OpenAI releases official plugin to run Codex agent inside Anthropic's Claude Code CLI

·1 views

OpenAI launched codex-plugin-cc on March 30, 2026, an Apache-2.0-licensed JavaScript plugin that lets users run the Codex coding agent directly within Anthropic's Claude Code command-line interface. The plugin does not introduce a new runtime but instead delegates to a locally installed Codex CLI, reusing existing authentication and configuration. Full setup requires four slash commands inside an active Claude Code session, not the two steps widely circulated online, as skipping the mandatory reload step leaves the plugin dormant. Users need Node.js 18.18.0 or later and either a ChatGPT subscription or an OpenAI API key to get started. The plugin has seen active development since launch, reaching version 1.0.6 by July 8, 2026, and brings Codex — which surpassed 5 million weekly users by June 2026 — into a rival vendor's ecosystem.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Audit of 36 MCP servers finds a third failing AI agents due to poor documentation

A developer who integrates MCP connectors into production AI agents built a tool called mcpgrade to audit the quality of Model Context Protocol servers beyond basic spec compliance. Scanning 36 popular servers revealed that 11 — including official offerings from MongoDB, Notion, Airtable, and GitHub — scored D or F grades. The dominant failure was rule D004: parameters lacking descriptions, with firecrawl logging 132 such errors out of 134 total and todoist hitting 110. Most failing servers auto-generate schemas from Zod or OpenAPI definitions without adding human-readable descriptions, leaving AI models unable to correctly select or call tools. The author argues that adding parameter descriptions is the single highest-leverage fix developers can make to improve agent reliability.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

AI Bubble Fears Are Real, But Professionals Can Still Prepare and Adapt

AI has moved well beyond research labs and is now embedded in industries ranging from healthcare and finance to marketing and software development. While the technology delivers genuine productivity gains, analysts warn that valuations, infrastructure spending, and business promises may be outpacing actual adoption and profitability — classic signs of an investment bubble. Experts note that AI typically eliminates specific tasks rather than entire professions, with repetitive, rules-based, and text-heavy roles facing the most near-term disruption. To stay relevant, professionals are advised to build skills in AI literacy, data interpretation, workflow design, and responsible AI governance. Emerging regulatory frameworks such as the EU AI Act and NIST AI Risk Management Framework are also creating new career paths in AI auditing, model risk, and human-in-the-loop operations.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

JavaScript Core Concepts Explained: Variables, Closures, Scope and More

A developer learning guide published on DEV Community breaks down essential JavaScript fundamentals covered in a third-week study session. The article explains key concepts including variable declarations using var, let, and const, hoisting behavior, and how the JavaScript engine processes code through execution context and the call stack. It also covers lexical scope and the scope chain, describing how inner functions can access variables from their outer functions, a mechanism that enables closures. Additional topics include the this keyword, and clean coding principles such as DRY and KISS. The guide is aimed at beginner developers seeking to understand what happens behind the scenes when JavaScript code runs.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Claude Code's SKILL.md format explained: how to write skills that trigger correctly

Claude Code skills are reusable, structured instruction sets designed to replace repetitive procedures users paste into chat sessions. Unlike entries in CLAUDE.md, a skill's body only loads into context when the skill is actually invoked, keeping overhead minimal. Each skill lives in a dedicated directory with a SKILL.md file containing frontmatter fields — most importantly a description, which Claude reads in every session to decide when to activate the skill. The description acts as the trigger mechanism, so it should mirror the natural phrases a user might say, while the body holds the full step-by-step procedure. Optional frontmatter settings like disable-model-invocation and allowed-tools give developers control over whether a skill fires automatically or only on explicit user command.

0 comments Read more at DEV Community