anthropics/claude-code-action
1
0
Fork 0
mirror of https://github.com/anthropics/claude-code-action.git synced 2026-01-22 14:24:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: implement Claude Code GitHub Action v1.0 with auto-detection and slash commands (#421)

Browse Source 
* feat: implement Claude Code GitHub Action v1.0 with auto-detection and slash commands

Major features:
- Mode auto-detection based on GitHub event type
- Unified prompt field replacing override_prompt and direct_prompt
- Slash command system with pre-built commands
- Full backward compatibility with v0.x

Key changes:
- Add mode detector for automatic mode selection
- Implement slash command loader with YAML frontmatter support
- Update action.yml with new prompt input
- Create pre-built slash commands for common tasks
- Update all tests for v1.0 compatibility

Breaking changes (with compatibility):
- Mode input now optional (auto-detected)
- override_prompt deprecated (use prompt)
- direct_prompt deprecated (use prompt)

* test + formatting fixes

* feat: simplify to two modes (tag and agent) for v1.0

BREAKING CHANGES:
- Remove review mode entirely - now handled via slash commands in agent mode
- Remove all deprecated backward compatibility fields (mode, anthropic_model, override_prompt, direct_prompt)
- Simplify mode detection: prompt overrides everything, then @claude mentions trigger tag mode, default is agent mode
- Remove slash command resolution from GitHub Action - Claude Code handles natively
- Remove variable substitution - prompts passed through as-is

Architecture changes:
- Only two modes now: tag (for @claude mentions) and agent (everything else)
- Agent mode is the default for all events including PRs
- Users configure behavior via prompts/slash commands (e.g. /review)
- GitHub Action is now a thin wrapper that passes prompts to Claude Code
- Mode names changed: 'experimental-review' → removed entirely

This aligns with the philosophy that the GitHub Action should do minimal work and delegate to Claude Code for all intelligent behavior.

* fix: address PR review comments for v1.0 simplification

- Remove duplicate prompt field spread (line 160)
- Remove async from generatePrompt since slash commands are handled by Claude Code
- Add detailed comment explaining why prompt → agent mode logic
- Remove entire slash-commands loader and directories as Claude Code handles natively
- Simplify prompt generation to just pass through to Claude Code

These changes align with v1.0 philosophy: GitHub Action is a thin wrapper
that delegates everything to Claude Code for native handling.

* chore: remove unused js-yaml dependencies

These were added for slash-command YAML parsing but are no longer
needed since we removed slash-command preprocessing entirely

* fix: remove experimental-review mode reference from MCP config

The inline comment server configuration was checking for deprecated
'mode' field. Since review mode is removed in v1.0, this conditional
block is no longer needed.

* prettify

* feat: add claudeArgs input for direct CLI argument passing

- Add claude_args input to both action.yml files
- Implement shell-style argument parsing with quote handling
- Pass arguments directly to Claude CLI for maximum flexibility
- Add comprehensive tests for argument parsing
- Log custom arguments for debugging

Users can now pass any Claude CLI arguments directly:
  claude_args: '--max-turns 3 --mcp-config /path/to/config.json'

This provides power users full control over Claude's behavior without
waiting for specific inputs to be added to the action.

* refactor: use industry-standard shell-quote for argument parsing

- Replace custom parseShellArgs with battle-tested shell-quote package
- Simplify code by removing unnecessary -p filtering (Claude handles it)
- Update tests to use shell-quote directly
- Add example workflow showing claude_args usage

This provides more robust argument parsing while reducing code complexity.

* bun format

* feat: add claudeArgs input for direct CLI argument passing

- Add claude_args input to action.yml for flexible CLI control
- Parse arguments with industry-standard shell-quote library
- Maintain proper argument order: -p [claudeArgs] [legacy] [BASE_ARGS]
- Keep tag mode defaults (needed for functionality)
- Agent mode has no defaults (full user control)
- Add comprehensive tests for new functionality
- Add example workflow showing usage

* format

* refactor: complete v1.0 simplification by removing all legacy inputs

- Remove all backward compatibility for v1.0 simplification
- Remove 10 legacy inputs from base-action/action.yml
- Remove 9 legacy inputs from main action.yml
- Simplify ClaudeOptions type to just timeoutMinutes and claudeArgs
- Remove all legacy option handling from prepareRunConfig
- Update tests to remove references to deleted fields
- Remove obsolete test file github/context.test.ts
- Clean up types to remove customInstructions, allowedTools, disallowedTools

Users now use claudeArgs exclusively for CLI control.

* fix: update MCP server tests after removing additionalPermissions

- Change github_ci server logic to check for workflow token presence
- Update test names to reflect new behavior
- Fix test that was incorrectly setting workflow token

* model version update

* Update package json

* remove deprecated workflow file (tests features we no longer support)

* Simplify agent mode and re-add additional_permissions input

- Agent mode now only triggers when explicit prompt is provided
- Removed automatic triggering for workflow_dispatch/schedule without prompt
- Re-added additional_permissions input for requesting GitHub permissions
- Fixed TypeScript types for mock context helpers to properly handle partial inputs
- Updated documentation to reflect simplified mode behavior

* Fix MCP config not being passed to Claude CLI

The MCP servers (including github_comment server) were configured but not passed to Claude. This caused the "update_claude_comment" tool to be unavailable.

