Add Claude Code GitHub Workflow by dodeja · Pull Request #229 · Terminal49/API

dodeja · 2026-05-29T19:20:07Z

🤖 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!

Greptile Summary

This PR introduces two GitHub Actions workflows to integrate Claude Code into the repository: an automated code-review workflow that triggers on every PR event, and an interactive assistant workflow that responds to @claude mentions in comments and issues.

claude-code-review.yml: Runs Claude as an automated reviewer on PR open/sync/reopen events using a plugin-based /code-review command; currently the job permissions are read-only on pull-requests and issues, which will prevent Claude from posting review output via the GITHUB_TOKEN.
claude.yml: Triggers Claude on @claude mentions across issue comments, PR review comments, and reviews; shares the same read-only permission issue, contains a redundant additional_permissions: actions: read (already declared in the job block), and has no actor authorization guard to restrict triggering to write-access collaborators.

Confidence Score: 3/5

Both workflows will silently fail to write back to GitHub until the permissions are corrected; merging as-is means Claude runs but can never post its output.

The job-level permissions in both files are read-only for pull-requests and issues. Since the action relies on the job's GITHUB_TOKEN for GitHub API calls, Claude will authenticate successfully with the AI backend but every attempt to write a comment or review back to the PR will be rejected. The workflows would be non-functional from day one.

Both .github/workflows/claude-code-review.yml and .github/workflows/claude.yml need their permissions blocks updated before the integration will work end-to-end.

Important Files Changed

Filename	Overview
.github/workflows/claude-code-review.yml	Adds automated Claude code review on every PR event; missing write permissions on pull-requests/issues/contents will prevent Claude from posting review comments, and the action is pinned to a mutable @v1 tag.
.github/workflows/claude.yml	Adds @claude mention-triggered assistant workflow; same missing write-permission issue, plus a redundant additional_permissions declaration and no actor authorization check to limit who can invoke Claude.

Sequence Diagram

sequenceDiagram
participant User
participant GitHub
participant ActionsRunner as GitHub Actions Runner
participant ClaudeAction as claude-code-action@v1
participant ClaudeAI as Claude AI (OAuth)
Note over User,ClaudeAI: claude.yml — @claude mention flow
User->>GitHub: "Post comment with @claude"
GitHub->>ActionsRunner: Trigger issue_comment / pull_request_review_comment event
ActionsRunner->>ActionsRunner: Evaluate if condition
ActionsRunner->>ActionsRunner: Checkout repository
ActionsRunner->>ClaudeAction: Run with claude_code_oauth_token
ClaudeAction->>ClaudeAI: Authenticate and send PR/issue context
ClaudeAI-->>ClaudeAction: Response / instructions
ClaudeAction->>GitHub: Post comment / create commit (needs write perms via GITHUB_TOKEN)
Note over User,ClaudeAI: claude-code-review.yml — automated PR review flow
User->>GitHub: Open / update PR
GitHub->>ActionsRunner: Trigger pull_request event
ActionsRunner->>ActionsRunner: Checkout repository
ActionsRunner->>ClaudeAction: Run with plugin code-review + OAuth token
ClaudeAction->>ClaudeAI: Send PR diff and context
ClaudeAI-->>ClaudeAction: Review output
ClaudeAction->>GitHub: Post PR review comment (needs pull-requests write via GITHUB_TOKEN)

