Automate code review with Claude Code and GitHub Actions

You will build a GitHub Actions workflow that runs Claude Code to automatically review pull requests, triage issues, and enforce code quality standards across your repository. This tutorial takes about 30 minutes to complete, including installation, workflow setup, and verification.

Prerequisites

• A GitHub account with admin access to a repository (public or private)
• A Claude subscription (Pro, Max, Team, or Enterprise) or an Anthropic Console account with pre-paid credits
• Git installed on your local machine (Git for Windows recommended on native Windows)
• A terminal or command prompt open
• A code project to work with (any language or framework)
• Basic familiarity with YAML syntax and GitHub Actions concepts

Step 1: Install Claude Code on your local machine

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. You need it installed locally to test your workflow before pushing to CI, and to authenticate your account.

Choose one of the following installation methods based on your operating system.

macOS, Linux, or WSL (native install, recommended)

Open your terminal and run:

curl -fsSL https://claude.ai/install.sh | bash

This installs the latest stable version of Claude Code. Native installations automatically update in the background to keep you on the latest version.

macOS with Homebrew

brew install --cask claude-code

Homebrew offers two casks. claude-code tracks the stable release channel, which is typically about a week behind and skips releases with major regressions. claude-code@latest tracks the latest channel and receives new versions as soon as they ship. Homebrew installations do not auto-update. Run brew upgrade claude-code or brew upgrade claude-code@latest periodically to get the latest features and security fixes.

Windows with WinGet

winget install Anthropic.ClaudeCode

WinGet installations do not auto-update. Run winget upgrade Anthropic.ClaudeCode periodically to get the latest features and security fixes.

Windows with PowerShell or CMD

If you prefer the native install script on Windows, use the appropriate command for your shell.

PowerShell:

irm https://claude.ai/install.ps1 | iex

CMD:

curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

If you see The token '&&' is not a valid statement separator, you are in PowerShell, not CMD. If you see 'irm' is not recognized as an internal or external command, you are in CMD, not PowerShell. Your prompt shows PS C:\ when you are in PowerShell and C:\ without the PS when you are in CMD. If the install command fails with syntax error near unexpected token ', refer to the installation troubleshooting guide to match the error to a fix and for alternative install methods.

Git for Windows is recommended on native Windows so Claude Code can use the Bash tool. If Git for Windows is not installed, Claude Code uses PowerShell as the shell tool instead. WSL setups do not need Git for Windows.

Linux package managers (apt, dnf, apk)

You can also install with apt, dnf, or apk on Debian, Fedora, RHEL, and Alpine. Refer to the advanced setup documentation for the specific commands.

Verify the installation

Run the following command to confirm Claude Code installed correctly:

claude --version

The command prints a version number followed by (Claude Code). If you see an error, revisit the installation steps or check the troubleshooting guide.

Step 2: Log in to your Claude account

Claude Code requires an account to use. Start an interactive session with the claude command and you will be prompted to log in on first use:

claude

For Claude subscription or Console accounts, follow the prompts to complete authentication in your browser. Once logged in, your credentials are stored on your system and you will not need to log in again.

You can log in using any of these account types:

• Claude Pro, Max, Team, or Enterprise (recommended)
• Claude Console (API access with pre-paid credits). On first login, a "Claude Code" workspace is automatically created in the Console for centralized cost tracking.
• Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry (enterprise cloud providers)
• A self-hosted Claude apps gateway, if your organization runs one: your admin pre-configures the gateway URL, and /login opens directly on the Cloud gateway screen for you to sign in with corporate SSO

To switch accounts later or re-authenticate, type /login inside the running session:

/login

After logging in, type /exit or press Ctrl+D twice to exit the session.

Step 3: Create a GitHub Actions workflow file

Now you will create a GitHub Actions workflow that runs Claude Code on every pull request. The workflow will review the code changes, check for issues, and post a comment with the review results.

In your repository, create the file .github/workflows/claude-code-review.yml. You can do this through the GitHub web interface, or locally with:

mkdir -p .github/workflows

Open the file in your editor and add the following content:

name: Claude Code Review

on:
  pull_request:
    types: [opened, synchronize, reopened]
  issues:
    types: [opened]

jobs:
  review:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write
      issues: write
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Install Claude Code
        run: |
          curl -fsSL https://claude.ai/install.sh | bash

      - name: Run code review on PR
        if: github.event_name == 'pull_request'
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
        run: |
          git fetch origin ${{ github.base_ref }} --depth=1
          changed_files=$(git diff --name-only origin/${{ github.base_ref }}...HEAD)
          echo "Changed files:"
          echo "$changed_files"
          echo "$changed_files" | claude -p "Review these changed files for bugs, security issues, and code quality problems. Provide a concise summary with specific file:line references for each issue found. If the code looks good, say so." --print

      - name: Post review comment
        if: github.event_name == 'pull_request'
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require('fs');
            const review = fs.readFileSync('review_output.txt', 'utf8');
            github.rest.issues.createComment({
              issue_number: context.issue.number,
              owner: context.repo.owner,
              repo: context.repo.repo,
              body: `## Claude Code Review\n\n${review}`
            });

      - name: Triage issue
        if: github.event_name == 'issues'
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
        run: |
          issue_body="${{ github.event.issue.body }}"
          echo "$issue_body" | claude -p "Analyze this issue report. Suggest a root cause, potential fix, and any additional information needed. Provide a response suitable for posting as a comment." --print > triage_output.txt

      - name: Post triage comment
        if: github.event_name == 'issues'
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require('fs');
            const triage = fs.readFileSync('triage_output.txt', 'utf8');
            github.rest.issues.createComment({
              issue_number: context.issue.number,
              owner: context.repo.owner,
              repo: context.repo.repo,
              body: `## Claude Code Triage\n\n${triage}`
            });

This workflow does the following:

• Triggers on pull request events (opened, synchronized, reopened) and issue creation
• Checks out the full git history with fetch-depth: 0 so Claude can see the diff
• Installs Claude Code using the native install script
• For pull requests: gets the list of changed files, pipes them into Claude Code with a review prompt, and posts the result as a comment
• For issues: pipes the issue body into Claude Code for triage and posts the analysis as a comment

Why fetch-depth: 0?

The actions/checkout action defaults to a shallow clone with only the latest commit. Setting fetch-depth: 0 ensures Claude Code has access to the full git history, which is necessary for comparing branches and understanding the context of changes.