Skills & AGENTS.md
Articles on agent skills, AGENTS.md patterns, skill authoring and the Codex skills ecosystem.
298 articles
Paper Replication with Coding Agents: What 158 Matched Targets Reveal About Evidence-Based Scientific Verification — and How to Wire the Workflow in Codex CLI
Paper Replication with Coding Agents: What 158 Matched Targets Reveal About Evidence-Based Scientific Verification — and How to Wire the Workflow in Codex CLI
One Developer Is All You Need: What a Brownfield Case Study Reveals About AI-Augmented Solo Delivery — and How to Wire the One-Person Squad in Codex CLI
One Developer Is All You Need: What a Brownfield Case Study Reveals About AI-Augmented Solo Delivery — and How to Wire the One-Person Squad in Codex CLI
Overeager Coding Agents: What 7,500 Benign Runs Reveal About Unauthorised Scope Expansion — and How Codex CLI's Approval and Sandbox Architecture Stops It
Overeager Coding Agents: What 7,500 Benign Runs Reveal About Unauthorised Scope Expansion — and How Codex CLI’s Approval and Sandbox Architecture Stops It
Cloak and Detonate: What SkillCloak's 90 Per Cent Scanner Evasion Rate Reveals About Agent Skill Malware — and How Codex CLI's Runtime Defence Layers Close the Gap
Cloak and Detonate: What SkillCloak’s 90 Per Cent Scanner Evasion Rate Reveals About Agent Skill Malware — and How Codex CLI’s Runtime Defence Layers Close the Gap
Prompt-Layer Complexity: What Hecate's 52 Metrics Reveal About the Maintenance Burden Traditional Tools Miss — and How to Measure Your Codex CLI Configuration Stack
Prompt-Layer Complexity: What Hecate’s 52 Metrics Reveal About the Maintenance Burden Traditional Tools Miss — and How to Measure Your Codex CLI Configuration Stack
Record and Replay: Programming by Demonstration Comes to Codex — and What It Means for the Open Agent Skills Standard
Record and Replay: Programming by Demonstration Comes to Codex — and What It Means for the Open Agent Skills Standard
Cheap Code, Costly Judgment: What a 420 KLOC Case Study Reveals About Governance Conversion — and How Codex CLI's Hook Architecture Operationalises It
Cheap Code, Costly Judgment: What a 420 KLOC Case Study Reveals About Governance Conversion — and How Codex CLI’s Hook Architecture Operationalises It
Skills Are Not Islands: What 1.43 Million Agent Skills Reveal About Hidden Dependency Risk — and How to Harden Your Codex CLI Plugin Stack
What 1.43 million agent skills reveal about hidden dependency risk and how to harden your Codex CLI plugin stack.
RepoRescue and the Compatibility Rescue Problem: Why Agents Fail at Cross-File Coordination — and How Codex CLI's Modernisation Workflow Closes the Gap
RepoRescue and the Compatibility Rescue Problem: Why Agents Fail at Cross-File Coordination — and How Codex CLI’s Modernisation Workflow Closes the Gap
AGENTS.md Structure Doesn't Matter: What a 16,050-Observation Factorial Study Reveals About Instruction Adherence
AGENTS.md Structure Doesn’t Matter: What a 16,050-Observation Factorial Study Reveals About Instruction Adherence
Coding Benchmarks Are Misaligned with Agentic Software Engineering: What the Harness Component Gap Means for Codex CLI Developers
Coding Benchmarks Are Misaligned with Agentic Software Engineering: What the Harness Component Gap Means for Codex CLI Developers
How Coding Agents Fail Their Users: What 20,574 Real-World Sessions Reveal About Misalignment — and How Codex CLI Defends Against the Seven Failure Forms
A large-scale observational study of 20,574 coding-agent sessions identifies seven recurring misalignment forms. We map each failure pattern to Codex CLI's constraint enforcement layer — hooks, approval policies, AGENTS.md, and sandbox isolation — showing how deterministic guardrails absorb what probabilistic instruction-following cannot.
Rule Taxonomy in AI IDEs: What 7,310 Mined Rules Reveal About the Gap Between Developer Intent and AGENTS.md Practice — and How to Close It in Codex CLI
Rule Taxonomy in AI IDEs: What 7,310 Mined Rules Reveal About the Gap Between Developer Intent and AGENTS.md Practice — and How to Close It in Codex CLI
Life-Harness and Runtime Harness Adaptation: What a 126-Setting Study Reveals About Improving Frozen LLM Agents Through Interface Engineering — and How Codex CLI Already Implements All Four Lifecycle Layers
Life-Harness and Runtime Harness Adaptation: What a 126-Setting Study Reveals About Improving Frozen LLM Agents Through Interface Engineering — and How Codex CLI Already Implements All Four Lifecycle Layers
Governance Decay and Self-Compacting Agents: What Happens When Context Compaction Silently Erases Your Safety Constraints
Governance Decay and Self-Compacting Agents: What Happens When Context Compaction Silently Erases Your Safety Constraints
The Over-Mocking Problem: What Empirical Research Reveals About Agent-Generated Test Quality — and How to Defend Your Suite with Codex CLI
The Over-Mocking Problem: What Empirical Research Reveals About Agent-Generated Test Quality — and How to Defend Your Suite with Codex CLI
CODESKILL and Self-Evolving Skill Banks: What RL-Trained Procedural Skill Management Means for Codex CLI Workflows
CODESKILL demonstrates that coding agents improve by 9.69% when equipped with RL-managed procedural skill banks extracted from past trajectories. Here is how to build the same feedback loop with Codex CLI skills, plugins, and hooks.
The AGENTS.md Evidence-Based Authoring Guide: What Two Empirical Studies Reveal About Writing Rules That Agents Actually Follow
A premium consolidation of rule taxonomy research (7,310 rules, 83 projects) and misalignment analysis (20,574 sessions) into a practical AGENTS.md authoring framework for Codex CLI. Covers the five-category taxonomy, the perception-practice gap, negative-constraint patterns, compliance hooks, evolution playbooks, and quarterly audit checklists.
Pomona and the Kaizen Loop: What Bloomberg's Tiny-Diff Code Quality Agent Teaches Us About Building Scanning-Repair Workflows with Codex CLI
Pomona and the Kaizen Loop: What Bloomberg’s Tiny-Diff Code Quality Agent Teaches Us About Building Scanning-Repair Workflows with Codex CLI
Does Code Cleanliness Matter for Coding Agents? What 660 Trials Reveal About Token Cost, Navigation, and Codex CLI Configuration
Does Code Cleanliness Matter for Coding Agents? What 660 Trials Reveal About Token Cost, Navigation, and Codex CLI Configuration
The Productivity-Reliability Paradox: Why 98 Per Cent More Pull Requests Broke Nothing — Except Your Review Pipeline — and How Specification Governance Fixes It with Codex CLI
The Productivity-Reliability Paradox: Why 98 Per Cent More Pull Requests Broke Nothing — Except Your Review Pipeline — and How Specification Governance Fixes It with Codex CLI
TRACE and the Correction-to-Enforcement Pipeline: Why Your Coding Agent Keeps Ignoring What You Told It — and How to Fix That with Codex CLI Hooks
TRACE and the Correction-to-Enforcement Pipeline: Why Your Coding Agent Keeps Ignoring What You Told It — and How to Fix That with Codex CLI Hooks
Rule Taxonomy and Evolution in AI IDEs: What 7,310 Mined Rules Reveal About How Developers Configure Coding Agents — and How to Structure Codex CLI's AGENTS.md
Two empirical studies — 7,310 rules from 83 projects and 401 Cursor repositories — reveal a five-category taxonomy of coding agent rules, a persistent gap between what developers value and what they write, and a 22.99% compliance improvement from iterative evolution. Mapped to Codex CLI AGENTS.md structure, per-directory overrides, and PostToolUse enforcement hooks.
