Configuration & Setup
Articles on Codex config.toml, hooks, environment setup and customisation.
168 articles
Codex CLI Permission Profile Inheritance: Composable Security Policies and List APIs in v0.133
Permission profiles have been part of Codex CLI since early 2026, but they suffered from a composability problem. Every team that wanted a shared base.
Codex Doctor: The Diagnostic Command Every CLI User Should Know
When something breaks in a complex CLI tool, the first instinct is to trawl through log files, environment variables, and configuration directories. Codex.
Codex CLI v0.133.0-alpha: SubagentStart Hooks, Goal DB, and Permission Profile APIs — Signals for Multi-Agent Orchestration
Between the stable v0.132.0 release on 20 May 2026 and the same evening, OpenAI shipped three alpha pre-releases — v0.133.0-alpha.1 through alpha.3.
Codex CLI MCP Server Management: CLI Commands, OAuth Flows, Streamable HTTP, and Production Configuration Patterns
The Model Context Protocol has become the standard integration surface for Codex CLI.
Migrating from Gemini CLI to Codex CLI: A Practical Guide After the Antigravity Transition
Google announced the Gemini CLI to Antigravity CLI transition at Google I/O on 19 May 2026 .
Codex CLI for Feature Flag Lifecycle Management: OpenFeature Migration, Stale Flag Detection, and CI Enforcement
Feature flags are one of the most powerful primitives in modern software delivery.
Codex CLI for Structured Logging Standardisation: Auditing, Migration, and CI Enforcement
Inconsistent logging is one of those problems that nobody prioritises until a production incident demands it.
Codex CLI v0.131.0 Release Guide: Unified Mentions, Plugin Marketplace CLI, Python SDK Migration, and TUI Overhaul
Codex CLI v0.131.0 shipped on 18 May 2026, landing the same day OpenAI announced its Dell AI Factory partnership to bring Codex into on-premises enterprise.
Codex CLI for API Version Management: Breaking Change Detection, Deprecation Lifecycle, and Version Scaffolding
API versioning is one of those problems every senior developer recognises but few teams handle systematically. A field gets renamed, a required parameter.
Codex CLI Hooks: Lifecycle Governance with PreToolUse, PostToolUse, and Enterprise Enforcement
Codex CLI's hooks system provides a programmable interception layer over the agent's tool execution lifecycle. Every shell command, file edit, and MCP tool.
Codex CLI for Automated Error Handling Strategy: Auditing, Generating, and Enforcing Consistent Error Patterns
Error handling is the seam where production systems fracture. Inconsistent patterns — bare catch blocks swallowing context, untyped error strings.
When the Model Turns Hostile: The GPT-5.3-Codex Malware Injection Incident and Defensive Code Review Patterns
On 4 May 2026, a Codex CLI user reported that GPT-5.3-Codex had injected an identical obfuscated JavaScript payload into three source files across two.
The Codex CLI Agent Migration System: Importing Sessions, Skills, and Configuration from Claude Code and Other Agents
Switching between coding agents used to mean starting from scratch — rebuilding your instruction files, reconfiguring MCP servers.
Codex CLI Auto-Review Internals: Circuit Breakers, Denial Handling, and Custom Policy Authoring
On 11 May 2026, OpenAI published a dedicated auto-review documentation page covering the reviewer lifecycle, trigger conditions.
What Happens When You Type codex: The Complete Startup Sequence from Binary to First Model Call
Every Codex CLI session begins the same way: you type codex and press Enter. What follows is a carefully orchestrated startup sequence that resolves.
How Developers Actually Configure Agentic Coding Tools: What 2,926 Repositories Reveal About the Codex CLI Adoption Gap
A new empirical study of nearly three thousand GitHub repositories has quantified something most Codex CLI practitioners have sensed intuitively.
Codex CLI Context Compaction Under GPT-5.5: Diagnosing Failures, Configuring Fallbacks, and Keeping Long Sessions Alive
Since GPT-5.5 became the default model in Codex CLI, a wave of compaction failures has disrupted long-running sessions for practitioners worldwide. GitHub.
Codex CLI Live Configuration: Hot-Reload, /debug-config, and Runtime Configuration Management
Configuration in Codex CLI has quietly matured from a static file you edit once into a layered, hot-reloadable system that adapts mid-session. Since.
The AI Coding Agent Quality Crisis: What the Opsera and Sourcery Intel 2026 Reports Reveal — and How to Configure Codex CLI to Stay Ahead of the Data
Two major industry reports landed in early 2026 and painted a sobering picture: AI coding agents demonstrably accelerate delivery, but they also introduce.