Changes:
- Write MCP config to a file at $RUNNER_TEMP/claude-mcp-config.json
- Add mcp_config_file output from prepare.ts
- Pass MCP config file via --mcp-config flag in claude_args
- Use fs/promises writeFile to match codebase conventions

* Fix MCP tool availability and shell escaping in tag mode

Pass MCP config and allowed tools through claude_args to ensure tools like
mcp__github_comment__update_claude_comment are properly available to Claude CLI.

Key changes:
- Tag mode outputs claude_args with MCP config (as JSON string) and allowed tools
- Fixed shell escaping vulnerability when JSON contains single quotes
- Agent mode passes through user-provided claude_args unchanged
- Re-added mcp_config input for users to provide custom MCP servers
- Cleaned up misleading comments and unused file operations
- Clarified test workflow is for fork testing

Security fix: Properly escape single quotes in MCP config JSON to prevent
shell injection vulnerabilities.

Co-Authored-By: Claude <noreply@anthropic.com>

* bun format

* tests, typecheck, format

* registry test update

* Update agent mode to have github server as a default

* Fix agent mode to include GitHub MCP server with proper token

* Simplify review workflow - prevent multiple submissions

- Rename workflow to avoid conflicts
- Remove review submission tools
- Keep only essential tools for reading and analyzing PR

* Add GitHub MCP server and context prefix to agent mode

- Include main GitHub MCP server (Docker-based) by default
- Fetch and prefix GitHub context to prompts when in PR/issue context
- Users no longer need to manually configure GitHub tools

* Delete .github/workflows/claude-auto-review-test.yml

* Remove github_comment and inline_comment servers from agent mode defaults

- Agent mode now only includes the main GitHub MCP server by default
- Users can add additional servers via mcp_config if needed
- Reduces unnecessary MCP server overhead

* Remove all default MCP servers from agent mode

Agent mode now starts with no default servers - users must explicitly configure any MCP servers they need via mcp_config input

* Remove GitHub context prefixing and clean up agent mode

- Remove automatic GitHub context fetching and prefixing
- Remove unused imports (fetcher, formatter, context checks)
- Clean up comments
- Agent mode now simply passes through the user's prompt as-is

* Add GitHub MCP support to agent mode

- Parse --allowedTools from claude_args to detect when user wants GitHub MCPs
- Wire up github_inline_comment server in prepareMcpConfig for PR contexts
- Update agent mode to use prepareMcpConfig instead of manual config
- Add comprehensive tests for parseAllowedTools edge cases
- Fix TypeScript types to support both entity and automation contexts

* Format code with prettier

* Fix agent mode test to expect branch values

* Fix agent test to handle dynamic branch names from environment

* Better fix: Control environment variables in agent test for predictable behavior

* minor formatting

* Simplify MCP configuration to use multiple --mcp-config flags

- Remove MCP config merging logic from prepareMcpConfig
- Update agent and tag modes to pass multiple --mcp-config flags
- Let Claude handle config merging natively through multiple flags
- Fix TypeScript errors in test file

This approach is cleaner and relies on Claude's built-in support for multiple --mcp-config flags instead of manual JSON merging.

* feat: Copy project subagents to Claude runtime environment

Enables custom subagents defined in .claude/agents/ to work in GitHub Actions by:
- Checking for project agents in GITHUB_WORKSPACE/.claude/agents/
- Creating ~/.claude/agents/ directory if needed
- Copying all .md agent files to Claude's runtime location
- Following same pattern as slash commands for consistency

Includes comprehensive test coverage for the new functionality.

* formatting

* Add auto-fix CI workflows with slash command and inline approaches

- Add /fix-ci slash command for programmatic CI failure fixing
- Create auto-fix-ci.yml workflow using slash command approach
- Create auto-fix-ci-inline.yml workflow with full inline prompt
- Both workflows automatically analyze CI failures and create fix branches

* Add workflow_run event support and auto-fix CI workflows

- Add support for workflow_run event type in GitHub context
- Create /fix-ci slash command for programmatic CI failure fixing
- Add auto-fix-ci.yml workflow using slash command approach
- Add auto-fix-ci-inline.yml workflow with full inline prompt
- Both workflows automatically analyze CI failures and create fix branches
- Fix workflow syntax issues with optional chaining operator

* Use proper WorkflowRunEvent type instead of any

* bun formatting

* Remove auto-fix workflows and commands from v1-dev

These files should only exist in km-anthropic fork:
- .github/workflows/auto-fix-ci.yml
- .github/workflows/auto-fix-ci-inline.yml
- slash-commands/fix-ci.md
- .claude/commands/fix-ci.md

The workflow_run event support remains as it's useful for general automation.

* feat: Expose GitHub token as action output for external use

This allows workflows to use the Claude App token obtained by the action
for posting comments as claude[bot] instead of github-actions[bot].

Changes:
- Add github_token output to action.yml
- Export token from prepare.ts after authentication
- Allows workflows to use the same token Claude uses internally

* Debug: Add logging and always output github_token in prepare step

* Fix: Add git authentication to agent mode

Agent mode now fetches the authenticated user (claude[bot] when using Claude App token)
and configures git identity properly, matching the behavior of tag mode.

This fixes the issue where commits in agent mode were failing due to missing git identity.