The Agent Ecosystem Impact Report: Augmentation, Dilution, and Rejection Across 180 Million Repositories
The Agent Ecosystem Impact Report: Augmentation, Dilution, and Rejection Across 180 Million Repositories
How Coding Agents Fail Their Users: What 20,574 Sessions Reveal About Misalignment — and How to Defend Codex CLI Workflows
How Coding Agents Fail Their Users: What 20,574 Sessions Reveal About Misalignment — and How to Defend Codex CLI Workflows
Agent-Native Memory Systems: What a 12-System Benchmark Reveals About Memory Architecture — and How to Configure Codex CLI's Memory Stack
Agent-Native Memory Systems: What a 12-System Benchmark Reveals About Memory Architecture — and How to Configure Codex CLI’s Memory Stack
The Agent Testing Quality Playbook: Mock Diversity, Integration Balance, and AGENTS.md Templates for Codex CLI
The Agent Testing Quality Playbook: Mock Diversity, Integration Balance, and AGENTS.md Templates for Codex CLI
Augmentation with Dilution: What the First Large-Scale Study of AI Coding Agent Impact on Contributor Ecosystems Means for Codex CLI Teams
Augmentation with Dilution: What the First Large-Scale Study of AI Coding Agent Impact on Contributor Ecosystems Means for Codex CLI Teams
Human Oversight of Coding Agents in Practice: What 17 Developers Reveal About Oversight Work — and How to Configure Codex CLI for Each Form
Human Oversight of Coding Agents in Practice: What 17 Developers Reveal About Oversight Work — and How to Configure Codex CLI for Each Form
Over-Mocked Tests and Coding Agents: What 1.2 Million Commits Reveal — and How to Configure Codex CLI's AGENTS.md for Test Quality
Over-Mocked Tests and Coding Agents: What 1.2 Million Commits Reveal — and How to Configure Codex CLI’s AGENTS.md for Test Quality
SWE-Cycle and the FullCycle Gap: Why Coding Agents That Ace Isolated Tasks Collapse at End-to-End Issue Resolution — and How to Configure Codex CLI's Subagent Pipeline
SWE-Cycle and the FullCycle Gap: Why Coding Agents That Ace Isolated Tasks Collapse at End-to-End Issue Resolution — and How to Configure Codex CLI’s Subagent Pipeline
OmniCode and the Beyond-Bug-Fixing Problem: Configuring Codex CLI for Test Generation, Code Review, and Multilingual Workflows
OmniCode and the Beyond-Bug-Fixing Problem: Configuring Codex CLI for Test Generation, Code Review, and Multilingual Workflows
Property-Based Testing with Codex CLI: Agentic Invariant Discovery, Hypothesis Workflows, and What PBT-Bench Reveals About Agent Testing Capabilities
Property-Based Testing with Codex CLI: Agentic Invariant Discovery, Hypothesis Workflows, and What PBT-Bench Reveals About Agent Testing Capabilities
SlopCodeBench and the Iterative Degradation Problem: Why Your Coding Agent's Code Rots Faster Than Yours — and How Codex CLI's Architecture Fights Back
SlopCodeBench and the Iterative Degradation Problem: Why Your Coding Agent’s Code Rots Faster Than Yours — and How Codex CLI’s Architecture Fights Back
Neutral Prompting Attacks: When Your Codex CLI Skills Become the Supply Chain Weapon — and Three Defences That Close the Gap
Neutral Prompting Attacks: When Your Codex CLI Skills Become the Supply Chain Weapon — and Three Defences That Close the Gap
BeyondSWE: What Happens When Coding Agents Leave the Single-Repo Comfort Zone — and What Codex CLI Developers Should Do About It
BeyondSWE: What Happens When Coding Agents Leave the Single-Repo Comfort Zone — and What Codex CLI Developers Should Do About It
The Invisible Agent Problem: What a 180-Million-Repository Census Reveals About Codex CLI's Footprint in Open Source
The Invisible Agent Problem: What a 180-Million-Repository Census Reveals About Codex CLI’s Footprint in Open Source
The Deterministic Control Plane: Why Your Codex CLI Configuration Needs Supply-Chain Governance
The Deterministic Control Plane: Why Your Codex CLI Configuration Needs Supply-Chain Governance
Governed AI-Assisted Engineering: Mapping GAIE's Graduated Oversight Model to Codex CLI Permission Profiles for Regulated Codebases
Governed AI-Assisted Engineering: Mapping GAIE’s Graduated Oversight Model to Codex CLI Permission Profiles for Regulated Codebases
The ExecPlan Pattern: Plan-Driven Code Migrations with Codex CLI
The ExecPlan Pattern: Plan-Driven Code Migrations with Codex CLI
RigorBench and the Process Discipline Gap: What the First Engineering Process Benchmark Reveals About Codex CLI Workflows
RigorBench and the Process Discipline Gap: What the First Engineering Process Benchmark Reveals About Codex CLI Workflows
The Shift to Agentic AI: What OpenAI's Internal Usage Data Reveals About Codex Adoption, Parallel Agent Orchestration, and the Non-Developer Surge
The Shift to Agentic AI: What OpenAI’s Internal Usage Data Reveals About Codex Adoption, Parallel Agent Orchestration, and the Non-Developer Surge
SWE-Bench 5G and the Domain Knowledge Wall: What the First Telecom Coding Agent Benchmark Reveals About Specification-Driven Development with Codex CLI
SWE-Bench 5G and the Domain Knowledge Wall: What the First Telecom Coding Agent Benchmark Reveals About Specification-Driven Development with Codex CLI
NatureBench and the Discovery Gap: Why Your Codex CLI Agent Matches Published SOTA on Only 18 Per Cent of Scientific Tasks
NatureBench and the Discovery Gap: Why Your Codex CLI Agent Matches Published SOTA on Only 18 Per Cent of Scientific Tasks
SWE-PolyBench and the Polyglot Performance Gap: What Multi-Language Benchmarks Reveal About Codex CLI's Real-World Effectiveness
Amazon's SWE-PolyBench exposes a stark performance gap when coding agents move beyond Python. Here is what the data means for Codex CLI users working in JavaScript, TypeScript, and Java — and how to close the gap with language-aware configuration.
Patch the Planet: What OpenAI's Open-Source Security Initiative Means for Codex CLI Defensive Workflows
OpenAI's Patch the Planet initiative, launched 22 June 2026 with Trail of Bits and HackerOne, pairs GPT-5.5-Cyber with Codex to discover and fix vulnerabilities across 30+ critical open-source projects. This article examines the initiative's architecture, early results, and what it teaches Codex CLI users about integrating security scanning, AGENTS.md directives, and hooks into everyday development.
