Add Claude Code GitHub Workflow

[wshobson]

🤖 Installing Claude Code GitHub App

This PR adds a GitHub Actions workflow that enables Claude Code integration in our repository.

What is Claude Code?

Claude Code is an AI coding agent that can help with:

• Bug fixes and improvements
• Documentation updates
• Implementing new features
• Code reviews and suggestions
• Writing tests
• And more!

How it works

Once this PR is merged, we'll be able to interact with Claude by mentioning @claude in a pull request or issue comment.
Once the workflow is triggered, Claude will analyze the comment and surrounding context, and execute on the request in a GitHub action.

Important Notes

• This workflow won't take effect until this PR is merged
• @claude mentions won't work until after the merge is complete
• The workflow runs automatically whenever Claude is mentioned in PR or issue comments
• Claude gets access to the entire PR or issue context including files, diffs, and previous comments

Security

• Our Anthropic API key is securely stored as a GitHub Actions secret
• Only users with write access to the repository can trigger the workflow
• All Claude runs are stored in the GitHub Actions run history
• Claude's default tools are limited to reading/writing files and interacting with our repo by creating comments, branches, and commits.
• We can add more allowed tools by adding them to the workflow file like:

allowed_tools: Bash(npm install),Bash(npm run build),Bash(npm run lint),Bash(npm run test)

There's more information in the Claude Code action repo.

After merging this PR, let's try mentioning @claude in a comment on any PR to get started!

[claude]

Code Review: Claude Code GitHub Workflow Integration

Thanks for adding Claude Code integration! Here's my review of the implementation:

Overall Assessment

Status: Good implementation with solid security practices. Some recommendations for follow-up improvements.

---

Strengths

✅ Security-Conscious Permissions

• Both workflows use minimal required permissions (read-only for most resources)
• Proper use of id-token: write for OIDC authentication
• Tool restrictions in claude-code-review.yml limit potential security risks

✅ Well-Structured Workflows

• Two complementary approaches: automatic reviews + on-demand assistance
• Clear inline documentation and comments
• Proper use of conditional logic to filter @claude mentions

✅ Performance Optimizations

• Uses fetch-depth: 1 for faster checkouts
• Appropriate trigger filtering to avoid unnecessary runs

✅ Community Governance

• Excellent addition of CODE_OF_CONDUCT.md, CONTRIBUTING.md, and issue templates
• Shows good project stewardship

---

Recommendations for Follow-up

1. Missing Documentation Reference

.github/workflows/claude-code-review.yml:26

Use the repository's CLAUDE.md for guidance on style and conventions.

The workflow references a CLAUDE.md file that doesn't exist in the repository. Consider adding this file with:

• Code style guidelines
• Architectural patterns
• Review priorities specific to this project

2. Tool Restrictions Inconsistency

.github/workflows/claude.yml has no tool restrictions (the claude_args line is commented out), while claude-code-review.yml has explicit restrictions. For security consistency, consider adding similar restrictions to claude.yml:

claude_args: '--allowed-tools "Bash(gh issue view:*),Bash(gh search:*),Bash(gh issue list:*),Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh pr list:*)"'

Or expand allowed tools based on your trust level and use case.

3. Secret Setup Documentation

Add documentation (perhaps in README.md or a new SETUP.md) explaining how to:

• Obtain the CLAUDE_CODE_OAUTH_TOKEN
• Configure it as a GitHub Actions secret
• Verify the integration is working

4. Cost Control Considerations

The claude-code-review.yml workflow runs on every PR open/synchronize event. Consider:

• Adding path filters to only review code files (uncomment the paths section)
• Limiting to specific branches
• Adding manual approval requirements for external contributors

Example:

paths:
  - "src/**/*.ts"
  - "src/**/*.tsx"
  - "src/**/*.js"
  - "src/**/*.jsx"
  - "**/*.go"
  - "**/*.py"

5. Self-Trigger Prevention

Add logic to prevent Claude from triggering itself in a loop:

if: |
  github.actor != 'github-actions[bot]' &&
  ((github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) || ...)

6. Error Handling

Neither workflow includes failure handling. Consider adding a final step:

- name: Notify on failure
  if: failure()
  run: |
    echo "Claude Code workflow failed"
    # Add Slack notification or similar

7. Deeper Git History

fetch-depth: 1 limits context for reviews. For more comprehensive analysis, consider increasing this for the review workflow:

fetch-depth: 10  # or 0 for full history

---

Security Review

✅ No security vulnerabilities identified

• Secrets are properly referenced via GitHub Actions secrets
• No hardcoded credentials
• Appropriate permission scoping
• Read-only access to most resources

⚠️ Minor Security Consideration
The claude.yml workflow has unrestricted tool access (commented claude_args). While this provides flexibility, it increases the attack surface if the OAuth token is compromised. Recommend adding explicit tool restrictions.

---

Performance Considerations

✅ Efficient Configuration

• Shallow clones for fast checkouts
• Proper event filtering
• Conditional execution based on mentions

---

Test Coverage

ℹ️ No tests needed - These are workflow configurations, not code requiring unit tests. However, consider:

• Testing the workflows manually with a test PR
• Documenting expected behavior in CLAUDE.md
• Creating a workflow_dispatch trigger for manual testing

---

Code Quality

✅ Well-formatted YAML

• Proper indentation
• Clear naming conventions
• Good use of comments

---

Action Items Summary

High Priority:

1. Create CLAUDE.md with style guidelines
2. Add setup documentation for the OAuth token
3. Add tool restrictions to claude.yml

Medium Priority:
4. Add path filters to reduce review workflow runs
5. Implement self-trigger prevention
6. Add error handling/notifications

Low Priority:
7. Consider increasing fetch-depth for reviews
8. Add workflow_dispatch for manual testing

---

Great work on implementing this integration! The foundation is solid, and these recommendations will help make it even more robust and maintainable. 🚀