Qodo's Codex plugin brings code review context into coding sessions

Giving Codex the view of the whole system

Qodo co-founder and CEO Itamar Friedman calls his company's product "the coding agent's best friend." The problem it targets is scale. Friedman describes customer environments that can span 10,000 or more repositories, where a local code change can break a downstream service even if it looks correct on its own.

"Codex is really good at taking a local task and completing it in an efficient way," Friedman says. Qodo's plugin adds access to codebase knowledge, organizational rules and independent review through Qodo's Agentic Toolbox. With that context, Codex can account for dependencies across repositories, including those hosted by different Git providers or services connected through Kafka.

"Qodo will make that connection and will help Codex look at the software as a whole and not miss those P0 bugs," Friedman says.

Review inside the same session

The workflow has two steps. Before Codex starts writing code, it can use the plugin to retrieve relevant codebase rules, along with pull request history and patterns. After Codex makes its changes, Qodo reviews them and returns its findings directly to Codex in the same session, before the developer opens a pull request.

Nnenna Ndukwe, Qodo's AI Developer Relations Lead, says she sees developers using this setup to build features and tackle technical debt with GPT-6 models in Codex, automating the handoff between Codex's coding work and Qodo's independent review.

Friedman describes coding and review agents as "yin and yang": one creates code, the other challenges it. Each role needs its own setup and context and may involve multiple agents. His vision is for the agents to discuss findings and "surface only what they don't accept" for human review. Developers would then act as planners and reviewers, able to inspect unresolved issues alongside the agents' discussion, context and prior developer decisions. "That's how you create trust," he says.

Daily use and the Decisions API

Inside Qodo, Ndukwe has been using GPT-6 Astra's Extra High and Ultra effort settings in her own automated development workflows and in knowledge work. She schedules Codex to report on what she accomplished during the week and where she could focus next, to research conversations about agentic engineering on social platforms, and to analyze her code changes and suggest agent skills to create or refine.

Friedman also sees a role for OpenAI's recently launched Decisions API. Rather than relying on language models for every decision, Qodo could use it to choose which rules and agent skills apply at each stage of development. In his example, the API could select which of 200 rules need checking before a language model reasons through the relevant ones. Friedman says this would make selection faster and cheaper while improving review quality.

What it means for developers

Qodo's pitch is a division of labor: company knowledge guides coding agents, independent review checks their work, and human expertise resolves the questions that remain. Friedman describes the result as a software factory, a system customers could assemble and own, bringing coding and review agents together with an understanding of how software changes in production.

For teams working across many repositories, the plugin is aimed at catching cross-service problems before a pull request is opened, while keeping developers focused on the issues the agents cannot settle themselves.