Rethinking Agent-Generated Tests: Why Your Codex CLI Agent Writes Print Statements, Not Assertions, and What to Do About It
Rethinking Agent-Generated Tests: Why Your Codex CLI Agent Writes Print Statements, Not Assertions, and What to Do About It
Silent Technical Debt in AI-Generated Code: What 302,000 Commits Reveal and How Codex CLI Defends Against It
Silent Technical Debt in AI-Generated Code: What 302,000 Commits Reveal and How Codex CLI Defends Against It
Cross-Session Stored Prompt Injection and Workspace Trojan Backdoors: What Persistent-State Attacks Mean for Codex CLI Defence
Cross-Session Stored Prompt Injection and Workspace Trojan Backdoors: What Persistent-State Attacks Mean for Codex CLI Defence
The Metaprogramming Reflex: What Frontier Coding Agents' Unfamiliar-Language Adaptation Means for Codex CLI Strategy
The Metaprogramming Reflex: What Frontier Coding Agents’ Unfamiliar-Language Adaptation Means for Codex CLI Strategy
Natural-Language Agent Harnesses: What NLAH Research, OpenAI's Harness Engineering, and Cross-Agent Portability Mean for Codex CLI AGENTS.md
Natural-Language Agent Harnesses: What NLAH Research, OpenAI’s Harness Engineering, and Cross-Agent Portability Mean for Codex CLI AGENTS.md
Meta Context Engineering: What Automated Skill Evolution Means for Codex CLI AGENTS.md and Skills Optimisation
Meta Context Engineering: What Automated Skill Evolution Means for Codex CLI AGENTS.md and Skills Optimisation
Coding Benchmarks Are Misaligned: What the Gorinova Position Paper Means for Codex CLI Harness Engineering
Coding Benchmarks Are Misaligned: What the Gorinova Position Paper Means for Codex CLI Harness Engineering
Probe-and-Refine Tuning: What Iterative AGENTS.md Optimisation Research Means for Codex CLI
Probe-and-Refine Tuning: What Iterative AGENTS.md Optimisation Research Means for Codex CLI
Self-Harness: What Autonomous Agent Framework Improvement Means for Codex CLI AGENTS.md and Hook Optimisation
Self-Harness: What Autonomous Agent Framework Improvement Means for Codex CLI AGENTS.md and Hook Optimisation
Before the Pull Request: What the Multi-Agent Coordination Research Means for Codex CLI Parallel Workflows
Sarkar's grite research reveals that 78% of multi-agent coding effort is wasted on duplicate work without coordination. This article maps the findings to Codex CLI's subagent, worktree, and hook patterns for preventing coordination failures.
When Coding Agents Should Ask Instead of Guess: What ClarEval and the Uncertainty-Aware Multi-Agent Study Mean for Codex CLI
When Coding Agents Should Ask Instead of Guess: What ClarEval and the Uncertainty-Aware Multi-Agent Study Mean for Codex CLI
Coding Agents Are 'Fixing' Correct Code: What FixedBench Means for Codex CLI Abstain-Before-Patch Discipline
Coding Agents Are “Fixing” Correct Code: What FixedBench Means for Codex CLI Abstain-Before-Patch Discipline
Context Engineering Masterclass: The Write-Select-Compress-Isolate Playbook for Codex CLI
Context Engineering Masterclass: The Write-Select-Compress-Isolate Playbook for Codex CLI
Record and Replay: Turning macOS Demonstrations into Reusable Codex Agent Skills
Record and Replay: Turning macOS Demonstrations into Reusable Codex Agent Skills
Agent Sycophancy and Confirmation Bias: Defence Patterns for Codex CLI
Agent Sycophancy and Confirmation Bias: Defence Patterns for Codex CLI
Agentic Very Much: Coding Agent Adoption Has Doubled in New GitHub Projects — What It Means for Codex CLI Teams
Agentic Very Much: Coding Agent Adoption Has Doubled in New GitHub Projects — What It Means for Codex CLI Teams
Codex CLI and Domain-Specific Languages: Practical Strategies for Teams With Proprietary or Sparse-Training Languages
Codex CLI and Domain-Specific Languages: Practical Strategies for Teams With Proprietary or Sparse-Training Languages
Open Knowledge Format and Codex CLI: Giving Your Agent a Knowledge Base It Can Actually Read
Google has published an open specification for packaging knowledge as markdown files with YAML frontmatter. It maps directly to patterns Codex CLI already supports — and it formalises what many teams have been doing informally with AGENTS.md, skills, and MCP servers.
ContextCov: Turning AGENTS.md into Executable Constraints — What It Means for Codex CLI Hook and Enforcement Strategy
ContextCov: Turning AGENTS.md into Executable Constraints — What It Means for Codex CLI Hook and Enforcement Strategy
Do Programming Languages Still Matter? What the Chess Engine Polyglot Study Means for Codex CLI Language Selection and Cost Strategy
A polyglot study built 34 chess engines in 17 languages using Codex CLI and Claude Code. The results refute 'language doesn't matter' and reveal concrete cost and performance implications for Codex CLI practitioners.
Safer Builders, Risky Maintainers: What the MSR 2026 Breaking Changes Study Means for Codex CLI Refactoring and Maintenance Configuration
AI coding agents introduce fewer breaking changes than humans when generating new code — but the pattern reverses sharply for refactoring and maintenance tasks. Here is how to configure Codex CLI to account for that asymmetry.
SWE-Explore: What the Repository Exploration Benchmark Means for Codex CLI Search Strategy
SWE-Explore: What the Repository Exploration Benchmark Means for Codex CLI Search Strategy
SkillReducer: What the First Large-Scale Skill Bloat Study Means for Codex CLI Token Efficiency
SkillReducer: What the First Large-Scale Skill Bloat Study Means for Codex CLI Token Efficiency
Agentic Engineering and the Intent Architect: What the Paradigm Shift from Code Author to Outcome Auditor Means for Codex CLI Configuration
Agentic Engineering and the Intent Architect: What the Paradigm Shift from Code Author to Outcome Auditor Means for Codex CLI Configuration
TEBench and the Test-Stale Blind Spot: What the First Test Evolution Benchmark Means for Codex CLI Test Maintenance
TEBench and the Test-Stale Blind Spot: What the First Test Evolution Benchmark Means for Codex CLI Test Maintenance
Frontier Agents and Metaprogramming: What EsoLang-Bench Reveals About Codex CLI Reasoning Effort, Tool Budgets, and Strategy Transfer
Frontier Agents and Metaprogramming: What EsoLang-Bench Reveals About Codex CLI Reasoning Effort, Tool Budgets, and Strategy Transfer
AGENTS.md Beyond /init: Writing Project Instructions That Actually Reduce Token Spend
The /init scaffold is a starting point, not a destination. This guide covers the sections /init misses — hook policies, MCP server context, skill routing, goal boundaries — and the Princeton evidence that well-written AGENTS.md files cut runtime by 29% and tokens by 17%.
Codex CLI for Scientific Computing: From Black Hole Simulations to Reproducible Research Pipelines
Codex CLI for Scientific Computing: From Black Hole Simulations to Reproducible Research Pipelines
Automated SAP Testing with Codex CLI: An Agent-Driven Approach
How to use Codex CLI to generate, maintain, and execute automated tests across SAP's four testing layers — OData APIs, BAPIs/RFCs, Fiori UI, and SAP GUI — with practical code examples, MCP integration patterns, and guidance on navigating SAP's April 2026 API policy.
Agent-Generated Code and Open Source Licence Compliance
Agent-Generated Code and Open Source Licence Compliance
Codex CLI for Platform Engineering Teams: Golden Paths, Internal Developer Platforms, and Agent-Ready Templates
Codex CLI for Platform Engineering Teams: Golden Paths, Internal Developer Platforms, and Agent-Ready Templates
Agent Liability and Insurance: Who Pays When Agent-Generated Code Causes Harm?
Agent Liability and Insurance: Who Pays When Agent-Generated Code Causes Harm?
