SENS ADVISOR

Applied AI Notes · November 2026

nouez: Claude Code Asks Codex for a Second Opinion

An open-source MCP server that lets Claude Code consult a read-only Codex session, and open Claude Code sessions on my computer from my phone.

When I need a second reader

Some steps in my work are hard to undo: a production release, deleting files, a paid experiment, publishing a note, or treating an analysis as a conclusion. Before each of them I want a second reading from a model trained by another company, which can catch what the model that did the work missed. When Codex reviewed my note on agent harnesses, it found a diagram saying the agent loop ends when the model stops asking for tools, although some harnesses keep it going, and a sentence calling fixed workflows what “most business requests” describe, when my own survey put them at 41%. Neither error would have broken anything, but both would have misled a reader.

Without a bridge, getting that reading means two terminals and copying questions and answers between them by hand. nouez removes that step. It also lets me ask a Remote Control session on my phone to open or resume another project on my computer.

How I use it

Claude Code does the work and owns it. When a step needs review, Claude starts a Codex “consultant” in the same project, sends it the relevant files and a narrow question, and keeps working while the consultant reads. The consultant’s local file access is read-only, and Claude applies any edit it proposes, so one author stays responsible for the result. I can open the consultant in a terminal pane beside Claude to watch its work. The reply wakes Claude when it arrives, and I treat the consultant’s findings as claims to check against their sources, in the same way as the draft’s.

My consultations fall into these groups, roughly largest first:

Many of them ask for a verdict in a fixed format, such as go, changes or no-go, followed by what the consultant did not check, so that silence is not mistaken for approval.

From my phone, I ask a Remote Control session to open a new Claude Code session for a project, either a new folder or an existing one, and it appears in the app’s session list a few seconds later. An earlier conversation in that project can be picked up again, and a session that is stuck can be listed and closed from the phone too.

Opening a Claude Code session from the phone From the Claude app on my phone, I ask an existing Remote Control session to open a project. In the normal phone workflow, nouez opens nothing in an untrusted folder until I confirm trust. It then starts Claude Code with Remote Control in a new terminal window. The new session appears in the app once connected. Phone the Claude app MY COMPUTER 1Claude Code with Remote Control 2nouez checks folder trust 3New window in the chosen project ask the new session appears in the app's session list If untrusted: ask me first; open only after yes.
Something on the computer must already be running and connected, such as a Claude Code session with Remote Control. An earlier conversation in the project can be picked up instead of a new one. Project-specific approvals can still require an answer on the computer.

What nouez is, and why MCP

nouez is a small MCP server written in Python using only the standard library, so it needs no packages. Claude Code talks to it over the Model Context Protocol, and it talks to the Codex app-server daemon on the same computer, where the consultant sessions live and keep their whole conversation until they are stopped.

A consultation through nouez Claude Code sends a question through nouez's MCP server to a consultant on the local Codex daemon. The consultant's local file access is read-only. For replies that take longer than the initial wait, Claude starts a separate background waiter, which wakes it when the reply is ready. Claude decides which findings to act on and edits the project files. Claude Code does the work nouez MCP server + waiter Codex daemon holds the sessions READ-ONLY SANDBOX Consultant a Codex session question later replies arrive via a background waiter Project files edits reads only
Solid arrows: the question and Claude's edits. Dashed: the reply and the consultant's reading. The consultant keeps its conversation until it is stopped, so a later question in the same project reuses it. The background waiter is a separate process from the MCP server.

I chose MCP so that Claude Code can call the bridge as named tools, with a permission rule for each tool and one user-level setup across projects, including sessions opened from the phone. The server’s instructions tell Claude when to use each tool, and the Python code fixes the consultant’s sandbox settings instead of leaving Claude to write the command. A fixed script could enforce the same settings, and a personal skill could also be available in every project, but neither gives Claude a set of named tools with their own permissions.

How it has grown

nouez began as a bridge for consulting Codex. Later versions added more, as my use of it grew:

My harness and models

Claude Code is my main harness, running Claude Opus 5.5. My consultants run on gpt-6.1-sol at high reasoning effort, which is set in my Codex configuration. I find the pairing works well, because the two models are trained by different companies and read the same files differently. They are not the only choice: a consultant can use any model that Codex offers, and Claude can switch a consultant’s model or effort for a single hard question and then switch it back.

Try it

The code, with setup instructions, the tested versions and a full security note, is at github.com/jibarix/nouez under the MIT licence. It needs Claude Code, the Codex CLI and Python, and its doctor command checks the setup.

Before you enable it, know its limits. Agreement between two models does not establish truth, since both can share a gap in their knowledge. A consultant can read anything its sandbox permits, typically including files outside its project. Any Claude Code session with the server enabled can message any Codex session on the computer, and sessions I opened myself keep their own permissions and may be able to write. nouez works on one machine only, and it depends on an experimental Codex protocol that can change between releases, which is why the repository records the last combination of versions known to work.

Method and limits

The description of nouez follows its README, changelog and code at version 0.12.3. The harness-note examples compare that note’s drafts with its published text. The kinds of consultation come from the messages Claude Code sent to consultants on my laptop, sorted by an agent with keyword rules and checked by hand on a sample; about one label in ten was wrong, so the order of the kinds is approximate.

Use of AI tools

Claude (Anthropic) drafted this text under my direction, and a Codex model (OpenAI), reached through nouez, reviewed it; I checked the claims and the final wording.