MODULE 2.2 / 5 OF 9

Codex + Claude: one does the work, the other reviews it

Explain how to use Claude and Codex on the same project, covering the Use Both kit’s six levels, the routing card, and the difference between claudex and Use Both.

Area page: eventos.inema.pro/codex-claude/en/ · in the menu: “use both together”

0% 0 of 0
01 / CODEX-CLAUDEOne plans, the other critiques02 / CODEX-CLAUDEThe six levels of Use Both03 / CODEX-CLAUDEWho Does What: The Route Card04 / CODEX-CLAUDEOne Path: claudex × Use Both05 / CODEX-CLAUDECreate Images with Codex, Step by Step06 / CODEX-CLAUDEA First Step and All the Projects
The 6 topics in this module. At the end, you’ll fill out the area worksheet.
6 topics
~20 min reading and practice
1 area worksheet
1 ready-to-use prompt

1One plans, the other critiques

What it is

The Codex + Claude area’s central idea is: “One plans, the other critiques. Use both together.” Claude and Codex complement each other when each handles one part and the other checks the real artifact: the actual file, diff, or image. The rule that runs through it all: the second assistant gets the same brief and the real artifact, never a vague summary of what the first assistant did. The page is INEMA’s meeting place for the two tools. It brings together the Use Both kit’s six levels, a table showing who does what, and cards for all courses and projects. To move from one tool to the other, use the sister area Claude → Codex.

Why learn it

This is for people who already have Claude Code and Codex and don’t want to choose just one. A second opinion from another model catches issues the author may miss.

Key concepts

one does the work, the other reviews it; real artifact; same brief; it’s not Claude or Codex; sister area Claude → Codex

In practice

A developer writes a feature plan with one assistant and gives the same file to the other for a read-only review. The critique catches a missing test before anyone writes a line of code.

✓ Do

Choose a recent plan or document of yours and note who could review it using the same brief, without a summary.

✗ Avoid

Judging the area by its name: read the main idea on the page before deciding if it’s for you.

2The six levels of Use Both

What it is

The Use Both kit organizes working with both tools into six workflow levels, with ready-to-use prompts and two small skills. Level 1 is having them discuss: one writes the plan, the other critiques the same file in read-only mode, for no more than two rounds. Level 2, optional, is generating images, only if an image tool is available in the session and after checking access and billing. Level 3 is splitting building and review: one builds in a branch, the other reviews the diff against the brief and test results. Level 4 is supervised computer use, with passwords, payments, and important submissions kept under your control. Level 5 is a goal with a stop condition, observable success, and limits on files, rounds, and spending. Level 6 is handoff and prime: the handoff records the state in a portable file, and prime makes the next assistant read and verify that state before continuing.

Why learn it

The levels give you a path to follow: you can start by discussing a plan and move up only when you need to. Each level includes limits to prevent uncontrolled spending or actions.

Key concepts

discuss; generate images; build and review; supervised computer use; goal with a stop condition; handoff and prime

In practice

A team uses level 3: one assistant implements a fix in a branch, and the other reviews the diff along with the test output. Tests and human approval determine what goes into the project.

DiscussImagesBuildComputerGoal with stopHandoff/prime
The six Use Both levels, from discussing a plan to switching sessions; each has its own limit.

3Who Does What: The Route Card

What it is

The route card is a table in the kit that says, for each task, who does the first pass, who does the second, and what counts as done. Plan the work: Claude / Opus plans, Codex critiques the assumptions, and the result is a plan with scope and acceptance tests. Build a feature: Claude / Opus builds, Codex reviews the diff, and done means tests pass and findings are resolved. Tackle a difficult bug: Codex works toward a bounded goal, with tests and a human checkpoint. Switch sessions or models: create a handoff snapshot, and prime checks the current state. The page notes that these are "editorial choices, not a measured model ranking": try them and keep the route that produces the best evidence.

Why learn it

Having a starting route saves you from debating from scratch for every task. Knowing it is not a benchmark keeps you from treating it as a fixed rule.

Key concepts

first pass; second pass; finish line; editorial choices, not a ranking; models and billing vary by account

In practice

An analyst needs to review a requirements document. The route says either tool can write it, while the other checks the facts and requirements; done means every required claim has evidence.

Steps to try

  1. Open the area page beside this lesson.
  2. Choose a task from your week and fill in the route card’s three columns: first pass, second pass, and finish line.
  3. Write one sentence about what changed in your understanding.
PlanClaude; Codex critiquesBuildClaude; Codex reviewsHard bugCodex with a goalSwitch sessionhandoff and prime
Four lines on the routing card: who starts and who checks. These are editorial choices, not measured rankings.

4One Path: claudex × Use Both

What it is

The page organizes courses and projects into one path: understand, migrate or stay tool-agnostic, use both together, and automate the discussion. The common link is the project’s Markdown files, such as AGENTS.md, tasks, and handoffs, which any runtime can read. Two different tools appear along this path. claudex is a Claude Code plugin, or software: Claude writes PLAN.md and Codex critiques it from 3 angles, in a loop until LGTM or N rounds. Use Both is a method kit, with a guide, prompts, templates, and 2 skills. It covers all six workflows, manually or semiautomatically. The page sums it up: they are complementary; for a large plan, use claudex; for everything else, such as reviewing a diff, setting a goal with a stop condition, or switching sessions, use Use Both.

Why learn it

Knowing which layer each tool works at helps you avoid installing software to solve a process problem, or the other way around.

Key concepts

Understand → Migrate → Use both → Automate the discussion; claudex = software; Use Both = method; LGTM; complementary

In practice

A technical lead has a large architecture plan and uses claudex for the automated discussion. For day-to-day work, such as reviewing diffs and switching sessions, the team follows the Use Both levels.