Prompt To Fix All With AI

Fix the following 4 code review issues. Work through them one at a time, proposing concise fixes.
---### Issue 1 of 4
.github/workflows/claude-code-review.yml:22-26
**Insufficient permissions for Claude to write back to the PR**
Both this workflow and `claude.yml` set `pull-requests: read` and `issues: read`, but Claude needs write access to post review comments, create branches, or push commits. The `claude_code_oauth_token` authenticates Claude with the AI backend; GitHub API operations (posting comments, creating reviews, pushing code) go through the job's `GITHUB_TOKEN`, which is governed by this `permissions` block. With only `read` on `pull-requests` and `issues`, any attempt by Claude to leave a comment or open a review will fail at runtime. At minimum, `pull-requests: write` and `issues: write` are required; `contents: write` is needed if Claude should be able to commit changes. The same issue applies to the identical permissions block in `claude.yml` (lines 21–26).
### Issue 2 of 4
.github/workflows/claude.yml:39-41
**Duplicate `actions: read` declaration**`actions: read` is already declared in the job-level `permissions` block (line 26) and is redundantly restated under `additional_permissions`. The `additional_permissions` input is documented for granting permissions beyond what the workflow's token carries; listing one that is already granted there has no effect and is misleading.
```suggestion # This is an optional setting that allows Claude to read CI results on PRs # additional_permissions is used for permissions beyond what the job token provides; # 'actions: read' is already granted in the job permissions block above.```### Issue 3 of 4
.github/workflows/claude.yml:15-19
**No actor write-permission check — any commenter can trigger Claude**
The trigger condition only checks whether the comment body contains `@claude`; it does not verify that the actor is a repository collaborator or has write access. On any public or organisation repo where outside users can comment on issues, this means an unauthenticated third party can invoke Claude (and consume the team's API quota) simply by posting a comment with `@claude`. Adding a check such as `github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'OWNER'` would restrict execution to trusted contributors.
### Issue 4 of 4
.github/workflows/claude-code-review.yml:36
**Third-party action pinned to a mutable `@v1` tag**`anthropics/claude-code-action@v1` resolves to whatever commit the upstream maintainer points that tag at. If the tag is force-pushed with a compromised version, every future run fetches and executes untrusted code with the `CLAUDE_CODE_OAUTH_TOKEN` secret in scope. GitHub's own hardening guide recommends pinning to a full commit SHA (e.g. `anthropics/claude-code-action@<sha>`) and verifying it periodically. The same applies to the identical reference in `claude.yml` (line 35).

_{Reviews (1): Last reviewed commit: ""Claude Code Review workflow"" | Re-trigger Greptile}

Greptile also left 4 inline comments on this PR.

vercel · 2026-05-29T19:20:13Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
api	Ready	Preview, Comment	May 29, 2026 7:20pm

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit:18f5e9f19d

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-29T19:22:08Z

+ runs-on: ubuntu-latest
+ permissions:
+ contents: read
+ pull-requests: read


Grant the auto-review job PR write access
When this workflow runs on a pull request, the code-review plugin is expected to publish PR feedback, but the job token is limited to pull-requests: read. Anthropic's automatic PR review examples grant pull-requests: write and describe the expected output as posted PR comments (https://github.com/anthropics/claude-code-action/blob/main/docs/solutions.md#automatic-pr-code-review); with the current read scope, review/comment creation will be denied or produce a run with no PR feedback.
Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-05-29T19:22:08Z

+contents: read
+pull-requests: read
+issues: read


Grant the interactive Claude job write scopes
For @claude requests that ask Claude to reply, update files, or create PRs, this job only gives the action read access to contents, pull requests, and issues. The upstream interactive example grants contents: write, pull-requests: write, and issues: write for the same triggers (https://github.com/anthropics/claude-code-action/blob/main/examples/claude.yml), so in repositories with read-only defaults the workflow can start but Claude will fail when it tries to push changes or post comments.
Useful? React with 👍 / 👎.

greptile-apps · 2026-05-29T19:23:39Z

+ permissions:
+ contents: read
+ pull-requests: read
+ issues: read
+ id-token: write


Insufficient permissions for Claude to write back to the PR
Both this workflow and claude.yml set pull-requests: read and issues: read, but Claude needs write access to post review comments, create branches, or push commits. The claude_code_oauth_token authenticates Claude with the AI backend; GitHub API operations (posting comments, creating reviews, pushing code) go through the job's GITHUB_TOKEN, which is governed by this permissions block. With only read on pull-requests and issues, any attempt by Claude to leave a comment or open a review will fail at runtime. At minimum, pull-requests: write and issues: write are required; contents: write is needed if Claude should be able to commit changes. The same issue applies to the identical permissions block in claude.yml (lines 21–26).
Prompt To Fix With AI
This is a comment left during a code review. Path: .github/workflows/claude-code-review.yml Line: 22-26 Comment: **Insufficient permissions for Claude to write back to the PR** Both this workflow and `claude.yml` set `pull-requests: read` and `issues: read`, but Claude needs write access to post review comments, create branches, or push commits. The `claude_code_oauth_token` authenticates Claude with the AI backend; GitHub API operations (posting comments, creating reviews, pushing code) go through the job's `GITHUB_TOKEN`, which is governed by this `permissions` block. With only `read` on `pull-requests` and `issues`, any attempt by Claude to leave a comment or open a review will fail at runtime. At minimum, `pull-requests: write` and `issues: write` are required; `contents: write` is needed if Claude should be able to commit changes. The same issue applies to the identical permissions block in `claude.yml` (lines 21–26). How can I resolve this? If you propose a fix, please make it concise.

greptile-apps · 2026-05-29T19:23:40Z

+# This is an optional setting that allows Claude to read CI results on PRs
+additional_permissions: |
+ actions: read


Duplicate actions: read declaration
