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

* 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>

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

@@ -1,38 +0,0 @@
-name: Auto review PRs
-
-on:
-  pull_request:
-    types: [opened, synchronize]
-
-jobs:
-  auto-review:
-    permissions:
-      contents: read
-      id-token: write
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 1
-
-      - name: Auto review PR
-        uses: ./
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          prompt: |
-            Please review this PR and provide comprehensive feedback.
-            
-            Focus on:
-            - Code quality and best practices
-            - Potential bugs or issues
-            - Suggestions for improvements
-            - Overall architecture and design decisions
-            - Documentation consistency
-            
-            Use the GitHub MCP tools to create a proper PR review with comments.
-            You can use mcp__github__create_pending_pull_request_review to start a review
-            and mcp__github__submit_pull_request_review to submit it as a COMMENT (not APPROVE).
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          claude_args: "--allowedTools mcp__github__create_pending_pull_request_review,mcp__github__submit_pull_request_review,Read,Grep,Glob"

.github/workflows/claude-review.yml

@@ -0,0 +1,33 @@
+name: Auto review PRs
+
+on:
+  pull_request:
+    types: [opened]
+
+jobs:
+  auto-review:
+    permissions:
+      contents: read
+      id-token: write
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Auto review PR
+        uses: anthropics/claude-code-action@main
+        with:
+          direct_prompt: |
+            Please review this PR. Look at the changes and provide thoughtful feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Suggestions for improvements
+            - Overall architecture and design decisions
+            - Documentation consistency: Verify that README.md and other documentation files are updated to reflect any code changes (especially new inputs, features, or configuration options)
+
+            Be constructive and specific in your feedback. Give inline comments where applicable.
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          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"

.github/workflows/issue-triage.yml

@@ -102,5 +102,6 @@ jobs:
           prompt_file: /tmp/claude-prompts/triage-prompt.txt
           allowed_tools: "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"
           mcp_config: /tmp/mcp-config/mcp-servers.json
-          timeout_minutes: "5"
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-base-action.yml

@@ -25,7 +25,6 @@ jobs:
           prompt: ${{ github.event.inputs.test_prompt || 'List the files in the current directory starting with "package"' }}
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           allowed_tools: "LS,Read"
-          timeout_minutes: "3"
 
       - name: Verify inline prompt output
         run: |
@@ -83,7 +82,6 @@ jobs:
           prompt_file: "test-prompt.txt"
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           allowed_tools: "LS,Read"
-          timeout_minutes: "3"
 
       - name: Verify prompt file output
         run: |

.github/workflows/test-custom-executables.yml

@@ -0,0 +1,89 @@
+name: Test Custom Executables
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  test-custom-executables:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+
+      - name: Install Bun manually
+        run: |
+          echo "Installing Bun..."
+          curl -fsSL https://bun.sh/install | bash
+          echo "Bun installed at: $HOME/.bun/bin/bun"
+
+          # Verify Bun installation
+          if [ -f "$HOME/.bun/bin/bun" ]; then
+            echo "✅ Bun executable found"
+            $HOME/.bun/bin/bun --version
+          else
+            echo "❌ Bun executable not found"
+            exit 1
+          fi
+
+      - name: Install Claude Code manually
+        run: |
+          echo "Installing Claude Code..."
+          curl -fsSL https://claude.ai/install.sh | bash -s latest
+          echo "Claude Code installed at: $HOME/.local/bin/claude"
+
+          # Verify Claude installation
+          if [ -f "$HOME/.local/bin/claude" ]; then
+            echo "✅ Claude executable found"
+            ls -la "$HOME/.local/bin/claude"
+          else
+            echo "❌ Claude executable not found"
+            exit 1
+          fi
+
+      - name: Test with both custom executables
+        id: custom-test
+        uses: ./base-action
+        with:
+          prompt: |
+            List the files in the current directory starting with "package"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          path_to_claude_code_executable: /home/runner/.local/bin/claude
+          path_to_bun_executable: /home/runner/.bun/bin/bun
+          allowed_tools: "LS,Read"
+
+      - name: Verify custom executables worked
+        run: |
+          OUTPUT_FILE="${{ steps.custom-test.outputs.execution_file }}"
+          CONCLUSION="${{ steps.custom-test.outputs.conclusion }}"
+
+          echo "Conclusion: $CONCLUSION"
+          echo "Output file: $OUTPUT_FILE"
+
+          if [ "$CONCLUSION" = "success" ]; then
+            echo "✅ Action completed successfully with both custom executables"
+          else
+            echo "❌ Action failed with custom executables"
+            exit 1
+          fi
+
+          if [ -f "$OUTPUT_FILE" ] && [ -s "$OUTPUT_FILE" ]; then
+            echo "✅ Execution log file created successfully"
+            if jq . "$OUTPUT_FILE" > /dev/null 2>&1; then
+              echo "✅ Output is valid JSON"
+              # Verify the task was completed
+              if grep -q "package" "$OUTPUT_FILE"; then
+                echo "✅ Claude successfully listed package files"
+              else
+                echo "⚠️ Could not verify if package files were listed"
+              fi
+            else
+              echo "❌ Output is not valid JSON"
+              exit 1
+            fi
+          else
+            echo "❌ Execution log file not found or empty"
+            exit 1
+          fi