* minor bun format

* remove unnecessary file

* fix: Add branch environment variable support to agent mode for signed commits

- Read CLAUDE_BRANCH and BASE_BRANCH env vars in agent mode
- Pass correct branch info to MCP file ops server
- Enables signed auto-fix workflows to create branches via API

* feat: Add auto-fix CI workflow examples

- Add auto-fix-ci example with inline git commits
- Add auto-fix-ci-signed example with signed commits via MCP
- Include corresponding slash commands for both workflows
- Examples demonstrate automated CI failure detection and fixing

* fix: Fix TypeScript error in agent mode git config

- Remove dependency on configureGitAuth which expects ParsedGitHubContext
- Implement git configuration directly for automation contexts
- Properly handle git authentication for agent mode

* fix: Align agent mode git config with existing patterns

- Use GITHUB_SERVER_URL from config module consistently
- Remove existing headers before setting new ones
- Use remote URL with embedded token like git-config.ts does
- Match the existing git authentication pattern in the codebase

* refactor: Use shared configureGitAuth function in agent mode

- Update configureGitAuth to accept GitHubContext instead of ParsedGitHubContext
- This allows both tag mode and agent mode to use the same function
- Removes code duplication and ensures consistent git configuration

* feat: Improve error message for 403 permission errors when committing

When the github_file_ops MCP server gets a 403 error, it now shows a cleaner
message suggesting to rebase from main/master branch to fix the issue.

* docs: Update documentation for v1.0 release (#476)

* docs: Update documentation for v1.0 release

- Integrate breaking changes naturally without alarming users
- Replace deprecated inputs (direct_prompt, custom_instructions, mode) with new unified approach
- Update all examples to use prompt and claude_args instead of deprecated inputs
- Add migration guides to help users transition from v0.x to v1.0
- Emphasize automatic mode detection as a key feature
- Update all workflow examples to @v1 from @beta
- Document how claude_args provides direct CLI control
- Update FAQ with automatic mode detection explanation
- Convert all tool configuration to use claude_args format

* fix: Apply prettier formatting to documentation files

* fix: Update all Claude model versions to latest and improve documentation accuracy

- Update all model references to claude-4-0-sonnet-20250805 (latest Sonnet 4)
- Update Bedrock models to anthropic.claude-4-0-sonnet-20250805-v1:0
- Update Vertex models to claude-4-0-sonnet@20250805
- Fix cloud-providers.md to use claude_args instead of deprecated model input
- Ensure all examples use @v1 instead of @beta
- Keep claude-opus-4-1-20250805 in examples where Opus is demonstrated
- Align all documentation with v1.0 patterns consistently

* feat: Add dedicated migration guide as requested in PR feedback

- Create comprehensive migration-guide.md with step-by-step instructions
- Add prominent links to migration guide in README.md
- Update usage.md to reference the separate migration guide
- Include before/after examples for all common scenarios
- Add checklist for systematic migration
- Address Ashwin's feedback about having a separate, clearly linked migration guide

* feat: Add comprehensive examples for hero use cases

- Add dedicated issue deduplication workflow example
- Add issue triage example (moved from .github/workflows)
- Update all examples to use v1-dev branch consistently
- Enable MCP tools in claude-auto-review.yml
- Consolidate PR review examples into single comprehensive example

Hero use cases now covered:
1. Code reviews (claude-auto-review.yml)
2. Issue triaging (issue-triage.yml)
3. Issue deduplication (issue-deduplication.yml)
4. Auto-fix CI failures (auto-fix-ci/auto-fix-ci.yml)

All examples updated to follow v1-dev paradigm with proper prompt and claude_args configuration.

* refactor: Remove timeout_minutes parameter from action (#482)

This change removes the custom timeout_minutes parameter from the action in favor of using GitHub Actions' native timeout-minutes feature.

Changes:
- Removed timeout_minutes input from action.yml and base-action/action.yml
- Removed all timeout handling logic from base-action/src/run-claude.ts
- Updated base-action/src/index.ts to remove timeoutMinutes parameter
- Removed timeout-related tests from base-action/test/run-claude.test.ts
- Removed timeout_minutes from all example workflow files (19 files)

Rationale:
- Simplifies the codebase by removing custom timeout logic
- Users can use GitHub Actions' native timeout-minutes at the job/step level
- Reduces complexity and maintenance burden
- Follows GitHub Actions best practices

BREAKING CHANGE: The timeout_minutes parameter is no longer supported. Users should use GitHub Actions' native timeout-minutes instead.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <noreply@anthropic.com>

* refactor: Remove unused slash commands and agents copying logic

Removes experimental file copying features that had no default content:
- Removed experimental_slash_commands_dir parameter and related logic
- Removed automatic project agents copying from .claude/agents/
- Eliminated flaky error-prone cp operations with stderr suppression
- Removed 175 lines of unused code and associated tests

These features were infrastructure without default content that used
problematic error handling patterns (2>/dev/null || true) which could
hide real filesystem errors.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* docs: Remove references to timeout_minutes parameter

The timeout_minutes parameter was removed in commit 986e40a but
documentation still referenced it. This updates:
- docs/usage.md: Removed timeout_minutes from inputs table
- base-action/README.md: Removed from inputs table and example

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kashyap Murali <13315300+katchu11@users.noreply.github.com>
This commit is contained in:
km-anthropic
2025-08-25 12:51:37 -07:00
committed by GitHub
parent 9c7e1bac94
commit 0630ef383a
68 changed files with 2315 additions and 2387 deletions
Download Patch File Download Diff File Expand all files Collapse all files