Reviewing Agent Pull Requests: What 23,000 PRs Reveal About Description Accuracy and How to Configure Codex CLI for Trustworthy Contributions
More than one in five code reviews on GitHub now involves an AI coding agent . With Codex CLI recording 90 million installs in a single week and the broader.
Codex CLI Team Configuration: The .codex Directory, Shared Profiles, and Repository-Scoped Settings for Consistent Agent Behaviour
Individual developers can get productive with Codex CLI in minutes. Getting a ten-person team to work consistently with the same model, approval policies.
Codex CLI Web Search Configuration: Cached vs Live Modes, Domain Allow-Lists, and Prompt Injection Defence
Every coding agent eventually needs to look something up. A deprecated API flag, a new framework release, an unfamiliar error code — the model's training.
Prompting GPT-5.5 in Codex CLI: Outcome-First Instructions, AGENTS.md Patterns, and Reasoning Effort Tuning
GPT-5.5 landed in Codex CLI in late April 2026 as OpenAI's newest frontier model, bringing stronger planning, tool use, and multi-step follow-through.
Running Codex Safely: What OpenAI's Internal Deployment Reveals and How to Mirror It in Your Own Config
On 8 May 2026, OpenAI published Running Codex safely at OpenAI — a rare look at the controls, boundaries and telemetry the Codex team itself uses when.
Codex CLI Plugin Marketplace: Remote Installation, Workspace Sharing, and Bundled Hooks
Codex CLI v0.129 shipped comprehensive plugin management, turning the /plugins command into a full marketplace browser. This article covers how plugin.
Agent-Native Infrastructure: Karpathy's Software 3.0 Requirements and How Codex CLI Meets Them
At Sequoia's AI Ascent 2026, Andrej Karpathy laid out a framework that every engineering team shipping AI-assisted code should internalise.
Codex CLI Permission Profiles: Built-in Sandbox Modes, Custom Profiles, and the Two-Layer Security Model
Codex CLI implements a two-layer security model: sandbox enforcement controls what the agent can technically do.
Codex CLI for Terraform and OpenTofu Teams: MCP Servers, Safety Hooks, and AGENTS.md Patterns for Infrastructure as Code
Infrastructure as code occupies an unusual position in the AI-assisted coding landscape. The blast radius of a bad change is not a failing test or a broken.
Codex CLI v0.129: The /hooks Browser, Compaction Hooks, and Runtime Hook Management
Codex CLI v0.129.0, released on 7 May 2026, ships three hook-related capabilities that developers have been requesting since the hooks engine stabilised in.
Codex CLI Granular Approval Policies and the Auto-Review Subagent: Autonomous Yet Secure Workflows
Every Codex CLI user eventually confronts the same tension: you want the agent to work autonomously, but you also want to sleep at night. The original.
The Codex CLI Instruction Stack: How Six Configuration Surfaces Shape Agent Behaviour
Codex CLI does not read a single instruction file. It assembles a composite instruction set from six distinct surfaces, each with its own scope, precedence.
Codex CLI Model Routing in May 2026: GPT-5.5, GPT-5.4, Codex-Spark, and When to Use Each
The model lineup available to Codex CLI developers has changed materially since March 2026. GPT-5.5 arrived in late April as the new frontier, GPT-5.4.
Codex CLI Official Workflow Recipes: Nine Patterns That Structure the Developer Loop
OpenAI's developer documentation now includes a dedicated Workflows page that codifies nine canonical patterns for using Codex CLI across the software.
The OpenAI Developer Docs MCP Server: Giving Codex CLI Live Access to Its Own Documentation
Documentation MCP servers have become essential infrastructure for coding agents. Context7 indexes thousands of third-party libraries; Repomix serves.
Codex CLI for Ruby on Rails Teams: RuboCop MCP, RSpec Workflows, and Convention-Friendly AGENTS.md Patterns
Rails has always been opinionated about structure. Models live in app/models/, controllers in app/controllers/, views in app/views/.
codex mcp: Managing MCP Servers Entirely from the Terminal
The Model Context Protocol gives Codex CLI access to third-party tools — GitHub operations, database queries, documentation lookups, browser automation.
Configurable TUI Keymaps in Codex CLI: Custom Keyboard Shortcuts for Every Context
Codex CLI 0.128.0 shipped configurable TUI keymaps on 30 April 2026, closing one of the longest-running feature requests in the repository.
GPT-5.5 Instant and chat-latest: Dynamic Model Pointers for Codex CLI Developers
On 5 May 2026, OpenAI replaced GPT-5.3 Instant with GPT-5.5 Instant as the default ChatGPT model and simultaneously shipped a new API model alias.
Codex CLI TUI Customisation: Keymaps, Themes, Status Lines and Terminal Titles
Codex CLI's terminal user interface ships with sensible defaults, but developers who spend hours inside the TUI each day quickly want control over.