.github/workflows/test-settings.yml

@@ -26,7 +26,6 @@ jobs:
                 "allow": ["Bash(echo:*)"]
               }
             }
-          timeout_minutes: "2"
 
       - name: Verify echo worked
         run: |
@@ -76,7 +75,6 @@ jobs:
                 "deny": ["Bash(echo:*)"]
               }
             }
-          timeout_minutes: "2"
 
       - name: Verify echo was denied
         run: |
@@ -114,7 +112,6 @@ jobs:
             Use Bash to echo "Hello from settings file test"
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           settings: "test-settings.json"
-          timeout_minutes: "2"
 
       - name: Verify echo worked
         run: |
@@ -169,7 +166,6 @@ jobs:
             Use Bash to echo "This should not work from file"
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           settings: "test-settings.json"
-          timeout_minutes: "2"
 
       - name: Verify echo was denied
         run: |

README.md

@@ -1,11 +1,12 @@
 ![Claude Code Action responding to a comment](https://github.com/user-attachments/assets/1d60c2e9-82ed-4ee5-b749-f9e021c85f4d)
 
-# Claude Code Action - No Approval Test
+# Claude Code Action
 
-A general-purpose [Claude Code](https://claude.ai/code) action for GitHub PRs and issues that can answer questions and implement code changes. This action listens for a trigger phrase in comments and activates Claude act on the request. It supports multiple authentication methods including Anthropic direct API, Amazon Bedrock, and Google Vertex AI.
+A general-purpose [Claude Code](https://claude.ai/code) action for GitHub PRs and issues that can answer questions and implement code changes. This action intelligently detects when to activate based on your workflow context—whether responding to @claude mentions, issue assignments, or executing automation tasks with explicit prompts. It supports multiple authentication methods including Anthropic direct API, Amazon Bedrock, and Google Vertex AI.
 
 ## Features
 
+- 🎯 **Intelligent Mode Detection**: Automatically selects the appropriate execution mode based on your workflow context—no configuration needed
 - 🤖 **Interactive Code Assistant**: Claude can answer questions about code, architecture, and programming
 - 🔍 **Code Review**: Analyzes PR changes and suggests improvements
 - ✨ **Code Implementation**: Can implement simple fixes, refactoring, and even new features
@@ -13,19 +14,11 @@ A general-purpose [Claude Code](https://claude.ai/code) action for GitHub PRs an
 - 🛠️ **Flexible Tool Access**: Access to GitHub APIs and file operations (additional tools can be enabled via configuration)
 - 📋 **Progress Tracking**: Visual progress indicators with checkboxes that dynamically update as Claude completes tasks
 - 🏃 **Runs on Your Infrastructure**: The action executes entirely on your own GitHub runner (Anthropic API calls go to your chosen provider)
+- ⚙️ **Simplified Configuration**: Unified `prompt` and `claude_args` inputs provide clean, powerful configuration aligned with Claude Code SDK
 
-## ⚠️ **BREAKING CHANGES COMING IN v1.0** ⚠️
+## 📦 Upgrading from v0.x?
 
