Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstalliTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
To have Codex review GitHub pull requests without a prompt on each one, connect the repository to Codex, enable Automatic review under Review code, then choose a Review trigger. For repository-specific checks, add concise rules under ## Code Review Rules in an applicable AGENTS.md file. Automatic reviews need a connected repository and a matching trigger event; rules guide findings but do not enforce merge requirements.
What Codex PR review does—and how automatic review differs from a manual request
Codex Code Review examines a GitHub pull request’s diff alongside applicable repository guidance. You can initiate it manually with a comment or configure it to run automatically for enabled repositories.
| Mode | How it starts | What to expect |
|---|---|---|
| Manual Code Review | Comment @codex review on the pull request. |
Codex responds with a review. GitHub comments flag only P0 and P1 issues; this is not a merge gate. OpenAI’s GitHub pull request review guide |
| Automatic Code Review | Enable Automatic review and select a Review trigger in Codex settings. | Reviews run when the configured event occurs for a repository with Code Review enabled. No comment is needed. OpenAI’s GitHub pull request review guide |
| Security Review | Configure its separate setting or comment @codex security review. |
Focuses more deeply on security risks using the diff, repository context, and configured threat-model or security guidance. It can overlap with general Code Review. OpenAI’s GitHub pull request review guide; OpenAI’s Security Review article |
How to enable automatic Codex reviews on GitHub pull requests
Before you configure it
- The GitHub repository must be connected to Codex.
- You need access to Code Review settings. To change repository settings, you need GitHub push or admin permission for that repository.
Configure the repository and trigger
- Connect the GitHub repository to Codex.
- Open Codex settings and select the repository.
- Under Review code, enable Automatic review.
- In Personal preferences, enable Automatic review and select when reviews run using Review trigger. The trigger determines which pull-request events start a review.
Automatic review applies to repositories where Code Review is enabled. When the chosen event occurs, Codex can start a review without an @codex review comment. For exact current settings and trigger behavior, see OpenAI’s GitHub review setup guide.
How to request a one-off review manually
On the pull request, post @codex review. To focus that review on a particular area, add the focus to the comment, such as @codex review for issues in the database migration. Manual requests are useful when you want a review outside the automatic trigger schedule or want to direct attention to a specific concern. GitHub comments flag only P0 and P1 findings, according to OpenAI’s guide.
#1 Best Overall
How to add custom Codex code review rules
Put rules in a ## Code Review Rules section in an AGENTS.md file. Codex looks for these files and applies guidance relevant to the changed code. Use the root file for repository-wide invariants; place more specific rules in a nested file close to the service or subsystem they govern. Applicable root and nested guidance can combine for a change.
Write rules as actionable invariants
- State the behavior or boundary that must remain true, not just a function name or broad aspiration.
- Explain why it matters and specify the safe approach or exception.
- Keep the initial set small—two or three consequential checks are a practical starting point.
- Leave formatting, lint, and other deterministic checks to CI.
For example, a rule for an experiment-analysis directory could say:
## Code Review Rules
- Build experiment comparison cohorts from assignment or exposure. Do not filter cohorts using behavior measured after exposure, because that can bias the comparison. Report conversion as an outcome instead.This expresses the invariant, why it matters, and a safe alternative. OpenAI’s examples also show how to document compatibility surfaces that may look experimental but are consumed by another system. See OpenAI’s custom Code Review rules article.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Check rules for usefulness, not just strictness
Try a representative pull request that violates a rule, a safe counterexample, and an unrelated change. If the rule misses the violation or creates noise on safe changes, refine or remove it. In an evaluation reported by OpenAI on July 20, 2026, rule-guided variants recovered 98% of required custom findings, compared with 58.3% for the baseline control in the primary evaluation suite. Those are OpenAI evaluation results, not a promise of production performance; the evaluation also considered coverage, restraint, ordinary-bug findings, and actionability. Details are in the published evaluation article.
Rank #3
What Codex review rules do not enforce
Review rules guide what Codex looks for; they do not replace tests, branch protections, or required approvals. Use CI for mechanical requirements and repository controls for hard merge gates. Human maintainers still need to decide among valid designs, product behaviors, compatibility policies, naming, migration approaches, release communication, and cross-team trade-offs. OpenAI describes Code Review as an additional reviewer, not an enforcement layer, in its custom rules article.
How Code Review differs from Security Review
Security Review is a separate, security-focused pull-request analysis. It considers the diff, supporting repository context, and configured threat models or security guidance. General Code Review may also surface security issues, so findings can overlap.
OpenAI’s Security Review article, published August 21, 2026, lists automatic triggers as a pull request opening, every push, or whenever an existing Codex code review runs. That article describes availability for ChatGPT Enterprise, Business, Edu, and Pro accounts; eligibility and settings can change, so check the current Security Review information before relying on access for a particular account.
Free tools Windows power users keep installed
One-click scans. No signup required.
Troubleshoot an automatic review that did not start
- Confirm Code Review is enabled for the repository in Codex.
- Check the GitHub connection and verify the repository is connected.
- Compare the pull-request event with Review trigger. An event that does not match the selected trigger will not start an automatic review.
- For a manual request, use the exact trigger
@codex reviewin a pull-request comment.
These checks follow the troubleshooting guidance in OpenAI’s GitHub review documentation.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
