GitHub Copilot Code Review: How It Works, Custom Instructions and Local Reviews
How GitHub Copilot code review works on Pull Requests, how to customize it with copilot-instructions.md, and how to review your branch locally with Copilot CLI before pushing.
"Copilot" covers several products: completions in the IDE, the chat, the cloud agent, the code review on GitHub.com and Copilot CLI in the terminal. For reviewing code, two of them matter: Copilot code review on GitHub and Copilot CLI. This guide shows how each works, how to customize the review and where each one fits.
How to request a Copilot review on a Pull Request
- Open or create a Pull Request on GitHub.com.
- In the right sidebar, under Reviewers, click Request next to Copilot.
- Wait for the review, then read and resolve its comments like a human reviewer's.
By default Copilot leaves a "Comment" review, so it does not count toward required approvals. Its suggestions can be applied in a few clicks. Replies you write to Copilot's comments are visible to teammates but are not read by Copilot.
Customize the review with instruction files
Repository-wide instructions live in .github/copilot-instructions.md. Keep them short and concrete: GitHub notes that Copilot is non-deterministic and that very long instruction files are followed less reliably.
# Review guidance
- Flag endpoints that do not check the caller's permissions.
- Flag user input used without validation.
- Flag SQL built with string concatenation.
- Every bug fix should include a regression test.
- Ignore formatting; the linter enforces it.For rules that only apply to part of the code, add a path-specific file under .github/instructions/ with an applyTo pattern.
---
applyTo: "src/api/**/*.ts"
---
- Validate request bodies with a schema before using them.
- Return errors in the shared { error: { code, message } } shape.Review before you push with Copilot CLI
The GitHub review only runs after a PR exists. To catch problems on your branch first, run Copilot CLI in your local clone and give it an explicit scope.
cd path/to/your-repo
copilotReview the changes on this branch compared with origin/main
(git diff origin/main...HEAD). For each changed function, check its
callers and tests. Report bugs, security issues and missing tests with
file and line. Do not modify any files.GitHub review vs local review
- When: GitHub review runs on an open PR; a local review runs before you push.
- Where the code is read: GitHub review runs on GitHub; Copilot CLI reads your local checkout.
- Output: GitHub review posts PR comments; a local review stays private until you decide what to share.
Many teams use both: a private review on the branch, then the PR review as a second pass.
How CodeCrab fits in
CodeCrab is a desktop app that uses your existing Copilot CLI sign-in (or Claude Code, Cursor or Codex) to run pre-push reviews, review teammates' PRs and explain reviewer feedback in My PRs, with a history of every review on your laptop. See setting up Copilot CLI in CodeCrab, or compare the same workflow in Cursor and Claude Code.
Quick questions
Does Copilot code review approve PRs?
By default it leaves comment reviews that do not count toward required approvals.
Can I request Copilot from a script?
Yes, through the REST API by requesting copilot-pull-request-reviewer[bot] as a reviewer.
Does Copilot read AGENTS.md?
Copilot agents can use AGENTS.md; for code review, put guidance in the Copilot instruction files above.
Try it on your next Pull Request
Free Public Beta — runs 100% on your machine. No code leaving your laptop.
Download CodeCrabKEEP READING
GitLab AI Code Review: How to Review Merge Requests Locally with AI
Review GitLab merge requests with AI on your own machine: glab mr checkout, view and diff, a copy-ready review prompt for Claude Code, Cursor, Codex or Copilot CLI.
How to Use Cursor for Code Review: Review Rules, Diff Checks and PR Workflows
Use Cursor for code review: review your branch before pushing, review PRs with the GitHub CLI, use Bugbot, and add a copy-ready .cursor/rules code review rule.
Can Claude Code Review PRs? How to Review a Pull Request with Claude Code (Step by Step)
Yes, Claude Code can review Pull Requests. Learn three ways to review a PR with Claude Code: pre-push branch reviews, GitHub CLI PR reviews and repeatable claude -p reviews, with copy-ready prompts.
The AI-Era Code Review Checklist: How to Review AI-Generated Code (and Vibe-Coded PRs)
A practical code review checklist for AI-generated code: verify authorization, API contracts, data integrity and tests, with copy-ready review templates and a repository-aware prompt.
Cursor Bugbot vs Codex vs Claude Code: Which AI Reviews Pull Requests Best?
Compare Cursor Bugbot, OpenAI Codex and Claude Code for PR and pre-push reviews: triggers, repository rules, permissions, privacy, practical prompts and a fair evaluation method.
Claude Code Subagents for Code Review: Security, Performance and Architecture Reviewers
Build three specialized Claude Code review subagents with copy-ready definitions: a security reviewer, a performance reviewer and an architecture reviewer, each with isolated context and read-only tools.
Best AI Code Review Tools in 2026: CodeRabbit vs Greptile vs Qodo vs Cursor Bugbot vs CodeCrab
A no-pricing comparison of the leading AI code review tools: where your code goes, what permissions you grant, how much context the reviewer sees, and when the review happens.
Claude Code Skills for Code Review: How to Create, Install and Activate Them
Create and install a custom Claude Code review skill with a copy-ready SKILL.md template. Learn local vs global paths, activation, troubleshooting, and the CodeCrab output format.
Local-First AI Code Review: Why Enterprise Codebases Can't Rely on Cloud Review Bots
Cloud review bots copy your diffs to vendor servers and ask for org-wide permissions. Here is how local AI code review and self-hosted PR review really differ, and what to verify before trusting either.
How to Review Code with Claude Code: From Generic Prompts to Repo-Aware Reviews
Claude Code can review Pull Requests, but generic prompts miss what matters. Learn how review skills, repository context and a fixed output format turn it into a real reviewer.
AI Can Write Your Code. But Who Reviews It? The New PR Bottleneck
AI made writing code cheap, but reviewing AI-generated code is now the bottleneck. Learn why PR queues grow, why rubber-stamping is risky, and how to review before the Pull Request.
Code review that fits your workflow: local skills and repository-aware agents
CodeCrab combines your existing local review skills with per-repository profiles and specialized agents, so you can review PRs and pre-push changes with the full codebase in context.
PR Code Reviews: how CodeCrab unblocks your team in the AI era
AI writes more code than ever, so review queues are the new bottleneck. Here is how CodeCrab reviews Pull Requests locally, with repo-specific skills and full engineer control.
My PRs — Feedback: turn vague review comments into a clear fix
Generic or unclear feedback on your Pull Request stalls you for days. CodeCrab investigates every comment with full local code context and hands you a ready-to-run fix prompt.
Pre-Push Code Review: catch bugs before the Pull Request even exists
The cheapest bug is the one that never reaches a PR. CodeCrab reviews your local changes with your repo's own profile and skills, so you push higher-quality code the first time.