97
examples/auto-fix-ci-signed/auto-fix-ci-signed.yml Normal file
View File

@@ -0,0 +1,97 @@
name: Auto Fix CI Failures (Signed Commits)
on:
workflow_run:
workflows: ["CI"]
types:
- completed
permissions:
contents: write
pull-requests: write
actions: read
issues: write
id-token: write # Required for OIDC token exchange
jobs:
auto-fix-signed:
if: |
github.event.workflow_run.conclusion == 'failure' &&
github.event.workflow_run.pull_requests[0] &&
!startsWith(github.event.workflow_run.head_branch, 'claude-auto-fix-ci-signed-')
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ github.event.workflow_run.head_branch }}
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}
- name: Generate fix branch name
id: branch
run: |
BRANCH_NAME="claude-auto-fix-ci-signed-${{ github.event.workflow_run.head_branch }}-${{ github.run_id }}"
echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
# Don't create branch locally - MCP tools will create it via API
echo "Generated branch name: $BRANCH_NAME (will be created by MCP tools)"
- name: Get CI failure details
id: failure_details
uses: actions/github-script@v7
with:
script: |
const run = await github.rest.actions.getWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: ${{ github.event.workflow_run.id }}
});
const jobs = await github.rest.actions.listJobsForWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: ${{ github.event.workflow_run.id }}
});
const failedJobs = jobs.data.jobs.filter(job => job.conclusion === 'failure');
let errorLogs = [];
for (const job of failedJobs) {
const logs = await github.rest.actions.downloadJobLogsForWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
job_id: job.id
});
errorLogs.push({
jobName: job.name,
logs: logs.data
});
}
return {
runUrl: run.data.html_url,
failedJobs: failedJobs.map(j => j.name),
errorLogs: errorLogs
};
- name: Fix CI failures with Claude (Signed Commits)
id: claude
uses: anthropics/claude-code-action@v1-dev
env:
CLAUDE_BRANCH: ${{ steps.branch.outputs.branch_name }}
BASE_BRANCH: ${{ github.event.workflow_run.head_branch }}
with:
prompt: |
/fix-ci-signed
Failed CI Run: ${{ fromJSON(steps.failure_details.outputs.result).runUrl }}
Failed Jobs: ${{ join(fromJSON(steps.failure_details.outputs.result).failedJobs, ', ') }}
PR Number: ${{ github.event.workflow_run.pull_requests[0].number }}
Branch Name: ${{ steps.branch.outputs.branch_name }}
Base Branch: ${{ github.event.workflow_run.head_branch }}
Repository: ${{ github.repository }}
Error logs:
${{ toJSON(fromJSON(steps.failure_details.outputs.result).errorLogs) }}
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
use_commit_signing: true
claude_args: "--allowedTools 'Edit,MultiEdit,Write,Read,Glob,Grep,LS,Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*),mcp__github_file_ops__commit_files,mcp__github_file_ops__delete_files'"