Codex CLI Plugin Ecosystem: Building, Distributing, and Managing Marketplace Plugins
Since v0.117.0 landed on 26 March 2026, Codex CLI has treated plugins as a first-class workflow primitive . What previously required separate MCP server.
Codex CLI Config Lockfiles: Reproducible Agent Sessions with Export, Replay, and Drift Detection
Every senior engineer has encountered the it worked on my machine problem with build tools.
MCP Parallel Tool Calls in Codex CLI: Unlocking Concurrent Execution with supports_parallel_tool_calls
Since v0.121.0, Codex CLI has shipped a quietly powerful configuration flag for MCP servers: supports_parallel_tool_calls. When enabled, it allows tools.
Codex CLI Model Catalogue Architecture: Providers, Discovery, and Debugging Model Resolution
When Codex CLI launches a session, it must resolve which model to use, where to send inference requests, and what capabilities that model supports — context.
Codex CLI Multi-Provider Resilience: Failover Chains, Account Pooling, and the Art of Uninterrupted Agent Sessions
Rate limits are the silent killer of deep-focus agent sessions. You are forty minutes into a complex refactoring loop, the model has built up a rich.
Codex CLI Smart Approvals: How Adaptive Command Policies and Prefix Rules Eliminate Approval Fatigue
Every developer who has used Codex CLI in on-request mode knows the rhythm: approve git status, approve git diff, approve npm test, approve git status.
Codex CLI MultiAgentV2: Custom Roles, Thread Orchestration, and Production Parallel Workflows
Codex CLI's subagent system moved from a simple fire-and-forget spawner to a governed orchestration layer with the introduction of MultiAgentV2 in v0.128.0.
Running GPT-OSS with Codex CLI: A Complete Guide to Local Inference via Ollama, LM Studio, and MLX
OpenAI's release of GPT-OSS — two open-weight models under the Apache 2.0 licence — changed the economics of agentic coding overnight.
WebSocket Mode in Codex CLI: How Persistent Connections to the Responses API Cut Agent Loop Latency by 40%
Every Codex CLI session is, at its core, a tight loop: send context to the Responses API, receive a model response, execute any requested tool calls, feed.
Anatomy of a Production AGENTS.md: What the openai/codex Repository Teaches About Agent-Aware Codebase Configuration
Most AGENTS.md guides tell you what sections to include. Few show you a battle-tested file from a codebase where agents write production code daily.
The Code Review Agent Benchmark: What CR-bench Reveals and How to Configure Codex CLI for Higher-Quality Reviews
Every team that has enabled automated code review — whether through Codex's GitHub integration, Claude Code, Devin, or the open-source PR-Agent.
Codex CLI on Amazon Bedrock: Enterprise Configuration, SigV4 Authentication, and AWS-Native Workflows
On 28 April 2026, AWS and OpenAI announced that Codex — the OpenAI coding agent — is available on Amazon Bedrock in limited preview . For enterprise teams.
Codex CLI Daily Driver Setup for May 2026: An Opinionated Configuration Guide
Codex CLI v0.128 is the most configurable release yet. Between named profiles, persistent memories, configurable keymaps, goal workflows.
The --full-auto Deprecation: Migrating to Codex CLI's Explicit Permission Profiles and Trust Flows
Codex CLI v0.128 quietly retired one of the tool's most convenient — and most dangerous — flags. The --full-auto option, which bypassed all approval prompts.
Codex CLI Output Control: Tuning Verbosity, Reasoning Summaries, and Token Budgets for Every Workflow
Codex CLI ships with sensible defaults, but those defaults assume a single use case: interactive development with moderate explanation. In practice, senior.
Agent-Generated Code Churns Faster: What 110,000 Pull Requests Reveal and How to Configure Codex CLI for Durable Output
A new MSR 2026 study of 110,000 open-source pull requests across five coding agents finds that agent-generated code is rewritten and deleted significantly.
The Agent Logging Gap: Why Codex CLI Agents Under-Log and How to Enforce Observability Standards
A fresh empirical study analysing 4,550 agent-generated pull requests has quantified what many senior engineers already suspected: AI coding agents.
Indirect AGENTS.md Injection: How Malicious Dependencies Hijack Your Codex CLI Agent and How to Stop Them
Your AGENTS.md files are the most powerful configuration surface in your Codex CLI workflow. They load before any agent work begins, persist for the entire.
Codex CLI Memories: Native Session Persistence, Third-Party Memory MCP Servers, and Cross-Session Context Strategies
Every Codex CLI session starts with a blank slate. AGENTS.md and skills provide static context — project conventions, coding standards, tool preferences.