-**We're planning a major update that will significantly change how this action works.** The new version will:
+**See our [Migration Guide](./docs/migration-guide.md)** for step-by-step instructions on updating your workflows to v1.0. The new version simplifies configuration while maintaining compatibility with most existing setups.
-
-- ✨ Automatically select the appropriate mode (no more `mode` input)
-- 🔧 Simplify configuration with unified `prompt` and `claude_args`
-- 🚀 Align more closely with the Claude Code SDK capabilities
-- 💥 Remove multiple inputs like `direct_prompt`, `custom_instructions`, and others
-
-**[→ Read the full v1.0 roadmap and provide feedback](https://github.com/anthropics/claude-code-action/discussions/428)**
-
----
 
 ## Quickstart
 
@@ -40,6 +33,7 @@ This command will guide you through setting up the GitHub app and required secre
 
 ## Documentation
 
+- **[Migration Guide](./docs/migration-guide.md)** - **⭐ Upgrading from v0.x to v1.0**
 - [Setup Guide](./docs/setup.md) - Manual setup, custom GitHub apps, and security best practices
 - [Usage Guide](./docs/usage.md) - Basic usage, workflow configuration, and input parameters
 - [Custom Automations](./docs/custom-automations.md) - Examples of automated workflows and custom prompts
@@ -57,21 +51,3 @@ Having issues or questions? Check out our [Frequently Asked Questions](./docs/fa
 ## License
 
 This project is licensed under the MIT License—see the LICENSE file for details.
-
-
-## Testing token fix
-
-
-## Testing token fix v2
-
-
-## Testing token fix v3
-
-
-## Testing review tools
-
-
-## Testing MCP server fix
-
-
-## Testing gh comment command

action.yml

@@ -57,10 +57,6 @@ inputs:
     required: false
     default: "false"
 
-  timeout_minutes:
-    description: "Timeout in minutes for execution"
-    required: false
-    default: "30"
   claude_args:
     description: "Additional arguments to pass directly to Claude CLI"
     required: false
@@ -85,6 +81,14 @@ inputs:
     description: "Restrict network access to these domains only (newline-separated). If not set, no restrictions are applied. Provider domains are auto-detected."
     required: false
     default: ""
+  path_to_claude_code_executable:
+    description: "Optional path to a custom Claude Code executable. If provided, skips automatic installation and uses this executable instead. WARNING: Using an older version may cause problems if the action begins taking advantage of new Claude Code features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment."
+    required: false
+    default: ""
+  path_to_bun_executable:
+    description: "Optional path to a custom Bun executable. If provided, skips automatic Bun installation and uses this executable instead. WARNING: Using an incompatible version may cause problems if the action requires specific Bun features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment."
+    required: false
+    default: ""
 
 outputs:
   execution_file:
@@ -93,15 +97,28 @@ outputs:
   branch_name:
     description: "The branch created by Claude Code for this execution"
     value: ${{ steps.prepare.outputs.CLAUDE_BRANCH }}
+  github_token:
+    description: "The GitHub token used by the action (Claude App token if available)"
+    value: ${{ steps.prepare.outputs.github_token }}
 
 runs:
   using: "composite"
   steps:
     - name: Install Bun
+      if: inputs.path_to_bun_executable == ''
       uses: oven-sh/setup-bun@735343b667d3e6f658f44d0eca948eb6282f2b76 # https://github.com/oven-sh/setup-bun/releases/tag/v2.0.2
       with:
         bun-version: 1.2.11
 