actions: read is already declared in the job-level permissions block (line 26) and is redundantly restated under additional_permissions. The additional_permissions input is documented for granting permissions beyond what the workflow's token carries; listing one that is already granted there has no effect and is misleading.
Suggested change
# This is an optional setting that allows Claude to read CI results on PRs
additional_permissions: |
actions: read
# This is an optional setting that allows Claude to read CI results on PRs
#additional_permissions is used for permissions beyond what the job token provides;
# 'actions: read' is already granted in the job permissions block above.
Prompt To Fix With AI
This is a comment left during a code review. Path: .github/workflows/claude.yml Line: 39-41 Comment: **Duplicate `actions: read` declaration**`actions: read` is already declared in the job-level `permissions` block (line 26) and is redundantly restated under `additional_permissions`. The `additional_permissions` input is documented for granting permissions beyond what the workflow's token carries; listing one that is already granted there has no effect and is misleading. ```suggestion # This is an optional setting that allows Claude to read CI results on PRs # additional_permissions is used for permissions beyond what the job token provides; # 'actions: read' is already granted in the job permissions block above.``` How can I resolve this? If you propose a fix, please make it concise.
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

greptile-apps · 2026-05-29T19:23:41Z

+if: |
+ (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+ (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+ (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+ (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))


No actor write-permission check — any commenter can trigger Claude
The trigger condition only checks whether the comment body contains @claude; it does not verify that the actor is a repository collaborator or has write access. On any public or organisation repo where outside users can comment on issues, this means an unauthenticated third party can invoke Claude (and consume the team's API quota) simply by posting a comment with @claude. Adding a check such as github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'OWNER' would restrict execution to trusted contributors.
Prompt To Fix With AI
This is a comment left during a code review. Path: .github/workflows/claude.yml Line: 15-19 Comment: **No actor write-permission check — any commenter can trigger Claude** The trigger condition only checks whether the comment body contains `@claude`; it does not verify that the actor is a repository collaborator or has write access. On any public or organisation repo where outside users can comment on issues, this means an unauthenticated third party can invoke Claude (and consume the team's API quota) simply by posting a comment with `@claude`. Adding a check such as `github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'OWNER'` would restrict execution to trusted contributors. How can I resolve this? If you propose a fix, please make it concise.

greptile-apps · 2026-05-29T19:23:42Z

+
+ - name: Run Claude Code Review
+ id: claude-review
+ uses: anthropics/claude-code-action@v1


Third-party action pinned to a mutable @v1 tag
anthropics/claude-code-action@v1 resolves to whatever commit the upstream maintainer points that tag at. If the tag is force-pushed with a compromised version, every future run fetches and executes untrusted code with the CLAUDE_CODE_OAUTH_TOKEN secret in scope. GitHub's own hardening guide recommends pinning to a full commit SHA (e.g. anthropics/claude-code-action@<sha>) and verifying it periodically. The same applies to the identical reference in claude.yml (line 35).
Prompt To Fix With AI
This is a comment left during a code review. Path: .github/workflows/claude-code-review.yml Line: 36 Comment: **Third-party action pinned to a mutable `@v1` tag**`anthropics/claude-code-action@v1` resolves to whatever commit the upstream maintainer points that tag at. If the tag is force-pushed with a compromised version, every future run fetches and executes untrusted code with the `CLAUDE_CODE_OAUTH_TOKEN` secret in scope. GitHub's own hardening guide recommends pinning to a full commit SHA (e.g. `anthropics/claude-code-action@<sha>`) and verifying it periodically. The same applies to the identical reference in `claude.yml` (line 35). How can I resolve this? If you propose a fix, please make it concise.

dodeja added 2 commits May 29, 2026 12:19

"Claude PR Assistant workflow"
643e093

"Claude Code Review workflow"
18f5e9f

vercelBotdeployed to Preview May 29, 2026 19:20 View deployment

chatgpt-codex-connectorBot reviewed May 29, 2026
View reviewed changes

greptile-appsBot reviewed May 29, 2026
View reviewed changes

dodeja merged commit 3a7fa77 into mainMay 29, 2026
16 of 17 checks passed

This was referenced May 29, 2026
fix(ci): address Greptile review on Claude Code workflows #230
Closed
ci(security): pin claude-code-action to a commit SHA #233
Merged

Navigation Menu

Uh oh!

Add Claude Code GitHub Workflow - #229

Add Claude Code GitHub Workflow#229
dodeja merged 2 commits into
mainfrom
add-claude-github-actions-1780082396660

dodeja commented May 29, 2026•
edited by greptile-apps Bot
Loading

Uh oh!

vercelBot commented May 29, 2026•
edited
Loading

Uh oh!

chatgpt-codex-connectorBot left a comment

Uh oh!

chatgpt-codex-connectorBotMay 29, 2026

Uh oh!

chatgpt-codex-connectorBotMay 29, 2026

Uh oh!

greptile-appsBotMay 29, 2026

Uh oh!

greptile-appsBotMay 29, 2026

Uh oh!

greptile-appsBotMay 29, 2026

Uh oh!

greptile-appsBotMay 29, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

dodeja commented May 29, 2026• edited by greptile-apps BotLoading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🤖 Installing Claude Code GitHub App

What is Claude Code?

How it works

Important Notes

Security

Greptile Summary

Confidence Score: 3/5

Important Files Changed

Sequence Diagram

Uh oh!

vercelBot commented May 29, 2026• edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

chatgpt-codex-connectorBot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connectorBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connectorBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

greptile-appsBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

greptile-appsBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

greptile-appsBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

greptile-appsBotMay 29, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

dodeja commented May 29, 2026•
edited by greptile-apps Bot
Loading

vercelBot commented May 29, 2026•
edited
Loading