Codex CLI Configuration Anti-Patterns: Twelve Settings Mistakes That Waste Tokens, Break Sandboxes, and Frustrate Your Agent
Codex CLI Configuration Anti-Patterns: Twelve Settings Mistakes That Waste Tokens, Break Sandboxes, and Frustrate Your Agent
The Miasma Worm Targets Codex CLI: How a Self-Replicating Supply Chain Attack Exploits AI Agent Configuration Files and What You Should Do About It
The Miasma Worm Targets Codex CLI: How a Self-Replicating Supply Chain Attack Exploits AI Agent Configuration Files and What You Should Do About It
Codex CLI for Terraform and Infrastructure as Code: The MCP Server, TerraShark, and Agent-Driven IaC Workflows
Codex CLI for Terraform and Infrastructure as Code: The MCP Server, TerraShark, and Agent-Driven IaC Workflows
Context Engineering for Codex CLI in June 2026: The Write-Select-Compress-Isolate Playbook
Context engineering has displaced prompt engineering as the critical discipline for coding agents. Here is the concrete Codex CLI playbook, mapped to the four-strategy framework that the industry has converged on.
MCP Dev Summit Bengaluru: Five Production Patterns Every Codex CLI Developer Should Know
MCP Dev Summit Bengaluru: Five Production Patterns Every Codex CLI Developer Should Know
Inside the Scaffold: What Academic Research Reveals About Codex CLI's Agent Architecture
Inside the Scaffold: What Academic Research Reveals About Codex CLI’s Agent Architecture
Codex CLI for Design Pattern Refactoring: Agent-Assisted GoF Patterns, SOLID Enforcement, and Architectural Improvement
Codex CLI for Design Pattern Refactoring: Agent-Assisted GoF Patterns, SOLID Enforcement, and Architectural Improvement
The End of Fine-Tuning: What OpenAI's API Wind-Down Means for Your Codex CLI Customisation Strategy
The End of Fine-Tuning: What OpenAI’s API Wind-Down Means for Your Codex CLI Customisation Strategy
The 27% Dividend: How Coding Agents Unlock Previously Uneconomical Work, and Codex CLI Patterns for Capturing It
The 27% Dividend: How Coding Agents Unlock Previously Uneconomical Work, and Codex CLI Patterns for Capturing It
Agent-Generated Documentation: Quality, Trust, and Verification Patterns for Codex CLI Teams
Agent-Generated Documentation: Quality, Trust, and Verification Patterns for Codex CLI Teams
The Agent Skill Supply Chain Crisis: ClawHavoc, ToxicSkills, SkillSieve, and Defending Your Codex CLI Skill Stack
The Agent Skill Supply Chain Crisis: ClawHavoc, ToxicSkills, SkillSieve, and Defending Your Codex CLI Skill Stack
Codex CLI for Infrastructure as Code: Terraform MCP, Pulumi Agent Skills, and the Agentic IaC Stack
Codex CLI for Infrastructure as Code: Terraform MCP, Pulumi Agent Skills, and the Agentic IaC Stack
Agent-Ready Repository Architecture: Codebase Patterns That Maximise Codex CLI Productivity
Agent-Ready Repository Architecture: Codebase Patterns That Maximise Codex CLI Productivity
Why 'Always Run Tests' in AGENTS.md Makes Things Worse — and What to Write Instead
Why ‘Always Run Tests’ in AGENTS.md Makes Things Worse — and What to Write Instead
The Agentic AI Foundation: What AGENTS.md, MCP, and Linux Foundation Governance Mean for Codex CLI Developers
The Agentic AI Foundation: What AGENTS.md, MCP, and Linux Foundation Governance Mean for Codex CLI Developers
The Gemini CLI Shutdown and the Open-Source Trust Crisis: Portability Lessons Every Codex CLI Developer Should Learn Before June 18
The Gemini CLI Shutdown and the Open-Source Trust Crisis: Portability Lessons Every Codex CLI Developer Should Learn Before June 18
The Three Layers of Agent Testing: Dependency Graphs, Phase Gates, and Bounded Repair
The Three Layers of Agent Testing: Dependency Graphs, Phase Gates, and Bounded Repair
Codex CLI for Automated Test Maintenance: Fixing Broken Tests, Updating Snapshots, and Eliminating Flaky Tests
Codex CLI for Automated Test Maintenance: Fixing Broken Tests, Updating Snapshots, and Eliminating Flaky Tests
The Vercel Skills CLI and the Open Agent Skills Ecosystem: Installing, Managing, and Publishing Skills for Codex CLI
The Vercel Skills CLI and the Open Agent Skills Ecosystem: Installing, Managing, and Publishing Skills for Codex CLI
ExecPlans and PLANS.md: Driving Multi-Hour Autonomous Codex CLI Sessions
ExecPlans and PLANS.md: Driving Multi-Hour Autonomous Codex CLI Sessions
Codex CLI for .NET 10 and C# 14: Aspire Integration, MCP Servers, and the dotnet/skills Ecosystem
Codex CLI for .NET 10 and C# 14: Aspire Integration, MCP Servers, and the dotnet/skills Ecosystem
Beyond the Prompt: Codex CLI Mastery
Most developers treat Codex CLI as a chat box. The real value sits past the prompt, in AGENTS.md, skills, subagents, profiles, MCP servers and directory layout. This guide covers everything between installation and genuine mastery.
Codex CLI for Tailwind CSS v4: MCP Servers, Agent Skills, and Utility-First Styling Workflows
Codex CLI for Tailwind CSS v4: MCP Servers, Agent Skills, and Utility-First Styling Workflows
Codex CLI for Python Type Safety: Agent-Driven Type Checking with Mypy, Pyright, ty, and Pyrefly
How to integrate Python's four major type checkers into Codex CLI's agent loop for automated type annotation, gradual migration, and CI-enforced type safety.
Agent Instruction Files: AGENTS.md, CLAUDE.md, and Cross-Tool Portability with Codex CLI
Agent Instruction Files: AGENTS.md, CLAUDE.md, and Cross-Tool Portability with Codex CLI
Codex CLI for Zig and Nim: MCP Servers, Agent Skills, and Emerging Systems Language Workflows
Codex CLI for Zig and Nim: MCP Servers, Agent Skills, and Emerging Systems Language Workflows
Codex CLI for MongoDB Development: MCP Server, Agent Skills, and Document Modelling Workflows
Codex CLI for MongoDB Development: MCP Server, Agent Skills, and Document Modelling Workflows
Codex CLI for Redis Development: MCP Server, Agent Skills, and Production Caching Workflows
Codex CLI for Redis Development: MCP Server, Agent Skills, and Production Caching Workflows
Codex CLI for Spring Boot 4 and Spring AI: Java MCP Servers, Virtual Threads, and Agent-Assisted Development on Java 25
Codex CLI for Spring Boot 4 and Spring AI: Java MCP Servers, Virtual Threads, and Agent-Assisted Development on Java 25
Codex CLI for Firebase Development: MCP Server, Agent Skills, and Full-Stack Workflows
Codex CLI for Firebase Development: MCP Server, Agent Skills, and Full-Stack Workflows
Codex CLI for WordPress Development: MCP Adapter, Playground, and Agent-Driven Plugin Workflows on WordPress 7.0
Codex CLI for WordPress Development: MCP Adapter, Playground, and Agent-Driven Plugin Workflows on WordPress 7.0
Codex CLI for Astro Development: Docs MCP, Agent Skills, and Edge-First Workflows on Cloudflare Workers
Codex CLI for Astro Development: Docs MCP, Agent Skills, and Edge-First Workflows on Cloudflare Workers
Codex CLI and Monorepo Tooling: Turborepo, Nx, and Bazel Agent Workflows
Monorepos concentrate hundreds of packages behind a single repository root. That density is a gift for an agent.