+    - name: Setup Custom Bun Path
+      if: inputs.path_to_bun_executable != ''
+      shell: bash
+      run: |
+        echo "Using custom Bun executable: ${{ inputs.path_to_bun_executable }}"
+        # Add the directory containing the custom executable to PATH
+        BUN_DIR=$(dirname "${{ inputs.path_to_bun_executable }}")
+        echo "$BUN_DIR" >> "$GITHUB_PATH"
+
     - name: Install Dependencies
       shell: bash
       run: |
@@ -130,6 +147,7 @@ runs:
         ADDITIONAL_PERMISSIONS: ${{ inputs.additional_permissions }}
         CLAUDE_ARGS: ${{ inputs.claude_args }}
         MCP_CONFIG: ${{ inputs.mcp_config }}
+        ALL_INPUTS: ${{ toJson(inputs) }}
 
     - name: Install Base Action Dependencies
       if: steps.prepare.outputs.contains_trigger == 'true'
@@ -140,8 +158,18 @@ runs:
         bun install
         echo "Base-action dependencies installed"
         cd -
-        # Install Claude Code globally
+
-        bun install -g @anthropic-ai/claude-code@1.0.72
+        # Install Claude Code if no custom executable is provided
+        if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then
+          echo "Installing Claude Code..."
+          curl -fsSL https://claude.ai/install.sh | bash -s 1.0.90
+          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
+        else
+          echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}"
+          # Add the directory containing the custom executable to PATH
+          CLAUDE_DIR=$(dirname "${{ inputs.path_to_claude_code_executable }}")
+          echo "$CLAUDE_DIR" >> "$GITHUB_PATH"
+        fi
 
     - name: Setup Network Restrictions
       if: steps.prepare.outputs.contains_trigger == 'true' && inputs.experimental_allowed_domains != ''
@@ -165,9 +193,11 @@ runs:
         CLAUDE_CODE_ACTION: "1"
         INPUT_PROMPT_FILE: ${{ runner.temp }}/claude-prompts/claude-prompt.txt
         INPUT_SETTINGS: ${{ inputs.settings }}
-        INPUT_TIMEOUT_MINUTES: ${{ inputs.timeout_minutes }}
         INPUT_CLAUDE_ARGS: ${{ steps.prepare.outputs.claude_args }}
         INPUT_EXPERIMENTAL_SLASH_COMMANDS_DIR: ${{ github.action_path }}/slash-commands
+        INPUT_ACTION_INPUTS_PRESENT: ${{ steps.prepare.outputs.action_inputs_present }}
+        INPUT_PATH_TO_CLAUDE_CODE_EXECUTABLE: ${{ inputs.path_to_claude_code_executable }}
+        INPUT_PATH_TO_BUN_EXECUTABLE: ${{ inputs.path_to_bun_executable }}
 
         # Model configuration
         GITHUB_TOKEN: ${{ steps.prepare.outputs.GITHUB_TOKEN }}
@@ -241,7 +271,7 @@ runs:
         fi
 
     - name: Revoke app token
-      if: always() && inputs.github_token == ''
+      if: always() && inputs.github_token == '' && steps.prepare.outputs.skipped_due_to_workflow_validation_mismatch != 'true'
       shell: bash
       run: |
         curl -L \

base-action/README.md

@@ -100,7 +100,6 @@ Add the following to your workflow file:
 | `model`                   | Model to use (provider-specific format required for Bedrock/Vertex)                               | No       | 'claude-4-0-sonnet-20250219' |
 | `anthropic_model`         | DEPRECATED: Use 'model' instead                                                                   | No       | 'claude-4-0-sonnet-20250219' |
 | `fallback_model`          | Enable automatic fallback to specified model when default model is overloaded                     | No       | ''                           |
-| `timeout_minutes`         | Timeout in minutes for Claude Code execution                                                      | No       | '10'                         |
 | `anthropic_api_key`       | Anthropic API key (required for direct Anthropic API)                                             | No       | ''                           |
 | `claude_code_oauth_token` | Claude Code OAuth token (alternative to anthropic_api_key)                                        | No       | ''                           |
 | `use_bedrock`             | Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API                       | No       | 'false'                      |
@@ -320,7 +319,6 @@ You can combine MCP config with other inputs like allowed tools:
     prompt: "Access the custom MCP server and use its tools"
     mcp_config: "mcp-config.json"
     allowed_tools: "Bash(git:*),View,mcp__server-name__custom_tool"
-    timeout_minutes: "15"
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 

base-action/action.yml

@@ -20,17 +20,10 @@ inputs:
     default: ""
 