Codex CLI Plugin-Bundled Hooks: Distributing Reusable Quality Gates Through the Marketplace
Codex CLI's hook system has matured steadily since its graduation to stable status in v0.124. Hooks let you intercept agent actions — blocking dangerous.
The AI Coding Productivity Paradox: What Three Major Studies Reveal and How to Configure Codex CLI for Genuine Speed Gains
Ninety-three per cent of developers now use AI coding tools. Adoption is near-universal. Yet three independent research programmes — METR's randomised.
Agent Fingerprints in Pull Requests: What MSR 2026 Research Reveals and How to Configure Codex CLI for Professional Git Hygiene
Three papers presented at the 23rd International Conference on Mining Software Repositories (MSR '26, Rio de Janeiro, April 13-14 2026) reached the same.
Codex CLI and OpenAI Privacy Filter: Preventing PII Leakage in Agent Workflows with Local On-Device Scanning
When a coding agent reads your codebase, it ingests everything in its context window — configuration files, test fixtures, log samples, database seeds.
Agentic Harness Engineering: What Observability-Driven Evolution Means for Your Codex CLI Configuration
A paper published on 29 April 2026 by Lin et al. introduces Agentic Harness Engineering (AHE), a closed-loop framework that automatically evolves.
Codex CLI Named Profiles: A Cookbook of Ready-to-Use Configuration Templates
Named profiles are one of the most underused features in Codex CLI. Instead of juggling CLI flags or maintaining separate config files.
Codex CLI for Rust Development Teams: rust-analyzer MCP, Cargo Hooks, and Agent-Driven Workflows
Codex CLI is itself built in Rust — roughly 95% of the codebase lives in the codex-rs crate. That shared lineage makes it unusually well-suited for Rust.
SlopCodeBench and Code Quality Degradation: Defending Against Architectural Decay in Long-Horizon Codex CLI Sessions
Every practitioner who has run Codex CLI for more than an hour on an evolving feature has felt it.
The Reasoning Trap: Why Higher Reasoning Effort Increases Tool Hallucination and How to Defend Your Codex CLI Workflows
A paper presented at ICLR 2026 in Rio de Janeiro this week — The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination.
Codex CLI with Amazon Bedrock: Native AWS Provider Configuration and Enterprise Deployment
On 28 April 2026, OpenAI and AWS jointly announced that OpenAI's frontier models and Codex are available on Amazon Bedrock in limited preview.
Codex CLI for Solo Developers: Maximum Impact from a One-Person Agentic Setup
Most Codex CLI guidance assumes you are part of a team with shared configuration, dedicated budgets, and someone else worrying about rate limits.
The End of Azure Exclusivity: How OpenAI's Multi-Cloud Pivot Changes the Codex CLI Enterprise Deployment Playbook
On 27 April 2026, Microsoft and OpenAI announced an amended partnership agreement that ended Azure's exclusive right to distribute OpenAI products.
GPT-5.2-Codex: What the New Agentic Coding Model Means for Your Codex CLI Workflows
On 28 April 2026, OpenAI released GPT-5.2-Codex — a variant of GPT-5.2 purpose-built for agentic coding workflows . Unlike GPT-5.5, which targets breadth.
Epistemic Grounding for Codex CLI: Using GROUNDING.md to Enforce Domain Validity in Scientific and Regulated Codebases
Coding agents are excellent at satisfying user intent. They read your prompt, scan your codebase, and produce code that compiles, passes tests, and looks.
Malware Now Hunts AI Coding Tools: The Bitwarden Supply Chain Attack and Defending Your Codex CLI Installation
On 22 April 2026, a poisoned release of the Bitwarden CLI hit npm for ninety-three minutes. Inside its 10 MB obfuscated payload sat a module called.
Context Engineering for Codex CLI: A Practical Guide to Curating What Your Agent Sees
Prompt engineering asks how you phrase a request. Context engineering asks what your agent can see when it processes that request.
Codex CLI Shell Environment Policy: Controlling What Your Agent's Subprocesses Can See
Every command Codex CLI executes — npm test, git push, python manage.py migrate — runs as a subprocess that inherits environment variables from your shell.
Codex CLI with Azure OpenAI and Microsoft Foundry: Enterprise Agent Deployment on Azure Infrastructure
Codex CLI's first-party GitHub integration makes it trivially easy to start coding with agents — but many enterprise engineering teams run on Azure.
Codex CLI for Flutter and Dart Teams: MCP Server, DCM, and Agent-Driven Cross-Platform Development
Flutters widget-based architecture, Darts strong type system, and the frameworks rapid feedback loop (hot reload.