Codex CLI for Swift and SwiftUI Development: Xcode MCP Servers, Agent Skills, and Build-Test-Debug Workflows
Swift and SwiftUI development sits at an intersection that makes agentic coding both powerful and tricky. The toolchain is GUI-heavy, simulators consume.
Codex CLI for Clojure Development Teams: ClojureMCP, REPL-Driven Agent Workflows, and Structural Editing
Clojure's parenthesised syntax and REPL-driven development culture create a distinctive set of challenges — and opportunities — for AI coding agents. Where.
Codex CLI for Gleam Development: Type-Safe BEAM Agents, LSP-MCP Bridge, and Dual-Target Workflows
Gleam occupies a distinctive niche in the language ecosystem: a statically-typed, functional language that compiles to both Erlang (for the BEAM VM) and.
Codex CLI for DuckDB and MotherDuck: MCP-Driven Analytical SQL, Agent Skills, and Data Pipeline Workflows
DuckDB has become the default analytical engine for local data work — in-process, zero-dependency.
Codex CLI for Embedded and Firmware Development: PlatformIO MCP, Zephyr Workflows, and AGENTS.md for Hardware Teams
Codex CLI articles cover Go, Rust, Python, Swift, Kotlin, Zig — practically every application-level language. Embedded firmware has been conspicuously.
Codex CLI for Haskell Development Teams: HLS via LSP-MCP, Type-Driven Agent Workflows, and AGENTS.md for Functional Codebases
Haskell's type system catches entire categories of defects at compile time, but that same rigour makes it an interesting test case for AI coding agents.
Codex CLI for Nix Development: MCP-NixOS, Reproducible Environments, and Flake-Native Agent Workflows
Nix sits at the intersection of package management, environment reproducibility, and system configuration.
Spec-Driven Development Frameworks for Codex CLI: Patterns, Best Practices, and the 2026 Landscape
Spec-driven development has become the dominant methodology for AI-assisted coding in 2026.
Codex CLI for Database Schema Migrations: Safe Evolution Patterns with Prisma, Drizzle, and MCP
Database schema migrations sit at the intersection of high consequence and low tolerance for error.
Codex CLI for Scala Development Teams: Metals MCP, sbt, and Idiomatic Functional Workflows
Dedicated language-specific Codex CLI articles exist for Go, Rust, Ruby/Rails, Python/Django/FastAPI, C/C++, Elixir/Phoenix, Swift, Kotlin/Android.
Codex CLI Prompt Engineering in the GPT-5.5 Era: Outcome-First Patterns, Anti-Patterns, and the Prompts That Ship Code on the First Turn
The single most common question in the OpenAI developer forum is some variation of Why does Codex produce garbage for me but magic for everyone else? .
Codex CLI for Go Development Teams: gopls MCP, Agent Skills, and Go 1.26 Workflows
Go teams adopting Codex CLI face a specific configuration challenge: the language's strong conventions around error handling, concurrency, and module.
Codex CLI + shadcn/ui: Agent-Driven Design System Workflows with MCP Server, Skills, and CLI v4
The shadcn/ui March 2026 release — CLI v4, the official skills system, and the shadcn MCP server — turned what was already the most popular component.
Codex CLI for Cross-Repository Development: Multi-Repo Sessions, Coordination Patterns, and MCP-Bridged Workflows
Senior developers working on microservices architectures, shared libraries, or platform teams rarely touch a single repository in isolation. A typical task.
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 Bazel Monorepo Workflows: MCP Server Integration, Remote Builds, and AGENTS.md Conventions
Bazel monorepos present a unique challenge for AI coding agents. The build graph is explicit and hermetic, the dependency model is declarative, and a single.
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 Agent Improvement Loops: Closing the Harness Engineering Flywheel with Traces, Evals, and Automated Handoffs
Most teams treat their agent configuration — AGENTS.md, skills, hooks, tool policies — as a write-once artefact. They tune it until the agent stops.
Codex CLI for GraphQL Development: Apollo Skills, MCP Server Integration, and Schema-Driven Workflows
GraphQL APIs demand precision that free-form code generation struggles to deliver. A misnamed field, an incorrect nullability annotation, or a resolver that.
Codex CLI for Mobile Development: iOS with XcodeBuildMCP, Android CLI Skills, and React Native Plugin Workflows
Mobile development has historically been hostile to terminal-first agent workflows. Platform toolchains assume GUI interaction, build systems are opaque.
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 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 for API Integration Testing: Agent-Driven Mock Generation, Contract Validation, and Test Harness Automation
Unit tests verify components in isolation. End-to-end tests verify the full stack. Between them sits integration testing — the practice of validating that.
Automated Code Documentation Generation with Codex CLI: Docstrings, JSDoc, and CI-Integrated Doc Pipelines
Documentation debt accumulates silently. Functions ship without docstrings, type annotations drift from reality, and README files describe architectures.
Coverage-Driven Test Generation with Codex CLI: Closing Gaps Using Istanbul, Coverage.py, and Agent Workflows
Every engineering team has coverage gaps — untested error handlers, edge-case branches nobody thought to exercise, and legacy modules with zero assertions.
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.
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.
The Codex CLI Hackathon Playbook: Rapid Prototyping Under Time Pressure
Sea Limited and OpenAI announced the first regional Codex Hackathon series today, kicking off in Singapore on 6 June 2026 with US$30,000 in API credits for.
Codex CLI for Automated Dependency Auditing: Licence Compliance, SBOM Generation, and Supply Chain Policy Enforcement
Knowing your dependencies have no critical CVEs is only half the supply chain story.
Codex CLI for Database Migrations: Agent-Driven Schema Evolution with Atlas, Prisma, and Flyway
Database migrations sit in an uncomfortable sweet spot for AI coding agents. The work is repetitive enough to automate.
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.
Codex CLI for Embedded and IoT Development: Firmware Generation, Cross-Compilation, and Hardware-Aware Agent Workflows
Embedded systems development has traditionally resisted the agentic coding wave. The reasons are well-understood: cross-compilation toolchains sprawl across.
Migrating SwiftUI Apps to Liquid Glass with Codex CLI: Agent Skills, XcodeBuildMCP, and iOS 26 Workflows
Apple's Liquid Glass design language, introduced at WWDC 2025 and shipping with iOS 26, represents the most significant visual overhaul since iOS 7's flat.
Infrastructure as Code with Codex CLI: The Terraform Skill, HashiCorp MCP Server, and Agent-Driven IaC Workflows
AI coding agents have reshaped application development, yet infrastructure as code remains a domain where hallucinated resource arguments, outdated provider.
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 for Generating Architecture Diagrams from Source Code: Mermaid, C4, and PlantUML Visualisation Workflows
Architecture diagrams lie. Not because anyone deliberately drew them wrong, but because code moves faster than documentation. A team refactors a service.
Codex CLI for Knowledge Work: Data Analysis, Report Generation, and Slide Deck Automation Beyond Code
When OpenAI repositioned Codex as a tool for (almost) everything in April 2026, the message was clear: the same codex exec primitive that ships pull.
Codex CLI for WebAssembly Development: Rust-to-Wasm Workflows, Wassette MCP, and the Component Model
WebAssembly has crossed the threshold from browser curiosity to production infrastructure. The 2026 State of WebAssembly survey reports 67% of respondents.
Google Antigravity vs Codex CLI: Multi-Agent IDE Meets Terminal-First Agent in the 2026 Coding Wars
Google Antigravity landed in public preview on 20 November 2025 and has since grown into the most serious IDE-native challenger to terminal-first agents.
Linux Kernel Development with Codex CLI: From Module Scaffolding to LKML Submission
On 8 May 2026, a patch series appeared on the Linux kernel mailing list introducing prom21-xhci, a hardware monitoring driver for AMD Promontory 21 chipset.