   # Action settings
-  timeout_minutes:
-    description: "Timeout in minutes for Claude Code execution"
-    required: false
-    default: "10"
   claude_args:
     description: "Additional arguments to pass directly to Claude CLI (e.g., '--max-turns 3 --mcp-config /path/to/config.json')"
     required: false
     default: ""
-  experimental_slash_commands_dir:
-    description: "Experimental: Directory containing slash command files to install"
-    required: false
 
   # Authentication settings
   anthropic_api_key:
@@ -54,6 +47,14 @@ inputs:
     description: "Whether to use Node.js dependency caching (set to true only for Node.js projects with lock files)"
     required: false
     default: "false"
+  path_to_claude_code_executable:
+    description: "Optional path to a custom Claude Code executable. If provided, skips automatic installation and uses this executable instead. WARNING: Using an older version may cause problems if the action begins taking advantage of new Claude Code features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment."
+    required: false
+    default: ""
+  path_to_bun_executable:
+    description: "Optional path to a custom Bun executable. If provided, skips automatic Bun installation and uses this executable instead. WARNING: Using an incompatible version may cause problems if the action requires specific Bun features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment."
+    required: false
+    default: ""
 
 outputs:
   conclusion:
@@ -73,10 +74,20 @@ runs:
         cache: ${{ inputs.use_node_cache == 'true' && 'npm' || '' }}
 
     - name: Install Bun
+      if: inputs.path_to_bun_executable == ''
       uses: oven-sh/setup-bun@735343b667d3e6f658f44d0eca948eb6282f2b76 # https://github.com/oven-sh/setup-bun/releases/tag/v2.0.2
       with:
         bun-version: 1.2.11
 
+    - name: Setup Custom Bun Path
+      if: inputs.path_to_bun_executable != ''
+      shell: bash
+      run: |
+        echo "Using custom Bun executable: ${{ inputs.path_to_bun_executable }}"
+        # Add the directory containing the custom executable to PATH
+        BUN_DIR=$(dirname "${{ inputs.path_to_bun_executable }}")
+        echo "$BUN_DIR" >> "$GITHUB_PATH"
+
     - name: Install Dependencies
       shell: bash
       run: |
@@ -85,7 +96,16 @@ runs:
 
     - name: Install Claude Code
       shell: bash
-      run: bun install -g @anthropic-ai/claude-code@1.0.72
+      run: |
+        if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then
+          echo "Installing Claude Code..."
+          curl -fsSL https://claude.ai/install.sh | bash -s 1.0.90
+        else
+          echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}"
+          # Add the directory containing the custom executable to PATH
+          CLAUDE_DIR=$(dirname "${{ inputs.path_to_claude_code_executable }}")
+          echo "$CLAUDE_DIR" >> "$GITHUB_PATH"
+        fi
 
     - name: Run Claude Code Action
       shell: bash
@@ -103,9 +123,9 @@ runs:
         INPUT_PROMPT: ${{ inputs.prompt }}
         INPUT_PROMPT_FILE: ${{ inputs.prompt_file }}
         INPUT_SETTINGS: ${{ inputs.settings }}
-        INPUT_TIMEOUT_MINUTES: ${{ inputs.timeout_minutes }}
         INPUT_CLAUDE_ARGS: ${{ inputs.claude_args }}
-        INPUT_EXPERIMENTAL_SLASH_COMMANDS_DIR: ${{ inputs.experimental_slash_commands_dir }}
+        INPUT_PATH_TO_CLAUDE_CODE_EXECUTABLE: ${{ inputs.path_to_claude_code_executable }}
+        INPUT_PATH_TO_BUN_EXECUTABLE: ${{ inputs.path_to_bun_executable }}
 