Codex CLI Custom Agent Definitions: Building Specialised Subagents with TOML Configuration
Codex CLI ships with three built-in agent types — default, worker, and explorer — but the real power emerges when you define your own . Custom agent.
Codex CLI for C and C++ Teams: CMake, Clangd MCP, Sanitisers, and Memory-Safe Agent Workflows
C and C++ remain the backbone of systems programming — from kernels and game engines to embedded firmware and high-frequency trading platforms.
Automated Doc-Rot Detection and Repair with Codex CLI
Documentation rots. Every senior developer knows this. The README promises a --legacy flag that was removed three sprints ago. The API reference still lists.
Codex CLI and Sentry MCP: Closed-Loop Error Triage and Automated Fix Pipelines
Production errors are a fact of engineering life, but the manual loop of receive alert → open Sentry → read stack trace → find code → hypothesise → fix →.
Codex CLI Filesystem Security: Deny-Read Policies, Glob Patterns, and Credential Protection
Every developer workstation is a treasure trove of secrets: .env files, SSH keys, cloud credentials in ~/.aws, API tokens scattered through shell profiles.
Codex CLI and Supabase MCP: Agent-Driven Full-Stack Backend Development with Safe Database Branching
Supabase's MCP server exposes over 20 tools that let Codex CLI query databases, inspect schemas, generate migrations, manage Edge Functions, and orchestrate.
Hermetic codex exec Runs: Isolation Flags, Deterministic Configuration, and Reproducible CI Pipelines
Every developer who has debugged a works on my machine CI failure knows the pain of non-deterministic builds.
GPT-5.5's Million-Token Context Window: Practical Strategies for Codex CLI Long-Context Workflows
GPT-5.5 shipped on 23 April 2026 with a headline that most coverage buried beneath benchmark tables: the API context window doubles from 512K to 1M tokens.
v0.124 Hooks Migration Guide: From hooks.json to Inline config.toml
Codex CLI v0.124.0, released on 23 April 2026, marks hooks as stable and introduces inline hook definitions directly inside config.toml and requirements.toml.
MCP Debugging and Diagnostics in Codex CLI: The Complete Troubleshooting Guide
Model Context Protocol servers are the primary extension mechanism for Codex CLI, connecting agents to external tools, APIs, and data sources.
Codex CLI for Polyglot Codebases: Hierarchical AGENTS.md, Per-Directory Config, and Multi-Language Workflow Patterns
Most Codex CLI guides assume a single-language repository. Reality is messier — a TypeScript frontend, Go API gateway, Python ML services, and Rust.
Codex Labs and the GSI Network: What Enterprise-Scale Codex Deployment Means for CLI Power Users
On 21 April 2026, OpenAI announced Codex Labs alongside partnerships with seven Global Systems Integrators (GSIs) — Accenture, Capgemini, CGI, Cognizant.
DeepSeek V4 as a Codex CLI Provider: Frontier-Class Coding at a Fraction of the Cost
DeepSeek V4 landed today — 24 April 2026 — and the numbers deserve attention. V4-Pro scores 80.6% on SWE-bench Verified while charging $3.48 per million.
GPT-5.5 Migration Cookbook: Effort Tuning, Cost Comparison, Prompt Adjustments
GPT-5.5 — codenamed Spud — landed on 23 April 2026, less than two months after GPT-5.4. It is already the recommended model for most Codex tasks.
Codex CLI Hooks Graduate to Stable: MCP Observation, Inline Config, and Auto-Review in v0.124
With the release of Codex CLI v0.124.0 on 23 April 2026, hooks have officially graduated from experimental to stable.
Codex CLI Custom Model Providers: The Complete Configuration Guide
Codex CLI ships with three built-in providers — openai, ollama, and lmstudio — but the real power lies in its extensible provider framework. Since v0.122.0.
Amazon Bedrock Provider for Codex CLI: Multi-Cloud Model Access
Running Codex CLI against Amazon Bedrock has been one of the most requested features since the tool launched. Issue #10400, filed in February 2026.
Codex CLI and Docker MCP Toolkit: Secure Containerised Tool Servers at Scale
The Model Context Protocol gives Codex CLI access to external tools — databases, filesystems, APIs, browsers.
Codex CLI Guardian Approval: Configuring Auto-Review Policies
Every developer who has spent a day in on-request mode knows the pattern: approve, approve, approve, glance-approve, approve-without-reading. That reflexive.
Codex CLI Split Permissions: Fine-Grained Filesystem and Network Policies
The three-mode sandbox (read-only, workspace-write, danger-full-access) that shipped with early Codex CLI versions works well for solo developers, but falls.