✓ Do

Compare the "Limit" row in the claudex × Use Both table and note how many rounds each recommends.

✗ Avoid

Jumping to the tool or course without understanding the problem the area addresses.

UnderstandMigrateUse bothAutomate debate
Courses and kits cover steps along the same path, connected by the project’s Markdown files.

5Create Images with Codex, Step by Step

What it is

The page gives a real example: someone with a Codex subscription uses its image generator, image_gen, which INEMA calls "image 2.5." Today at INEMA, Claude Code runs codex exec in non-interactive mode and asks image_gen for a PNG in a folder; if Codex fails or there is no credit, it falls back to the local model FLUX.2 klein. Each generation uses subscription credit, so it runs only when authorized. The image is checked afterward because text near the edges may be made up. The kit proposes using level 2 step by step: first confirm the tool and billing, never switch automatically to a paid API, save the actual file in the project, and open it at the size it will be used. In the page’s words, INEMA’s approach runs automatically in batches, with a local fallback; the kit’s approach is manual, with more cost checks and review.

Why learn it

Generated images have costs and visible errors. The two approaches show how to balance automation with review before using the file.

Key concepts

image_gen; codex exec; FLUX.2 klein fallback; check first, inspect afterward; save as a sibling version instead of overwriting

In practice

A designer uses Codex to create a cover for a resource. Before publishing, they open the file at its actual size, spot a made-up word near the edge, and save the correction as a sibling version without deleting the original.

Check toolGenerate draftSave fileInspectSibling versions
Kit level 2, piece by piece: check the cost first and the actual file afterward, without overwriting the original.

6A First Step and All the Projects

What it is

The page sums up how to start: "The best first step: a plan of your own, reviewed by the other one." Choose a small task, write the brief and acceptance criteria, ask one to make the plan and the other to critique it in the same file, for no more than two rounds, and create a handoff before closing the session. The area includes six courses: Claude → Codex (PT, EN, and ES), Codex Básico, Master Codex, iClaudeX, MakeClaudeX, and DeepClaudeX. It also includes kits and references: agente-claude-codex, Use Both, claudex on GitHub, Codex Cheat Sheet, and the topic map on INEMA.CLUB. The page cites an external video by Mark Kashef, which the Use Both kit follows, as a source of the author’s opinions, not a benchmark. His summary is in RESUMO-VIDEO.md in the kit repository.

Why learn it

A short first cycle shows the value of a second look in practice. The courses and kits show you where to go deeper at each step.

Key concepts

a plan of your own, reviewed by the other one; no more than two rounds; Codex Básico; Master Codex; iClaudeX; MakeClaudeX; DeepClaudeX; Use Both; claudex; Codex Cheat Sheet

In practice

A coordinator asks Claude to plan a reporting routine and Codex to critique it in read-only mode. After the second round, the plan is settled, and they record a handoff to pick it up the next day.

Criteria for reviewing your worksheet

Use this rubric after the lab. Each row asks for evidence; marking a topic as read doesn’t mean the worksheet is complete.

Criterion Expected evidence If it doesn’t meet the criterion
Main idea You can describe the area in one sentence that reflects the page. Reread the top of the page and topic 1.
Audience You can say who the area is for and who it isn’t for. Return to topic 2 and write an example from your work.
Core elements You can name the area’s core elements. Use the module diagram as a guide.
First step You chose a small, concrete step. Copy the first step recommended on the page itself.
Starting point You know which course, kit, or project to open first. Check topic 6 and the page’s access section.
Source Every statement in the worksheet comes from the page. Replace your assumptions with what the page says.

HANDS-ON / ~10 MIN

Have the other assistant review your plan

Keep the area page open: https://eventos.inema.pro/codex-claude/en/. Use an example from your work, without personal or client data.

Command: Codex reviews your plan, read-only

Paste it into Claude, ChatGPT, or Codex. Replace the words inside < and > with details about your situation.

codex exec --sandbox read-only -c model_reasoning_effort=medium \
  --output-last-message review.md \
  'Read plan-v1.md. Point out correctness issues and missing tests, with evidence, impact, and the smallest fix. Do not change files.'

# Reverse path (Codex wrote it, Claude reviews):
claude -p --model opus --effort medium \
  'Read plan-v1.md and review it read-only: issues, assumptions, and missing tests. Do not change files.' > review-claude.md

Completion criterion

Explain how to use Claude and Codex on the same project, covering the Use Both kit’s six levels, the routing card, and the difference between claudex and Use Both. Keep the worksheet with the main idea, audience, first step, and starting point.

Open the area page ↗

Review what you’ve learned

Claude wrote the plan, and Claude itself approved it in the same session. Why isn’t that enough?

View suggested answer

Because the model that wrote the plan tends to approve its own work, and two AIs agreeing is not independent proof. The tests and your approval are what count.

If your answer was different, return to the relevant topic and describe the difference in one sentence. This check won’t block your progress.

Module summary

  • one does the work, the other reviews it; real artifact; same brief; it’s not Claude or Codex; sister area Claude → Codex
  • discuss; generate images; build and review; supervised computer use; goal with a stop condition; handoff and prime
  • first pass; second pass; finish line; editorial choices, not a ranking; models and billing vary by account
  • Understand → Migrate → Use both → Automate the discussion; claudex = software; Use Both = method; LGTM; complementary
  • image_gen; codex exec; FLUX.2 klein fallback; check first, inspect afterward; save as a sibling version instead of overwriting
  • a plan of your own, reviewed by the other one; no more than two rounds; Codex Básico; Master Codex; iClaudeX; MakeClaudeX; DeepClaudeX; Use Both; claudex; Codex Cheat Sheet

Check the source

Pages read on 28/09/2026. Area content changes; the official page takes precedence over this summary.

Module complete