frustrating.
Context Window Management: Avoiding Compaction with Sub-Agent Delegation
Long Codex sessions degrade. Not catastrophically — the model does not forget your instructions — but its reliability erodes as the context fills with tool.
Compound Engineering with Codex: The 80/20 Plan-Review Model
Based on: every.to/guides/compound-engineering · github.com/EveryInc/compound-engineering-plugin · notes/compound-engineering.md
Codex in Slack and Linear: Triggering Cloud Tasks from Collaboration Tools
When OpenAI shipped Codex to General Availability in early 2026, the headline was a shift in where developers hand off work.
Codex Enterprise Admin Guide: RBAC, Managed Policies and Compliance API
Sources: developers.openai.com/codex/enterprise/admin-setup · developers.openai.com/codex/enterprise/governance · March 2026
Codex Cloud vs Codex Local: When to Run in the Cloud
Codex ships as two distinct execution surfaces: a local CLI that runs code on your machine.
The Codex CLI Skills Ecosystem: agentskills.io and Community Skills
Agent Skills started as an Anthropic internal format and, within months of being released as an open standard in December 2025, became the dominant.
Codex CLI for Python Teams: Configuration, Conventions and Automation
Python teams adopting Codex CLI face a familiar problem: out-of-the-box, the agent will reach for pip, pytest directly.