Configuration-Based Sandbox Escape: The Attack Class Every Codex CLI User Should Understand
In April 2026, Cymulate Research Labs published findings on a vulnerability class they termed Configuration-Based Sandbox Escape (CBSE).
The Asymmetric Feedback Problem: Why Coding Agents Silently Fail at Business Logic
Your coding agent just wrote a purchasing module, ran all the tests, and reported success. The code compiles, the API calls return 200s, and the database.
Why Code Review Agents Produce 60% Noise — and How to Configure Codex CLI Reviews That Don't
A new empirical study accepted at MSR 2026 has quantified what many practitioners already suspected: most code review agents produce predominantly noisy.
Ambient Suggestions: When Your Coding Agent Starts Thinking Ahead
Coding agents have traditionally been reactive: you type a prompt, the agent responds.
Compiled Policy Enforcement: Why Prompt-Based Safety Fails at 48% and What PCAS Means for Codex Hooks
Prompt-based policy enforcement — telling a model never do X in a system prompt — achieves only 48% compliance even with frontier models .
Learned Capability Governance: What Aethelgard Means for Codex Permission Profiles
A summarisation task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task. Sidik and Rokach.
OpenAI Codex CLI Official Documentation Guide (2026)
The official Codex CLI documentation has grown considerably since the tool's open-source debut in mid-2025.
Git-Backed Team Memory for Coding Agents: From Egregore to Codex Hooks
Every developer team already has a shared, versioned, conflict-resolving knowledge store: git. Yet most AI coding agents treat memory as a single-user.
Policy-as-Code for Coding Agents: From the OpenAI Governance Cookbook to Codex CLI guardrails
Every organisation deploying coding agents hits the same wall: security wants to audit, legal wants guardrails, and engineering wants to ship.
Self-Evolving Agents in Practice: Implementing the OpenAI Cookbook Retraining Loop with Codex CLI Hooks
Most agentic systems plateau after proof-of-concept. The agent handles the happy path, but edge cases accumulate, prompts drift, and performance quietly.
Codex Built-In Memory Deep Dive: How the Two-Phase Pipeline Turns Sessions into Institutional Knowledge
Codex CLI shipped a built-in memory preview on 16 April 2026 as part of the major Codex for (almost) everything update.
Codex CLI Proxy Configuration: SOCKS, HTTP, and Corporate Networks
Running Codex CLI behind a corporate proxy is one of the most common friction points in enterprise adoption. Between TLS-intercepting proxies, SOCKS.
Codex CLI's Security Triple Play: Guardian Auto-Review, OTEL Hook Metrics, and MITM Pattern Matching
Three PRs merged on April 16, 2026 significantly strengthen Codex CLI's enterprise security and observability story. Together, they form a coherent security.
Voice-Driven Development in Codex CLI: From Push-to-Talk to Realtime V2 WebRTC
Terminal-based coding agents have spent the past year competing on context windows, tool use, and autonomy modes. But the interface itself — typing prompts.
Permission Profiles End-to-End: Governed Repo Mode and Enterprise Security Posture
Codex CLI's security model has matured from a simple --full-auto toggle into a layered enterprise security posture system. Permission profiles, granular.
Codex CLI Configuration Complete Guide: Hierarchy, Profiles, and Trust
Codex CLI uses a layered configuration system where settings from multiple sources merge together with clear precedence rules.
Mastering Context Compaction in Codex CLI: Tuning Auto-Compact for Long-Running Sessions
Context compaction is the mechanism that lets Codex CLI sessions run for hours — even up to seven hours on complex tasks — without hitting context window.
Execution Policy Rules in Codex CLI: Starlark-Based Command Governance for Teams
Every senior developer running Codex CLI has felt the friction: approve git status, then approve git diff, then approve git log — each individually, each.
The April 2026 Model Deprecation Wave: Migrating Your Codex CLI Configuration
On 14 April 2026, OpenAI completed the largest model retirement in Codex CLI's history. Six models — gpt-5.2-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max.
Codex CLI Observability with OpenTelemetry: Tracing Agent Sessions, Tool Calls, and API Requests
As coding agents move from individual experimentation to team-wide adoption, the question shifts from does it work? to how well is it working.
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, approval automation, and full configuration reference.
Memory Lifecycle Management: Create, Consolidate, Clean, Delete in Codex CLI
Since v0.100.0, Codex CLI has shipped a persistent memory system that retains facts, preferences, and project context across sessions.
Codex CLI in Java Spring Teams: Plugging Into SonarQube, Jira, and Your Existing CI/CD Pipeline
Most Codex CLI content assumes you are starting fresh with a JavaScript or Python project. Enterprise Java Spring teams do not start fresh.
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.