         # Provider configuration
         ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}

base-action/examples/issue-triage.yml

@@ -104,5 +104,4 @@ jobs:
           prompt_file: /tmp/claude-prompts/triage-prompt.txt
           allowed_tools: "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"
           mcp_config: /tmp/mcp-config/mcp-servers.json
-          timeout_minutes: "5"
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

base-action/src/index.ts

@@ -13,7 +13,6 @@ async function run() {
     await setupClaudeCodeSettings(
       process.env.INPUT_SETTINGS,
       undefined, // homeDir
-      process.env.INPUT_EXPERIMENTAL_SLASH_COMMANDS_DIR,
     );
 
     const promptConfig = await preparePrompt({
@@ -22,8 +21,18 @@ async function run() {
     });
 
     await runClaude(promptConfig.path, {
-      timeoutMinutes: process.env.INPUT_TIMEOUT_MINUTES,
       claudeArgs: process.env.INPUT_CLAUDE_ARGS,
+      allowedTools: process.env.INPUT_ALLOWED_TOOLS,
+      disallowedTools: process.env.INPUT_DISALLOWED_TOOLS,
+      maxTurns: process.env.INPUT_MAX_TURNS,
+      mcpConfig: process.env.INPUT_MCP_CONFIG,
+      systemPrompt: process.env.INPUT_SYSTEM_PROMPT,
+      appendSystemPrompt: process.env.INPUT_APPEND_SYSTEM_PROMPT,
+      claudeEnv: process.env.INPUT_CLAUDE_ENV,
+      fallbackModel: process.env.INPUT_FALLBACK_MODEL,
+      model: process.env.ANTHROPIC_MODEL,
+      pathToClaudeCodeExecutable:
+        process.env.INPUT_PATH_TO_CLAUDE_CODE_EXECUTABLE,
     });
   } catch (error) {
     core.setFailed(`Action failed with error: ${error}`);

base-action/src/run-claude.ts

@@ -13,8 +13,17 @@ const EXECUTION_FILE = `${process.env.RUNNER_TEMP}/claude-execution-output.json`
 const BASE_ARGS = ["--verbose", "--output-format", "stream-json"];
 
 export type ClaudeOptions = {
-  timeoutMinutes?: string;
   claudeArgs?: string;
+  model?: string;
+  pathToClaudeCodeExecutable?: string;
+  allowedTools?: string;
+  disallowedTools?: string;
+  maxTurns?: string;
+  mcpConfig?: string;
+  systemPrompt?: string;
+  appendSystemPrompt?: string;
+  claudeEnv?: string;
+  fallbackModel?: string;
 };
 
 type PreparedConfig = {
@@ -46,20 +55,16 @@ export function prepareRunConfig(
   // BASE_ARGS are always appended last (cannot be overridden)
   claudeArgs.push(...BASE_ARGS);
 
-  // Validate timeout if provided (affects process wrapper, not Claude)
+  const customEnv: Record<string, string> = {};
-  if (options.timeoutMinutes) {
+
-    const timeoutMinutesNum = parseInt(options.timeoutMinutes, 10);
+  if (process.env.INPUT_ACTION_INPUTS_PRESENT) {
-    if (isNaN(timeoutMinutesNum) || timeoutMinutesNum <= 0) {
+    customEnv.GITHUB_ACTION_INPUTS = process.env.INPUT_ACTION_INPUTS_PRESENT;
-      throw new Error(
-        `timeoutMinutes must be a positive number, got: ${options.timeoutMinutes}`,
-      );
-    }
   }
 
   return {
     claudeArgs,
     promptPath,
-    env: {},
+    env: customEnv,
   };
 }
 
@@ -88,9 +93,11 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
   console.log(`Prompt file size: ${promptSize} bytes`);
 
