Skip to content
The AI Agent Factory

15.11 How today's tools realize it

Approved by
Panaversity ·
5 min read

In everyday life. Three security firms will all inspect your building. One sends a team to walk it and leaves a report. One lends you the checklist to walk it yourself. One installs a camera on your own wall. None of them locks the doors. That stays your job.

What you will learn. What Claude Code, Codex and OpenCode each offer for review, as of October 31, 2026, what each one can and cannot block, and what each costs.

Why it matters. A managed review is the team that walks the building. A local command is the checklist. A review in your own workflow is the camera. The three products offer these in different places, read their rules from different files and cost different amounts. In all three, the checks that block a merge are yours.

How to use this page. Each lesson's Try it ends with the steps for your own tool. This page holds only what differs between the three tools and changes a decision. The exact clicks for GitHub and each review tool are in field-guide-code-review-setup.md, in the lab's download. 12.8 covers the three agents in full.

The differences that change a decision

  1. Which reviewers block. None of them, on their own. Claude's Code Review finishes neutral, and OpenAI's documentation names no blocking setting for Codex review. OpenCode has no reviewer of its own. Blocking always comes from your repository: required checks, conversation resolution, and your own step that reads a result and fails.
  2. Where the rules come from. Code Review reads REVIEW.md from the base branch. /code-review reads CLAUDE.md. Codex reads ## Code Review Rules in AGENTS.md. Your own reviewers, an OpenCode command included, read whatever you hand them. To share one set of rules, keep them in REVIEW.md and hand them git show main:REVIEW.md.

Outside the apps, the same agents run headless in CI, as in 12.7: claude -p, codex exec and opencode run.

For the exam. CCDV-F, Anthropic's Claude Certified Developer: Foundations, is about building on Claude. Its guide names no tool from OpenAI, OpenCode or GitHub.

What it costs

Code Review needs Team or Enterprise.1 An Owner sets a review level for the organization and can override it per repository: Quick, Standard (the default) or Deep. Deeper reviews take longer and cost more. There is no flat price. Reviews are billed on token usage, through usage credits separate from the plan, and a monthly spend limit applies to the organization. When the limit runs out, reviews are skipped.2 /code-review and /security-review need any Claude Code account: Pro, Max, Ultra, Team, Enterprise or Console.3 The Actions run on what you give them: an API key or a cloud account, or, for the Claude Code Action, a Claude subscription token.4

Codex is included in every ChatGPT plan, from Free to Enterprise. Code review on GitHub is listed from the Plus plan up. Reviews run locally count toward your general usage limits.5

OpenCode is free under the MIT license, at version 2.2.5 on October 30, 2026.6 You pay for the model.

Check yourself

Question 1 / 5

0 answered

A team on a Claude Team plan turns on Code Review. A review finds two Important bugs. What happens to the merge button?

  1. Code Review, Anthropic.↑
  2. Code Review costs and usage, Anthropic.↑
  3. Set up Claude Code, Anthropic.↑
Owner
Panaversity