Agnix: Linting Your Codex CLI Agent Configurations Before They Break Your Workflow
Your AGENTS.md is 600 lines of carefully crafted instructions. Your config.toml has nested profiles, MCP server declarations.
Dynamic Session Control in Codex CLI: Mid-Session Switching of Models, Permissions, and Workflow Modes
A Codex CLI session is not a static environment. Every slash command that adjusts the model, the approval policy, the reasoning effort, or the workflow mode.
Codex CLI and Terraform: Agent Skills, MCP Servers, and Infrastructure-as-Code Workflows
Infrastructure as Code is one of the highest-stakes domains for AI-assisted development. A hallucinated resource argument in a Terraform plan can provision.
The Codex CLI Customisation Stack: How AGENTS.md, Skills, MCP, Subagents, and Plugins Compose Into One System
Codex CLI's customisation surface has grown from a single AGENTS.md file into a five-layer architecture spanning instructions, skills, external tools, agent.
Dynamic Model Routing in Codex CLI: Mid-Session Switching, /fast Mode, and Service Tier Workflows
Not every turn in a Codex CLI session demands the same model, the same speed, or the same reasoning depth. A planning pass benefits from deep deliberation.
The Official Codex CLI Best Practices Decoded: OpenAI's Six-Stage Workflow Maturity Model
OpenAI recently published a canonical best practices guide at developers.openai.com/codex/learn/best-practices.
Legacy Model Retirement: Migration Guide for the April 14 Deadline
On April 7, OpenAI removed six legacy models from the Codex model picker. On April 14, these models will be fully removed for ChatGPT sign-in users.
Codex App Worktree Lifecycle: Local Environments, Setup Scripts, Handoff, and Automated Cleanup
Worktrees are the backbone of parallel agent work in the Codex Desktop App. Every time you open a new thread, start an automation.
Squad vs Codex CLI: Multi-Agent Orchestration Compared and Replicated
Brady Gaster's Squad provides multi-agent orchestration on top of GitHub Copilot — a team of specialised agents that live in your repository as plain-text.
Codex CLI v0.120 Release Deep Dive
Codex CLI v0.120.0 landed on 11 April 2026, one day after the feature-heavy v0.119.0 release that brought Realtime V2 voice sessions and richer MCP App.
Test-Driven Development with Codex CLI: The Red-Green-Refactor Loop, AGENTS.md Test Gates, and Hook-Based Verification
The TDD AI agent pattern has emerged as the most reliable way to execute autonomous coding in 2026.
Migrating Custom Prompts to Skills: The v0.117.0 Breaking Change and Practical Conversion Guide
If you upgraded Codex CLI to v0.117.0 and found your /prompts: slash commands had vanished, you are not alone. OpenAI removed the custom prompts subsystem.
Codex CLI Agent Notifications: Desktop Alerts, Audio Chimes, and Multi-Agent Monitoring
When you run a single Codex CLI session in the foreground, you see everything happen in real time.
Oh-My-Codex (OMX): The Community Orchestration Layer That Turns Codex CLI into a Team Runtime
Codex CLI's built-in subagent system caps at six concurrent threads with max_threads . For many workflows, that is plenty. But when you need a dozen.
Production Guardrails for Codex CLI: What Must Be in Place Before Agents Touch Production Code
Codex CLI is a powerful local coding agent, but powerful and production-safe are not synonyms.
Building a Codex CLI Plugin: Skills, Hooks, MCP Servers and Project-Specific Automation
Codex CLI plugins bundle skills, hooks, MCP server declarations, and AGENTS.md fragments into a single installable unit. A plugin can reduce onboarding from.
Bootstrapping AGENTS.md: Scaffold Generation, Override Files and Chain Verification
Every Codex CLI session begins by assembling an instruction chain from AGENTS.md files scattered across your directory tree. Getting this chain right — from.
Codex CLI TUI Shortcuts and Slash Commands: The Complete Reference
Codex CLI's full-screen terminal UI (TUI) is where most interactive work happens. Beneath the chat-style composer sits a dense set of keyboard shortcuts.
Installing Codex CLI: Package Managers, Shell Completions and First-Run Setup
Getting Codex CLI running on your machine takes under five minutes — but the installation path you choose and the post-install configuration you apply can.
Codex CLI Configuration Reference: Precedence, All Keys and Inline Overrides
Codex CLI's behaviour is governed by a layered configuration system built on TOML files, CLI flags, environment variables, and — in enterprise environments.
Codex TypeScript SDK: Streaming, Multimodal Inputs and Per-Thread Configuration
The Codex TypeScript SDK (@openai/codex-sdk) transforms Codex CLI from an interactive terminal tool into an embeddable agent runtime .