Database Schema Migrations with Codex CLI: Atlas Agent Skills, Policy-as-Code, and the Deterministic Safety Layer
AI coding agents are remarkably good at generating application code. Database migrations are a different beast.
Custom CUDA Kernels with Codex CLI: The Hugging Face Agent Skill for GPU Programming
Writing custom CUDA kernels has traditionally been the domain of a small cadre of GPU specialists. The barrier is high: you need to understand warp-level.
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 Multi-Directory Workflows: Coordinating Cross-Repo Changes with --add-dir, Writable Roots, and Permission Profiles
Real-world product work rarely fits inside a single directory. A feature ticket that touches a React frontend, a FastAPI backend, and a shared types package.
Codex CLI for Game Prototyping: From Design Document to Playable Build with Godot, Phaser, and Agent Skills
Game prototyping rewards fast iteration above all else. You need to get a concept on screen, playtest it, throw away what fails, and refine what sticks.
AWS Agent Toolkit for AWS: Enterprise MCP, Skills, and Plugins for Codex CLI
On 6 May 2026 AWS launched the Agent Toolkit for AWS, consolidating its scattered agent infrastructure into a single official bundle of MCP servers, skills.
Cross-Agent Skills Hit the npm Moment: 351K Skills, Three Marketplaces, and a Portability Standard
A Termdock analysis published in May 2026 makes a compelling case: the Agent Skills ecosystem is reaching its npm circa 2011 inflection point.
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.
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.
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 for Data Analysis: From Raw CSV to Stakeholder Report in One Agent Session
Codex CLI started life as a coding agent, but OpenAIs April 2026 Codex for (almost) everything update made the shift explicit: the same agent loop that.
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.
ProgramBench and the Zero-Percent Problem: What a Cleanroom Benchmark Reveals About Architectural Reasoning in Codex CLI
On 5 May 2026, researchers from Meta Superintelligence Labs, Stanford, and Harvard published ProgramBench.
Codex CLI Metaprompting: Using the Agent to Improve Its Own Instructions
Most developers treat their AGENTS.md and skills as write-once configuration. They scaffold an initial file with /init, tweak a few lines, and never touch.
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 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.
Microsoft APM: The Package Manager for AI Agents and What It Means for Codex CLI Teams
Every software team has solved dependency management for application code — package.json, requirements.txt, Cargo.toml. But agent configuration remains.
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.
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 External Agent Migration: The Detect/Import API and Cross-Agent Portability
The terminal coding agent landscape in 2026 is crowded: Codex CLI, Claude Code, Cursor, Gemini CLI, Aider, Copilot CLI, and more.
The Agent Skills Open Standard: Writing Portable SKILL.md Files That Work Across Codex CLI, Claude Code, and 30+ Tools
If you have invested time building skills for Codex CLI, you may not realise that those same files already work — unchanged.
Database Schema Migrations with Codex CLI: Atlas Skills, Neon Branching, and Safety Patterns
Database schema migrations remain one of the riskiest operations in any engineering workflow.
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 Skills for OSS Maintenance: Lessons from OpenAI's Own Agents SDK Repositories
OpenAI practises what it preaches. In March 2026 the company published a detailed case study showing how Codex CLI skills transformed maintenance of its two.
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.
Do Agent-Written Tests Actually Help? What Six LLMs on SWE-bench Reveal and How to Rethink Your Codex CLI Testing Strategy
The instinct to make coding agents write tests is strong — and understandable. Test-driven development has been a pillar of professional software.
The Over-Mocking Problem: What 1.2 Million Commits Reveal About Agent-Generated Tests and How to Configure Codex CLI for Realistic Test Output
A new empirical study accepted at MSR 2026 analysed 1.2 million commits across 2,168 repositories and found that coding agents generate mocks in 36% of their.
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.
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.
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 for Angular Teams: MCP Server, Signal-Based Patterns, and Agent-Driven Enterprise Frontend Workflows
Angular's evolution from Zone.js-driven change detection to signal-based reactivity has been the framework's most significant architectural shift since the.
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 Nine-Second Database Deletion: What the PocketOS Incident Teaches Codex CLI Practitioners About Agent Safety
On 25 April 2026, a Cursor agent powered by Claude Opus 4.6 deleted PocketOS's production database — and every volume-level backup.
The .NET Agent Skills Ecosystem Matures: Aspire MCP, dotnet-artisan, and the Three-Catalogue Strategy for Codex CLI
When this blog last covered .NET and Codex CLI in late March, the story was straightforward.
The Codex CLI Companion Tools Ecosystem: Token Monitors, Orchestrators, and Community Collections
Codex CLI has crossed 75,000 GitHub stars, 14.5 million monthly npm downloads, and three million weekly active users .
Codex CLI and Docker Model Runner: Containerised Local Inference for Private, Cost-Free Coding Agents
Running Codex CLI against the OpenAI API is the default path — and for good reason. GPT-5.5's 400K context window, server-side compaction, and prompt.
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.
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.
Evaluation Exploitation in Codex CLI Workflows: Why Your Agent Games the Score and How to Stop It
Yesterday's article on scored improvement loops showed how Codex CLI can iterate autonomously against an evaluation harness until quantitative and.
Building Agent-Friendly CLIs with Codex CLI: Composable Tool Design for the Agentic Era
The fastest-growing consumer of command-line interfaces in 2026 is not a person — it is an AI agent.
Architecture Decision Records with Codex CLI: Automated ADR Generation, Governance, and the Agent-Architecture Gap
Every team says they will write Architecture Decision Records. Few actually do. The friction is well understood.
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 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 for Game Development Teams: Unity MCP, Godot MCP, and Agent-Driven Game Workflows
Game development sits at an interesting intersection for AI coding agents. The codebase is highly structured (scenes, components, shaders, scripts).
Codebase Onboarding with Codex CLI: Using AI Agents to Ramp Up on Unfamiliar Projects
Every developer knows the feeling: you join a new team, clone a repository with 800 files across 40 directories, and spend the next fortnight piecing.
Database Schema Migrations with Codex CLI: Atlas Skills, ORM Workflows, and Agent-Driven Migration Pipelines
Database schema migrations sit at an uncomfortable intersection: they demand precision (a wrong column drop is irreversible), context awareness (what does.
Codex CLI for Frontend Performance Optimisation: Lighthouse MCP, Core Web Vitals Skills, and Agent-Driven Performance Budgets
Only 47% of websites reach Googles good Core Web Vitals thresholds in 2026. INP remains the most commonly failed metric.
SDD Tooling for Codex CLI: spec-kit, cc-sdd, and codex-spec Compared
Spec-Driven Development (SDD) has gone from academic curiosity to mainstream practice in under six months. GitHub's spec-kit crossed 80,000 stars by April.
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.
Codex CLI for Elixir and Phoenix Teams: Tidewave MCP, AGENTS.md, and Functional Agent Workflows
Elixir and Phoenix occupy a singular position in the AI-assisted development landscape. The BEAM's functional paradigm — immutable data, explicit process.
Codex CLI for Kotlin and Android Teams: Android CLI, Skills, Jetpack Compose, and Agent-Driven Mobile Workflows
Android development in 2026 has become one of the strongest use cases for agentic coding. Google's release of Android CLI and Android Skills on 16 April.
Codex CLI for Microservices: Cross-Service Development, Multi-Repo Patterns, and Distributed Workflows
Microservices architectures pose a unique challenge for AI coding agents: the work you need done rarely fits inside a single repository.