148
examples/auto-fix-ci-signed/commands/fix-ci-signed.md Normal file
View File

@@ -0,0 +1,148 @@
---
description: Analyze and fix CI failures with signed commits using MCP tools
allowed_tools: Edit,MultiEdit,Write,Read,Glob,Grep,LS,Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*),mcp__github_file_ops__commit_files,mcp__github_file_ops__delete_files
---
# Fix CI Failures with Signed Commits
You are tasked with analyzing CI failure logs and fixing the issues using MCP tools for signed commits. Follow these steps:
## Context Provided
$ARGUMENTS
## Important Context Information
Look for these key pieces of information in the arguments:
- **Failed CI Run URL**: Link to the failed CI run
- **Failed Jobs**: List of jobs that failed
- **PR Number**: The PR number to comment on
- **Branch Name**: The fix branch you're working on
- **Base Branch**: The original PR branch
- **Error logs**: Detailed logs from failed jobs
## CRITICAL: Use MCP Tools for Git Operations
**IMPORTANT**: You MUST use MCP tools for all git operations to ensure commits are properly signed. DO NOT use `git` commands directly via Bash.
- Use `mcp__github_file_ops__commit_files` to commit and push changes
- Use `mcp__github_file_ops__delete_files` to delete files
## Step 1: Analyze the Failure
Parse the provided CI failure information to understand:
- Which jobs failed and why
- The specific error messages and stack traces
- Whether failures are test-related, build-related, or linting issues
## Step 2: Search and Understand the Codebase
Use MCP search tools to locate the failing code:
- Use `mcp_github_file_ops_server__search_files` or `mcp_github_file_ops_server__file_search` to find failing test names or functions
- Use `mcp_github_file_ops_server__read_file` to read source files mentioned in error messages
- Review related configuration files (package.json, tsconfig.json, etc.)
## Step 3: Apply Targeted Fixes
Make minimal, focused changes:
- **For test failures**: Determine if the test or implementation needs fixing
- **For type errors**: Fix type definitions or correct the code logic
- **For linting issues**: Apply formatting using the project's tools
- **For build errors**: Resolve dependency or configuration issues
- **For missing imports**: Add the necessary imports or install packages
Requirements:
- Only fix the actual CI failures, avoid unrelated changes
- Follow existing code patterns and conventions
- Ensure changes are production-ready, not temporary hacks
- Preserve existing functionality while fixing issues
## Step 4: Verify Fixes Locally
Run available verification commands using Bash:
- Execute the failing tests locally to confirm they pass
- Run the project's lint command (check package.json for scripts)
- Run type checking if available
- Execute any build commands to ensure compilation succeeds
## Step 5: Commit and Push Changes Using MCP
**CRITICAL**: You MUST use MCP tools for committing and pushing:
1. Prepare all your file changes (using Edit/MultiEdit/Write tools as needed)
2. **Use `mcp__github_file_ops__commit_files` to commit and push all changes**
- Pass the file paths you've edited in the `files` array
- Set `message` to describe the specific fixes (e.g., "Fix CI failures: remove syntax errors and format code")
- The MCP tool will automatically create the branch specified in "Branch Name:" from the context and push signed commits
**IMPORTANT**: The MCP tool will create the branch from the context automatically. The branch name from "Branch Name:" in the context will be used.
Example usage:
```
mcp__github_file_ops__commit_files with:
- files: ["src/utils/retry.ts", "src/other/file.ts"] // List of file paths you edited
- message: "Fix CI failures: [describe specific fixes]"
```
Note: The branch will be created from the Base Branch specified in the context.
## Step 6: Create PR Comment (REQUIRED - DO NOT SKIP)
**CRITICAL: You MUST create a PR comment after pushing. This step is MANDATORY.**
After successfully pushing the fixes, you MUST create a comment on the original PR to notify about the auto-fix. DO NOT end the task without completing this step.
1. Extract the PR number from the context provided in arguments (look for "PR Number:" in the context)
2. **MANDATORY**: Execute the gh CLI command below to create the comment
3. Verify the comment was created successfully
**YOU MUST RUN THIS COMMAND** (replace placeholders with actual values from context):
```bash
gh pr comment PR_NUMBER --body "## 🤖 CI Auto-Fix Available (Signed Commits)
Claude has analyzed the CI failures and prepared fixes with signed commits.
[**→ Create pull request to fix CI**](https://github.com/OWNER/REPO/compare/BASE_BRANCH...FIX_BRANCH?quick_pull=1)
_This fix was generated automatically based on the [failed CI run](FAILED_CI_RUN_URL)._"
```
**IMPORTANT REPLACEMENTS YOU MUST MAKE:**
- Replace `PR_NUMBER` with the actual PR number from "PR Number:" in context
- Replace `OWNER/REPO` with the repository from "Repository:" in context
- Replace `BASE_BRANCH` with the branch from "Base Branch:" in context
- Replace `FIX_BRANCH` with the branch from "Branch Name:" in context
- Replace `FAILED_CI_RUN_URL` with the URL from "Failed CI Run:" in context
**DO NOT SKIP THIS STEP. The task is NOT complete until the PR comment is created.**
## Step 7: Final Verification
**BEFORE CONSIDERING THE TASK COMPLETE**, verify you have:
1. ✅ Fixed all CI failures
2. ✅ Committed the changes using `mcp_github_file_ops_server__push_files`
3. ✅ Verified the branch was pushed successfully
4. ✅ **CREATED THE PR COMMENT using `gh pr comment` command from Step 6**
If you have NOT created the PR comment, go back to Step 6 and execute the command.
## Important Guidelines
- Always use MCP tools for git operations to ensure proper commit signing
- Focus exclusively on fixing the reported CI failures
- Maintain code quality and follow the project's established patterns
- If a fix requires significant refactoring, document why it's necessary
- When multiple solutions exist, choose the simplest one that maintains code quality
- **THE TASK IS NOT COMPLETE WITHOUT THE PR COMMENT**
Begin by analyzing the failure details provided above.

97
examples/auto-fix-ci/auto-fix-ci.yml Normal file
View File

@@ -0,0 +1,97 @@
name: Auto Fix CI Failures
on:
workflow_run:
workflows: ["CI"]
types:
- completed
permissions:
contents: write
pull-requests: write
actions: read
issues: write
id-token: write # Required for OIDC token exchange
jobs:
auto-fix:
if: |
github.event.workflow_run.conclusion == 'failure' &&
github.event.workflow_run.pull_requests[0] &&
!startsWith(github.event.workflow_run.head_branch, 'claude-auto-fix-ci-')
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ github.event.workflow_run.head_branch }}
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}
- name: Setup git identity
run: |
git config --global user.email "claude[bot]@users.noreply.github.com"
git config --global user.name "claude[bot]"
- name: Create fix branch
id: branch
run: |
BRANCH_NAME="claude-auto-fix-ci-${{ github.event.workflow_run.head_branch }}-${{ github.run_id }}"
git checkout -b "$BRANCH_NAME"
echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
- name: Get CI failure details
id: failure_details
uses: actions/github-script@v7
with:
script: |
const run = await github.rest.actions.getWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: ${{ github.event.workflow_run.id }}
});
const jobs = await github.rest.actions.listJobsForWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: ${{ github.event.workflow_run.id }}
});
const failedJobs = jobs.data.jobs.filter(job => job.conclusion === 'failure');
let errorLogs = [];
for (const job of failedJobs) {
const logs = await github.rest.actions.downloadJobLogsForWorkflowRun({
owner: context.repo.owner,
repo: context.repo.repo,
job_id: job.id
});
errorLogs.push({
jobName: job.name,
logs: logs.data
});
}
return {
runUrl: run.data.html_url,
failedJobs: failedJobs.map(j => j.name),
errorLogs: errorLogs
};
- name: Fix CI failures with Claude
id: claude
uses: anthropics/claude-code-action@v1-dev
with:
prompt: |
/fix-ci
Failed CI Run: ${{ fromJSON(steps.failure_details.outputs.result).runUrl }}
Failed Jobs: ${{ join(fromJSON(steps.failure_details.outputs.result).failedJobs, ', ') }}
PR Number: ${{ github.event.workflow_run.pull_requests[0].number }}
Branch Name: ${{ steps.branch.outputs.branch_name }}
Base Branch: ${{ github.event.workflow_run.head_branch }}
Repository: ${{ github.repository }}
Error logs:
${{ toJSON(fromJSON(steps.failure_details.outputs.result).errorLogs) }}
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
claude_args: "--allowedTools 'Edit,MultiEdit,Write,Read,Glob,Grep,LS,Bash(git:*),Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*)'"