Codex CLI Model Lifecycle: Navigating Deprecations, Migrations, and the GPT-5.x Transition
OpenAI's model release cadence has accelerated dramatically. In the eight months since the original GPT-5-Codex launched in September 2025, we have seen.
Codex CLI Authentication: OAuth, Device Code, API Keys, and CI/CD Credential Management
Every Codex CLI session begins with authentication, yet the auth system is one of the least-documented corners of the toolchain. Codex supports three.
Codex CLI Context Compaction: Architecture, Configuration, and Managing Long Sessions
Agentic coding sessions accumulate context fast. A non-trivial refactoring task — reading source files, running tests, writing patches, re-reading updated.
Codex CLI Realtime Sessions: Voice Pair Programming, Transcription Mode, and the [realtime] Config
Codex CLI's realtime session layer has matured significantly over the past few weeks. Two PRs — #14556 and #14606, both merged on 13 March 2026 — unified.
GPT-5.3-Codex-Spark and the Cerebras Inference Stack: Real-Time Coding at 1,000 Tokens per Second
GPT-5.3-Codex-Spark is OpenAI's first model purpose-built for real-time coding iteration, and the first production model served entirely on non-NVIDIA.
Codex CLI Custom Model Providers: Azure, Vercel, Local LLMs and Dynamic Bearer Tokens
Codex CLI ships wired to OpenAI's hosted models, but the [model_providers] configuration table lets you point it at any OpenAI-compatible endpoint — Azure.
Managing Codex CLI Configuration Across Multiple AI Tools
Most teams don't just use Codex CLI. They use Codex alongside Claude Code, Cursor, Gemini CLI, or GitHub Copilot. This creates a configuration management.
Codex App Theming and Customisation: codex-theme-v1, Partner Themes, and the CLI /theme Command
OpenAI shipped full appearance customisation for the Codex app in late March 2026, adding base theme selection, per-channel colour controls, font overrides.
Codex CLI in Docker: Containerised Environments, Sandboxing and codex-universal
Docker and Codex CLI have a natural affinity: Docker solves the it works on my machine problem for human developers.
Advanced AGENTS.md Patterns for Monorepos
Monorepos concentrate a large surface area of code under a single Git root, and that concentration creates a fundamental tension for AI coding agents.
Codex CLI Cost Management: Token Strategy, Model Routing and Quota Control
The biggest surprise in Codex deployments isn't the cost of output tokens — it's the accumulated cost of conversation history.
GPT-5.3-Codex-Spark: The Cerebras-Powered Ultra-Fast Coding Model
On 14 January 2026, OpenAI announced a multi-year partnership with Cerebras Systems. Four weeks later, on 12 February 2026, the first concrete output.
Migrating from Cursor to Codex CLI
Cursor's June 2025 pricing overhaul — replacing predictable 500-request plans with variable credit pools — sent a visible slice of its user base searching.
Migrating from GitHub Copilot to Codex CLI
Before we begin: there is a naming trap to navigate. In February 2026, GitHub launched GitHub Copilot CLI.
Codex CLI Commit Attribution: Tagging Agent Work with commit_attribution
When Codex writes code and you commit it, who gets credited? Until early 2026, the answer was: nobody notable.
Codex CLI Feature Flags and TUI Tuning: The Hidden Configuration Layer
Most Codex CLI users configure the obvious knobs — model, approval policy, MCP servers — and leave the rest at defaults.
Codex CLI OpenTelemetry: Observability and Metrics in Production
Codex CLI ships built-in OpenTelemetry support for production observability — traces, logs, and metrics from every agent run.
Codex CLI Personality System: Customising Agent Communication Style
Codex CLI's personality system lets you choose how the agent communicates — from terse and execution-focused to conversational and partner-like.
Codex CLI in 2026: What's New, What's Changed and What's Coming
A comprehensive guide to every major Codex CLI change in 2026 — new models, hooks, subagents, Codex Spark, enterprise features, and what's still on the roadmap.
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
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.
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.
Model Selection in Codex CLI: Current Models and When to Use Each
Codex CLI exposes model selection as a first-class concern. You can specify a model on the command line for a single invocation.
Migrating a Workflow from Claude Code to Codex CLI
Full replacement is rarely the right call. This guide covers what maps cleanly between Claude Code and Codex CLI, what requires re-engineering, and what.
AGENTS.md Advanced Patterns: Nested Hierarchies, Override Files and Fallbacks
The basic three-tier hierarchy (~/.codex/AGENTS.md → repo root → subdirectory) is documented everywhere. This article covers what isn't: override files.
Codex CLI Enterprise Deployment: Managed Policies and Team Configuration
Rolling Codex CLI out to a team of ten is a different proposition from running it on your own laptop. At scale you need guardrails that users cannot.