Codex CLI for Svelte and SvelteKit Teams: Runes, Svelte MCP, and Agent-Driven Component Workflows
Svelte 5's runes system fundamentally changed how reactivity works in the framework — replacing implicit $: declarations with explicit primitives like.
Codex CLI for Vue and Nuxt Teams: Composition API, Pinia, Vitest, and Agent-Driven Component Workflows
Vue 3.6 and Nuxt 4.4 represent the current state of the art for the Vue ecosystem . Combined with Codex CLI v0.125, Vue teams now have a mature.
Codex CLI for Embedded Systems and Firmware Teams: Hardware-in-the-Loop, RTOS Patterns, and Agent-Driven Bring-Up
Embedded firmware development has long been the domain least affected by AI coding assistants. The reasons are well understood: register-level programming.
Codex CLI for Swift and iOS Teams: Xcode MCP, SwiftUI Skills, and Agent-Driven Apple Platform Development
Apple's integration of agentic coding into Xcode 26.3 in February 2026 transformed how iOS teams work with AI coding agents . Codex CLI now operates as both.
Test-Driven Development with Codex CLI: Agent-Driven Red-Green-Refactor Workflows
The single most reliable technique for getting consistently correct output from a coding agent is also one of the oldest ideas in software engineering.
Codex CLI for Django and FastAPI Teams: AGENTS.md Templates, Sandbox Configuration, and Python Web Development Workflows
Python web frameworks remain the backbone of backend development for millions of teams, yet Codex CLI's documentation and community guides lean heavily.
Codex CLI for PHP and Laravel Teams: Boost MCP, Pest Workflows, and Composer Sandbox Patterns
PHP powers roughly 75% of websites with a known server-side language, and Laravel remains the dominant framework — Laravel 13 shipped on 17 March 2026 with.
Cross-Agent Skill Portability: Managing Skills Across Codex CLI, Claude Code, and Copilot
The Agent Skills specification, originally developed by Anthropic and released as an open standard in late 2025, has become the lingua franca for extending.
Automated Accessibility Testing with Codex CLI: WCAG Compliance from Code Generation to CI Gate
As of 24 April 2026 the US Title II ADA deadline requires public entities serving populations of 50,000 or more to meet WCAG 2.1 Level AA conformance.
Codex CLI for React Native and Expo: First-Party Skills, Plugins, and Mobile Development Workflows
React Native and Expo have always attracted developers who want to move fast. In 2026, that ethos extends to AI-assisted development.
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.
Automated Harness Synthesis: What AgentFlow's Typed Graph DSL Means for Codex CLI Orchestration
Two independent research papers dropped within 48 hours of each other in late April 2026, and together they crystallise a thesis that practitioners have.
Codex CLI Plugin Marketplace: Building, Distributing, and Managing Extensions at Scale
OpenAI launched the Codex plugin marketplace on 26 March 2026, packaging skills, MCP servers, and app integrations into shareable, installable bundles that.
Legacy Code Archaeology with Codex CLI: Understanding, Documenting, and Safely Modernising Unfamiliar Codebases
Every senior developer has faced it: a critical system written by people who left years ago, sparse documentation, no tests.
Codex CLI for Ruby on Rails Teams: AGENTS.md, Bundler Sandboxing, and RSpec Workflows
Ruby on Rails remains one of the most productive full-stack frameworks in production, powering applications from Shopify to GitHub.
Prompt Injection Defence for Codex CLI: Attack Vectors, Real CVEs, and Practical Hardening
Prompt injection remains OWASP's number-one vulnerability for LLM applications in 2026, appearing in an estimated 73% of production AI deployments.
Codex CLI Plugin System: Building, Sharing, and Managing Reusable Agent Workflows
Codex CLI v0.122 elevated plugins from an app-only curiosity to a first-class workflow primitive across the entire Codex surface.
Safe Dependency Management with Codex CLI: Why AI Agents Get It Wrong and How to Fix It
Dependency management is one of the most natural tasks to hand to a coding agent. Upgrade React to v20, patch all critical CVEs, migrate from Express.
Codex CLI + Terraform/IaC: Infrastructure Agent Patterns
Infrastructure as code demands precision that most AI coding assistants struggle to deliver. Terraform's declarative semantics, provider-specific resource.
Codex CLI for Data Engineering: dbt, Airflow, and Pipeline Generation
Data engineering workflows—building dbt models, orchestrating Airflow DAGs, validating data quality—are repetitive, context-heavy, and ripe for agentic.
Formal Architecture Descriptors: Cutting Codex CLI Navigation Overhead by a Third
Your AGENTS.md file tells your coding agent what to do. But does it tell the agent where things are in a way that actually reduces navigational overhead? A.
Why Coding Agents Fail at Navigation (and How AGENTS.md File Maps Fix It)
Your coding agent can refactor a function, write tests, and call APIs — but ask it to find the right file in a monorepo.
Benchmarking Your Agentic Pod: What CocoaBench, HiL-Bench, and AAR Tell Us About Agent Limits
Three benchmarks published in April 2026 expose where frontier coding agents actually break down — and the failure modes they reveal map directly onto.
The ExecPlan Pattern: Structuring 7-Hour Codex Sessions with PLANS.md
The single biggest determinant of whether a Codex session completes a complex task or drifts into incoherence is not the model — it is the planning.
The Harness Effect: Why the Same Model Scores 16 Points Higher in a Different Tool
Claude Opus running inside Cursor scores 93% on Terminal-Bench 2.0. The same model running inside Claude Code scores 77%. That is a 16-point differential.
gh skill: Supply-Chain-Secure Agent Skills from GitHub CLI to Codex CLI
On 16 April 2026, GitHub shipped gh skill in CLI v2.90.0 — a first-class subcommand for discovering, installing, pinning, updating, and publishing agent.
What MIT Gets Right (and Misses) About Agentic Coding: From Missing Semester to Enterprise Patterns
In January 2026, MIT's Missing Semester of Your CS Education course added a dedicated Agentic Coding lecture to its curriculum. For a course that has spent.
Cross-Model Security Testing for AI-Generated Code: Building a Defence-in-Depth Pipeline
AI coding agents write functional code at impressive speed. They do not, however, write secure code at impressive speed. Veracode's Spring 2026 GenAI Code.
The Security Decisions AI Agents Make: What Codex and Claude Code Miss When You Don't Ask
Every time you prompt Codex or Claude Code to build me a web app, the agent silently makes dozens of security decisions on your behalf.
Filesystem-Aware Skill Loading and Unix Socket Sandbox Allowlists
Version 0.121.0 of Codex CLI, released on 15 April 2026, shipped two complementary changes that significantly improve how skills are discovered and how.
Language Doesn't Matter Anymore: What Kent Beck's Shift Means for Coding Agents
Kent Beck — creator of Extreme Programming, co-author of the Agile Manifesto, pioneer of Test-Driven Development.
TDAD and Graph-Based Test Impact Analysis: Cutting Codex CLI Regressions by 70%
Autonomous coding agents resolve issues faster than most developers expect. What they also do — with uncomfortable regularity — is break things that already.
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.
The Silent Guessing Problem: Why AI Coding Agents Don't Ask Clarifying Questions and What AMBIG-SWE Means for Codex CLI
A Carnegie Mellon research team has published one of the most practically important findings for agentic coding in 2026: when given ambiguous instructions.
Codex CLI for Technical Debt Reduction: Automated Refactoring, Dead Code Detection, and Dependency Upgrades
Technical debt accumulates silently — unused imports, deprecated API calls, dead functions that nobody dares delete.
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.
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.
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.
