OpenAI Official Plugin Strongly Integrated into Claude Code

marsbitPublicado em 2026-03-31Última atualização em 2026-03-31

Resumo

OpenAI has officially released the "codex-plugin-cc" on GitHub, enabling developers to integrate OpenAI’s Codex model capabilities directly into Anthropic’s command-line development tool, Claude Code. This cross-platform integration breaks down ecosystem barriers between major AI tools, allowing developers to leverage the strengths of both models without switching environments. With simple configuration, Claude Code becomes a versatile programming assistant combining the advantages of both companies. Key features include: - Standard code review via the `/codex:review` command, providing expert improvement recommendations and double-checking for logic errors. - Adversarial review using `/codex:adversarial-review`, which challenges design decisions to identify potential performance bottlenecks or security risks. - Task delegation through `/codex:rescue`, allowing complex debugging or repair tasks to be handed off to a Codex sub-agent for collaborative problem-solving. This integration enhances code quality and development efficiency through multi-model collaboration.

Recently, the AI developer community welcomed a major update: OpenAI officially released an open-source project named codex-plugin-cc on GitHub. This plugin allows developers to directly utilize the capabilities of OpenAI's Codex model within the command-line development tool Claude Code, introduced by Anthropic.

This "cross-brand" integration breaks down the ecosystem barriers that previously existed between major AI model tools, enabling developers to leverage the technical strengths of both industry giants without switching environments. With simple command configurations, Claude Code instantly transforms into an all-in-one programming assistant that combines the best of both.

Empowered by this plugin, users can initiate a standard read-only code review using the /codex:review command to receive professional improvement suggestions from Codex. This dual verification mechanism effectively catches logical vulnerabilities that a single model might miss, adding a "double insurance" for code quality.

More uniquely, its "adversarial review" feature allows developers to use /codex:adversarial-review to actively request Codex to challenge existing design decisions. This mode is specifically designed to stress-test the rationality of system architecture, uncovering potential performance bottlenecks or security risks from a "fault-finding" perspective.

Additionally, the plugin introduces a task delegation mechanism, enabling users to transfer complex debugging or repair tasks to a Codex sub-agent via /codex:rescue. This collaborative model achieves automatic task distribution, allowing the primary model and auxiliary models to each focus on their respective areas of expertise.

github:https://github.com/openai/codex-plugin-cc

Perguntas relacionadas

QWhat is the name of the official OpenAI plugin that integrates with Claude Code?

AThe plugin is called codex-plugin-cc.

QWhat is the primary function of the /codex:review command in the new plugin?

AThe /codex:review command is used to initiate a standard read-only code review to get professional improvement suggestions from the Codex model.

QWhat unique feature does the /codex:adversarial-review command provide?

AThe /codex:adversarial-review command enables an 'adversarial review' function, which actively challenges existing design decisions to stress-test the system architecture and uncover potential performance bottlenecks or security risks.

QHow does the /codex:rescue command facilitate task management?

AThe /codex:rescue command allows users to delegate complex debugging or repair tasks to a Codex sub-agent, enabling a collaborative model where the main and auxiliary models work in their respective areas of expertise.

QWhere was the codex-plugin-cc project officially released?

AThe project was officially released by OpenAI on GitHub.

Leituras Relacionadas

Coldcard Hardware Wallet Hacked: 594 Bitcoin Withdrawn in 25 Minutes

The Coldcard hardware wallet has been compromised, with hackers stealing approximately 594.5 Bitcoin (~$40 million) from 500 addresses in just 25 minutes. The root cause was a critical software bug, undetected for five years, which disabled the device's secure chip for generating true random numbers. This led to the creation of private keys based on predictable data like the processor's serial number, drastically reducing cryptographic security. The attackers exploited this offline by brute-forcing possible seed phrases, finding active addresses on the public ledger, and signing transactions. Initially, Coinkite (Coldcard's maker) claimed only older models were at risk but later admitted all devices running the compromised firmware were vulnerable. CEO Rodolphe Novak (NVK) apologized but ruled out financial compensation for affected users. To secure funds, owners must urgently update their firmware to specific safe versions, generate a completely new seed phrase on the updated device, and transfer all assets to new addresses created with that new seed. While a BIP-39 passphrase can help, it does not replace this migration process. Other Coinkite products like TAPSIGNER were not affected. This incident underscores that even specialized hardware requires rigorous, independent code audits, especially for cryptographic functions. It parallels past failures, like a 2006 OpenSSL bug in Debian, and raises questions about whether automated code analysis can ever fully replace human scrutiny in critical security areas.

cryptonews.ruHá 1h

Coldcard Hardware Wallet Hacked: 594 Bitcoin Withdrawn in 25 Minutes

cryptonews.ruHá 1h

Trading

Spot
活动图片