127
examples/auto-fix-ci/commands/fix-ci.md Normal file
View File

@@ -0,0 +1,127 @@
---
description: Analyze and fix CI failures by examining logs and making targeted fixes
allowed_tools: Edit,MultiEdit,Write,Read,Glob,Grep,LS,Bash(git:*),Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*)
---
# Fix CI Failures
You are tasked with analyzing CI failure logs and fixing the issues. Follow these steps:
## Context Provided
$ARGUMENTS
## Important Context Information
Look for these key pieces of information in the arguments:
- **Failed CI Run URL**: Link to the failed CI run
- **Failed Jobs**: List of jobs that failed
- **PR Number**: The PR number to comment on
- **Branch Name**: The fix branch you're working on
- **Base Branch**: The original PR branch
- **Error logs**: Detailed logs from failed jobs
## Step 1: Analyze the Failure
Parse the provided CI failure information to understand:
- Which jobs failed and why
- The specific error messages and stack traces
- Whether failures are test-related, build-related, or linting issues
## Step 2: Search and Understand the Codebase
Use search tools to locate the failing code:
- Search for the failing test names or functions
- Find the source files mentioned in error messages
- Review related configuration files (package.json, tsconfig.json, etc.)
## Step 3: Apply Targeted Fixes
Make minimal, focused changes:
- **For test failures**: Determine if the test or implementation needs fixing
- **For type errors**: Fix type definitions or correct the code logic
- **For linting issues**: Apply formatting using the project's tools
- **For build errors**: Resolve dependency or configuration issues
- **For missing imports**: Add the necessary imports or install packages
Requirements:
- Only fix the actual CI failures, avoid unrelated changes
- Follow existing code patterns and conventions
- Ensure changes are production-ready, not temporary hacks
- Preserve existing functionality while fixing issues
## Step 4: Verify Fixes Locally
Run available verification commands:
- Execute the failing tests locally to confirm they pass
- Run the project's lint command (check package.json for scripts)
- Run type checking if available
- Execute any build commands to ensure compilation succeeds
## Step 5: Commit and Push Changes
After applying ALL fixes:
1. Stage all modified files with `git add -A`
2. Commit with: `git commit -m "Fix CI failures: [describe specific fixes]"`
3. Document which CI jobs/tests were addressed
4. **CRITICAL**: Push the branch with `git push origin HEAD` - You MUST push the branch after committing
## Step 6: Create PR Comment (REQUIRED - DO NOT SKIP)
**CRITICAL: You MUST create a PR comment after pushing. This step is MANDATORY.**
After successfully pushing the fixes, you MUST create a comment on the original PR to notify about the auto-fix. DO NOT end the task without completing this step.
1. Extract the PR number from the context provided in arguments (look for "PR Number:" in the context)
2. **MANDATORY**: Execute the gh CLI command below to create the comment
3. Verify the comment was created successfully
**YOU MUST RUN THIS COMMAND** (replace placeholders with actual values from context):
```bash
gh pr comment PR_NUMBER --body "## 🤖 CI Auto-Fix Available
Claude has analyzed the CI failures and prepared fixes.
[**→ Create pull request to fix CI**](https://github.com/OWNER/REPO/compare/BASE_BRANCH...FIX_BRANCH?quick_pull=1)
_This fix was generated automatically based on the [failed CI run](FAILED_CI_RUN_URL)._"
```
**IMPORTANT REPLACEMENTS YOU MUST MAKE:**
- Replace `PR_NUMBER` with the actual PR number from "PR Number:" in context
- Replace `OWNER/REPO` with the repository from "Repository:" in context
- Replace `BASE_BRANCH` with the branch from "Base Branch:" in context
- Replace `FIX_BRANCH` with the branch from "Branch Name:" in context
- Replace `FAILED_CI_RUN_URL` with the URL from "Failed CI Run:" in context
**DO NOT SKIP THIS STEP. The task is NOT complete until the PR comment is created.**
## Step 7: Final Verification
**BEFORE CONSIDERING THE TASK COMPLETE**, verify you have:
1. ✅ Fixed all CI failures
2. ✅ Committed the changes
3. ✅ Pushed the branch with `git push origin HEAD`
4. ✅ **CREATED THE PR COMMENT using `gh pr comment` command from Step 6**
If you have NOT created the PR comment, go back to Step 6 and execute the command.
## Important Guidelines
- Focus exclusively on fixing the reported CI failures
- Maintain code quality and follow the project's established patterns
- If a fix requires significant refactoring, document why it's necessary
- When multiple solutions exist, choose the simplest one that maintains code quality
- **THE TASK IS NOT COMPLETE WITHOUT THE PR COMMENT**
Begin by analyzing the failure details provided above.

