Skip to main content
Your tests pass. But standards slip. Linters catch syntax. Tests verify behavior. But nobody’s checking whether that migration is safe, the API docs got updated, or the auth flow follows your team’s conventions. Reviewers repeat the same feedback on every PR, and things still slip through. Continue runs source-controlled AI checks on every pull request. Standards as checks, enforced by AI, decided by humans.

​
Quickstart

  1. Go to continue.dev/check to run checks on a pull request.

​
How it works

You define checks as markdown files in .continue/checks/, version-controlled and reviewable alongside your code. You specify what to look for. The AI enforces it on every PR. Results show up as GitHub status checks: green if the code looks good, red with a suggested fix if not.
.continue/checks/security-review.md
---
name: Security Review
description: Flag hardcoded secrets and missing input validation
---

Review this pull request for security issues.

Flag as failing if any of these are true:

- Hardcoded API keys, tokens, or passwords in source files
- New API endpoints without input validation
- SQL queries built with string concatenation
- Sensitive data logged to stdout

If none of these issues are found, pass the check.
When a PR is opened, Continue runs each check against the diff and reports the result as a GitHub status check. If a check fails, it suggests a fix you can accept or reject directly from GitHub.