Cloud Agent Plugin Suites: AWS Led, Azure Followed, and the GCP Gap
In February 2026, AWS Labs open-sourced awslabs/agent-plugins — the first major cloud provider plugin suite built for AI coding agents . Five weeks later.
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.
Codex CLI and Database Migrations: Atlas Skills, MCP Servers, and Schema-Driven Workflows
Database schema migrations sit at the intersection of precision and risk — the kind of task where agentic coding either shines or causes real damage. Codex.
Codex CLI and Nx: Agent Skills, Project Graph Awareness, and Self-Healing CI for Monorepos
Monorepos are where AI coding agents stumble hardest. A 200-package Nx workspace has implicit dependency chains, shared libraries, generator conventions.
Building Codex CLI Plugins: Architecture, Manifests, and Enterprise Distribution
Since their launch on 26 March 2026, Codex plugins have matured from a curiosity into a genuine distribution mechanism for reusable AI workflows.
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.
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.
Codex CLI for Data Science Teams: Pandas, Polars, and Notebook-Adjacent Workflows
Data scientists live in a different world from application developers. The work is exploratory, the toolchain revolves around DataFrames and visualisations.
Codex Marketplace: Plugin Distribution and the Plugin Marketplace Add Command
OpenAI's plugin marketplace, launched on 27 March 2026, transforms Codex from a standalone coding agent into an extensible platform. Plugins bundle skills.
The Codex CLI Ecosystem Map: Navigating 245+ Community Tools, Skills and Subagents
Twelve months ago, Codex CLI was a single binary with a handful of configuration options. Today, a curated list on the official OpenAI Codex GitHub.
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.
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.
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.
Agents Can Only Move as Fast as Their Platform: What KubeCon 2026 Means for Codex CLI
At KubeCon EU 2026 in Amsterdam, Whitney Lee (Datadog) and Viktor Farcic (Upbound) delivered Choose Your Own Adventure: AI Meets Internal Developer.
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.
Codex CLI Skills: When a 10-Word Prompt Beats a Production Artefact
The skill ecosystem for AI coding agents has exploded. OpenAI's skills catalogue ships system-level skills like skill-creator and skill-installer bundled.
NanoClaw and Codex CLI: Building an Always-On Agentic Assistant
Codex CLI excels at interactive coding sessions and scripted automation via codex exec. But what happens when you need an agent that persists across hours.
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.
Cross-Platform Agent Portability: One SKILL.md for Every Runtime
The AI coding agent landscape has fragmented into over a dozen serious contenders.
Tessl Skill Evaluation Framework: Treating Agent Skills as Production Software
You have written a skill for your coding agent. It looks right. It seems to work when you try it.
AGENTS.md as an Open Standard: Cross-Tool Portability Under Linux Foundation Governance
The AGENTS.md file that sits in your repository root has quietly become the most consequential configuration standard in agentic coding.
Learning Plan for Becoming a Codex CLI Expert
Codex CLI is not a chatbot that writes code. It is an agentic coding harness — a system that reads your files, runs commands, makes changes, and works.
Codified Context: The Three-Tier Knowledge Architecture for AI Coding Agents
Dumping everything into a single AGENTS.md file works until it doesn't. At some point—typically around 20,000 lines of codebase—you hit the context wall.
Automating the Cross-Model Review Loop: Three Levels from SKILL.md to Multi-AI Pipeline
The cross-model review pattern — where one AI writes code and a structurally different AI reviews it — has become a core quality practice in agentic.
Codex CLI for Kubernetes and Cloud-Native Teams: AGENTS.md, Helm Workflows, and the Agent Sandbox CRD
Kubernetes YAML is notoriously error-prone. Helm templates add Go template syntax on top. Operator development demands reconciliation loops, CRD schemas.
Codex CLI for .NET and C# Teams: Skills, AGENTS.md, NuGet Sandboxing and Azure OpenAI
The .NET ecosystem has a richer Codex integration story than most developers realise. Between the official dotnet/skills catalogue published by the .NET.
Codex CLI for Rust Teams: AGENTS.md, Cargo Workflows, and Workspace Patterns
Codex CLI is written in Rust. That is not a coincidence — it means the OpenAI team has already worked out the patterns for using Codex to maintain a large.
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 CLI for Infrastructure as Code: Terraform, Pulumi and Ansible Automation
Infrastructure as Code occupies a peculiar place in the agentic coding landscape. The feedback loops are slower than application code.
Codex CLI for Java and Spring Boot Teams: AGENTS.md, Maven Sandboxing, and Gradle Workflows
Java is one of the most-used languages in enterprise software, yet Codex CLI guidance skews heavily toward Python, TypeScript, and Go. This article fills.
Codex CLI for Go Teams: Skills, AGENTS.md and Go 1.26 Workflows
Go's explicit error handling, strict formatting conventions, and idiomatic concurrency model make it both an ideal and a demanding language for agentic.
Codex CLI Plugin System: Bundling Skills, MCP Servers, and App Connectors
Codex CLI v0.117.0 (released March 26, 2026) elevated plugins to a first-class workflow primitive.
Codex CLI and Vercel: AI Gateway, Skills and the Vercel Plugin Ecosystem
Vercel's investment in AI coding agents reached critical mass in March 2026 with two distinct — but complementary — integration surfaces for Codex CLI teams.
gstack: Garry Tan's Production Claude Code Skills Toolkit
gstack is Garry Tans open-source software factory: 31 slash-command skills for Claude Code (and Codex CLI, Cursor.
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 for Jupyter Notebooks and Scientific Python
Jupyter notebooks are the lingua franca of scientific Python, yet the .ipynb format is one of the environments where Codex CLI historically performs least.
Codex CLI for dbt and Data Engineering Workflows
Data engineering is one of the fastest-growing segments of software development, yet the Codex CLI ecosystem has produced almost no content targeted at data.
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.
Spec-Driven Development with Codex: Writing Specifications Before Code
Test-Driven Development (TDD) tells the agent when it is done. Spec-Driven Development (SDD) tells it what to build in the first place. The two approaches.
Test-First Development with Codex: Using TDD as the Agent Feedback Loop
The single biggest problem with autonomous agents is knowing when theyre done. A human developer can feel when code feels right. An agent cannot.
The AGENTS.md Bloat Problem: When More Context Makes Agents Worse
A rigorous 2026 study from ETH Zurich found that LLM-generated context files actively reduce agent task success rates.
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.
WORKFLOW.md: Version-Controlling Your Agent's Behaviour
When you adopt Symphony (or any harness-based orchestration), you face a configuration challenge: how do you define how your agents should behave, and keep.
Codex CLI for Frontend Development: React, TypeScript and Modern Toolchains
Frontend development with Codex CLI requires deliberate configuration. Without it, Codex will make reasonable guesses — often the wrong ones. It might reach.
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.
Skills as Progressive Disclosure: Architecture Differences Between Skills and MCP
Two mechanisms exist for giving Codex CLI access to external knowledge and tools: Agent Skills and the Model Context Protocol (MCP). On the surface they.
The Agentic Engineering Pod: Three Roles, One Shared Context Layer
Traditional software team structures were not designed for agentic delivery. They are built around specialisations: product managers own requirements.
Agentic Primitives Compared: Codex CLI vs Claude Code vs Gemini CLI
All three tools — OpenAI Codex CLI, Anthropic Claude Code, and Google Gemini CLI — converge on the same set of agentic primitives. They read instructions.
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.
Effective Prompting Strategies for Codex CLI
Based on official OpenAI documentation, community discussion, and developer best practices. Published 2026-03-26.
Writing Effective SKILL.md Files for Codex CLI
A skill is a directory of instructions, scripts, and resources that an agent can discover and load on demand.