30
examples/claude-args-example.yml Normal file
View File

@@ -0,0 +1,30 @@
name: Claude Args Example
on:
workflow_dispatch:
inputs:
prompt:
description: "Prompt for Claude"
required: true
type: string
jobs:
claude-with-custom-args:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Run Claude with custom arguments
uses: anthropics/claude-code-action@v1-dev
with:
prompt: ${{ github.event.inputs.prompt }}
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
# claude_args provides direct CLI argument control
# This allows full customization of Claude's behavior
claude_args: |
--max-turns 15
--model claude-opus-4-1-20250805
--allowedTools Edit,Read,Write,Bash
--disallowedTools WebSearch
--system-prompt "You are a senior engineer focused on code quality"

12
examples/claude-auto-review.yml
View File

@@ -1,4 +1,4 @@
name: Claude Auto Review
name: Claude PR Auto Review
on:
pull_request:
@@ -18,11 +18,10 @@ jobs:
fetch-depth: 1
- name: Automatic PR Review
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
timeout_minutes: "60"
direct_prompt: |
prompt: |
Please review this pull request and provide comprehensive feedback.
Focus on:
@@ -32,7 +31,10 @@ jobs:
- Security implications
- Test coverage
- Documentation updates if needed
- Verify that README.md and docs are updated for any new features or config changes
Provide constructive feedback with specific suggestions for improvement.
Use inline comments to highlight specific areas of concern.
# allowed_tools: "mcp__github__create_pending_pull_request_review,mcp__github__add_comment_to_pending_review,mcp__github__submit_pending_pull_request_review,mcp__github__get_pull_request_diff"
claude_args: |
--allowedTools "mcp__github__create_pending_pull_request_review,mcp__github__add_comment_to_pending_review,mcp__github__submit_pending_pull_request_review,mcp__github__get_pull_request_diff"

8
examples/claude-experimental-review-mode.yml
View File

@@ -27,13 +27,13 @@ jobs:
fetch-depth: 0 # Full history for better diff analysis
- name: Code Review with Claude
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
mode: experimental-review
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
# github_token not needed - uses default GITHUB_TOKEN for GitHub operations
timeout_minutes: "30"
custom_instructions: |
prompt: |
Review this pull request comprehensively.
Focus on:
- Code quality and maintainability
- Security vulnerabilities

34
examples/claude-modes.yml
View File

@@ -1,21 +1,21 @@
name: Claude Mode Examples
name: Claude Automatic Mode Detection Examples
on:
# Events for tag mode
# Events for interactive mode (responds to @claude mentions)
issue_comment:
types: [created]
issues:
types: [opened, labeled]
pull_request:
types: [opened]
# Events for agent mode (only these work with agent mode)
# Events for automation mode (runs with explicit prompt)
workflow_dispatch:
schedule:
- cron: "0 0 * * 0" # Weekly on Sunday
jobs:
# Tag Mode (Default) - Traditional implementation
tag-mode-example:
# Interactive Mode - Activated automatically when no prompt is provided
interactive-mode-example:
runs-on: ubuntu-latest
permissions:
contents: write
@@ -23,18 +23,17 @@ jobs:
issues: write
id-token: write
steps:
- uses: anthropics/claude-code-action@beta
- uses: anthropics/claude-code-action@v1-dev
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
# Tag mode (default) behavior:
# Interactive mode (auto-detected when no prompt):
# - Scans for @claude mentions in comments, issues, and PRs
# - Only acts when trigger phrase is found
# - Creates tracking comments with progress checkboxes
# - Perfect for: Interactive Q&A, on-demand code changes
# Agent Mode - Automation for workflow_dispatch and schedule events
agent-mode-scheduled-task:
# Only works with workflow_dispatch or schedule events
# Automation Mode - Activated automatically when prompt is provided
automation-mode-scheduled-task:
runs-on: ubuntu-latest
permissions:
contents: write
@@ -42,15 +41,14 @@ jobs:
issues: write
id-token: write
steps:
- uses: anthropics/claude-code-action@beta
- uses: anthropics/claude-code-action@v1-dev
with:
mode: agent
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
override_prompt: |
prompt: |
Check for outdated dependencies and security vulnerabilities.
Create an issue if any critical problems are found.
# Agent mode behavior:
# - ONLY works with workflow_dispatch and schedule events
# - Does NOT work with pull_request, issues, or issue_comment events
# - No @claude mention needed for supported events
# - Perfect for: scheduled maintenance, manual automation runs
# Automation mode (auto-detected when prompt provided):
# - Works with any GitHub event
# - Executes immediately without waiting for @claude mentions
# - No tracking comments created
# - Perfect for: scheduled maintenance, automated reviews, CI/CD tasks

5
examples/claude-pr-path-specific.yml
View File

@@ -24,11 +24,10 @@ jobs:
fetch-depth: 1
- name: Claude Code Review
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
timeout_minutes: "60"
direct_prompt: |
prompt: |
Please review this pull request focusing on the changed files.
Provide feedback on:
- Code quality and adherence to best practices

5
examples/claude-review-from-author.yml
View File

@@ -23,11 +23,10 @@ jobs:
fetch-depth: 1
- name: Review PR from Specific Author
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
timeout_minutes: "60"
direct_prompt: |
prompt: |
Please provide a thorough review of this pull request.
Since this is from a specific author that requires careful review,

29
examples/claude.yml
View File

@@ -32,7 +32,7 @@ jobs:
- name: Run Claude Code
id: claude
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -40,24 +40,23 @@ jobs:
additional_permissions: |
actions: read
# Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4.1)
# model: "claude-opus-4-1-20250805"
# Optional: Customize the trigger phrase (default: @claude)
# trigger_phrase: "/claude"
# Optional: Trigger when specific user is assigned to an issue
# assignee_trigger: "claude-bot"
# Optional: Allow Claude to run specific commands
# allowed_tools: "Bash(npm install),Bash(npm run build),Bash(npm run test:*),Bash(npm run lint:*)"
# Optional: Configure Claude's behavior with CLI arguments
# claude_args: |
# --model claude-opus-4-1-20250805
# --max-turns 10
# --allowedTools "Bash(npm install),Bash(npm run build),Bash(npm run test:*),Bash(npm run lint:*)"
# --system-prompt "Follow our coding standards. Ensure all new code has tests. Use TypeScript for new files."
# Optional: Add custom instructions for Claude to customize its behavior for your project
# custom_instructions: |
# Follow our coding standards
# Ensure all new code has tests
# Use TypeScript for new files
# Optional: Custom environment variables for Claude
# claude_env: |
# NODE_ENV: test
# Optional: Advanced settings configuration
# settings: |
# {
# "env": {
# "NODE_ENV": "test"
# }
# }

63
examples/issue-deduplication.yml Normal file
View File

@@ -0,0 +1,63 @@
name: Issue Deduplication
on:
issues:
types: [opened]
jobs:
deduplicate:
runs-on: ubuntu-latest
timeout-minutes: 10
permissions:
contents: read
issues: write
id-token: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Check for duplicate issues
uses: anthropics/claude-code-action@v1-dev
with:
prompt: |
Analyze this new issue and check if it's a duplicate of existing issues in the repository.
Issue: #${{ github.event.issue.number }}
Repository: ${{ github.repository }}
Your task:
1. Use mcp__github__get_issue to get details of the current issue (#${{ github.event.issue.number }})
2. Search for similar existing issues using mcp__github__search_issues with relevant keywords from the issue title and body
3. Compare the new issue with existing ones to identify potential duplicates
Criteria for duplicates:
- Same bug or error being reported
- Same feature request (even if worded differently)
- Same question being asked
- Issues describing the same root problem
If you find duplicates:
- Add a comment on the new issue linking to the original issue(s)
- Apply a "duplicate" label to the new issue
- Be polite and explain why it's a duplicate
- Suggest the user follow the original issue for updates
If it's NOT a duplicate:
- Don't add any comments
- You may apply appropriate topic labels based on the issue content
Use these tools:
- mcp__github__get_issue: Get issue details
- mcp__github__search_issues: Search for similar issues
- mcp__github__list_issues: List recent issues if needed
- mcp__github__create_issue_comment: Add a comment if duplicate found
- mcp__github__update_issue: Add labels
Be thorough but efficient. Focus on finding true duplicates, not just similar issues.
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
claude_args: |
--allowedTools "mcp__github__get_issue,mcp__github__search_issues,mcp__github__list_issues,mcp__github__create_issue_comment,mcp__github__update_issue,mcp__github__get_issue_comments"

75
examples/issue-triage.yml Normal file
View File

@@ -0,0 +1,75 @@
name: Issue Triage
on:
issues:
types: [opened]
jobs:
triage-issue:
runs-on: ubuntu-latest
timeout-minutes: 10
permissions:
contents: read
issues: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Triage issue with Claude
uses: anthropics/claude-code-action@v1-dev
with:
prompt: |
You're an issue triage assistant for GitHub issues. Your task is to analyze the issue and select appropriate labels from the provided list.
IMPORTANT: Don't post any comments or messages to the issue. Your only action should be to apply labels.
Issue Information:
- REPO: ${{ github.repository }}
- ISSUE_NUMBER: ${{ github.event.issue.number }}
TASK OVERVIEW:
1. First, fetch the list of labels available in this repository by running: `gh label list`. Run exactly this command with nothing else.
2. Next, use the GitHub tools to get context about the issue:
- You have access to these tools:
- mcp__github__get_issue: Use this to retrieve the current issue's details including title, description, and existing labels
- mcp__github__get_issue_comments: Use this to read any discussion or additional context provided in the comments
- mcp__github__update_issue: Use this to apply labels to the issue (do not use this for commenting)
- mcp__github__search_issues: Use this to find similar issues that might provide context for proper categorization and to identify potential duplicate issues
- mcp__github__list_issues: Use this to understand patterns in how other issues are labeled
- Start by using mcp__github__get_issue to get the issue details
3. Analyze the issue content, considering:
- The issue title and description
- The type of issue (bug report, feature request, question, etc.)
- Technical areas mentioned
- Severity or priority indicators
- User impact
- Components affected
4. Select appropriate labels from the available labels list provided above:
- Choose labels that accurately reflect the issue's nature
- Be specific but comprehensive
- Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
- Consider platform labels (android, ios) if applicable
- If you find similar issues using mcp__github__search_issues, consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
5. Apply the selected labels:
- Use mcp__github__update_issue to apply your selected labels
- DO NOT post any comments explaining your decision
- DO NOT communicate directly with users
- If no labels are clearly applicable, do not apply any labels
IMPORTANT GUIDELINES:
- Be thorough in your analysis
- Only select labels from the provided list above
- DO NOT post any comments to the issue
- Your ONLY action should be to apply labels using mcp__github__update_issue
- It's okay to not add any labels if none are clearly applicable
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
claude_args: |
--allowedTools "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"

5
examples/workflow-dispatch-agent.yml
View File

@@ -28,11 +28,10 @@ jobs:
fetch-depth: 2 # Need at least 2 commits to analyze the latest
- name: Run Claude Analysis
uses: anthropics/claude-code-action@beta
uses: anthropics/claude-code-action@v1-dev
with:
mode: agent
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
override_prompt: |
prompt: |
Analyze the latest commit in this repository.
${{ github.event.inputs.analysis_type == 'summarize-commit' && 'Task: Provide a clear, concise summary of what changed in the latest commit. Include the commit message, files changed, and the purpose of the changes.' || '' }}