   // Log custom environment variables if any
-  if (Object.keys(config.env).length > 0) {
+  const customEnvKeys = Object.keys(config.env).filter(
-    const envKeys = Object.keys(config.env).join(", ");
+    (key) => key !== "CLAUDE_ACTION_INPUTS_PRESENT",
-    console.log(`Custom environment variables: ${envKeys}`);
+  );
+  if (customEnvKeys.length > 0) {
+    console.log(`Custom environment variables: ${customEnvKeys.join(", ")}`);
   }
 
   // Log custom arguments if any
@@ -114,7 +121,10 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
     pipeStream.destroy();
   });
 
-  const claudeProcess = spawn("claude", config.claudeArgs, {
+  // Use custom executable path if provided, otherwise default to "claude"
+  const claudeExecutable = options.pathToClaudeCodeExecutable || "claude";
+
+  const claudeProcess = spawn(claudeExecutable, config.claudeArgs, {
     stdio: ["pipe", "pipe", "inherit"],
     env: {
       ...process.env,
@@ -173,57 +183,15 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
     claudeProcess.kill("SIGTERM");
   });
 
-  // Wait for Claude to finish with timeout
+  // Wait for Claude to finish
-  let timeoutMs = 10 * 60 * 1000; // Default 10 minutes
-  if (options.timeoutMinutes) {
-    timeoutMs = parseInt(options.timeoutMinutes, 10) * 60 * 1000;
-  } else if (process.env.INPUT_TIMEOUT_MINUTES) {
-    const envTimeout = parseInt(process.env.INPUT_TIMEOUT_MINUTES, 10);
-    if (isNaN(envTimeout) || envTimeout <= 0) {
-      throw new Error(
-        `INPUT_TIMEOUT_MINUTES must be a positive number, got: ${process.env.INPUT_TIMEOUT_MINUTES}`,
-      );
-    }
-    timeoutMs = envTimeout * 60 * 1000;
-  }
   const exitCode = await new Promise<number>((resolve) => {
-    let resolved = false;
-
-    // Set a timeout for the process
-    const timeoutId = setTimeout(() => {
-      if (!resolved) {
-        console.error(
-          `Claude process timed out after ${timeoutMs / 1000} seconds`,
-        );
-        claudeProcess.kill("SIGTERM");
-        // Give it 5 seconds to terminate gracefully, then force kill
-        setTimeout(() => {
-          try {
-            claudeProcess.kill("SIGKILL");
-          } catch (e) {
-            // Process may already be dead
-          }
-        }, 5000);
-        resolved = true;
-        resolve(124); // Standard timeout exit code
-      }
-    }, timeoutMs);
-
     claudeProcess.on("close", (code) => {
-      if (!resolved) {
-        clearTimeout(timeoutId);
-        resolved = true;
       resolve(code || 0);
-      }
     });
 
     claudeProcess.on("error", (error) => {
-      if (!resolved) {
       console.error("Claude process error:", error);
-        clearTimeout(timeoutId);
-        resolved = true;
       resolve(1);
-      }
     });
   });
 
@@ -253,7 +221,10 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
       await writeFile("output.txt", output);
 
       // Process output.txt into JSON and save to execution file
-      const { stdout: jsonOutput } = await execAsync("jq -s '.' output.txt");
+      // Increase maxBuffer from Node.js default of 1MB to 10MB to handle large Claude outputs
+      const { stdout: jsonOutput } = await execAsync("jq -s '.' output.txt", {
+        maxBuffer: 10 * 1024 * 1024,
+      });
       await writeFile(EXECUTION_FILE, jsonOutput);
 
       console.log(`Log saved to ${EXECUTION_FILE}`);
@@ -270,7 +241,10 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
     if (output) {
       try {
         await writeFile("output.txt", output);
-        const { stdout: jsonOutput } = await execAsync("jq -s '.' output.txt");
+        // Increase maxBuffer from Node.js default of 1MB to 10MB to handle large Claude outputs
+        const { stdout: jsonOutput } = await execAsync("jq -s '.' output.txt", {
+          maxBuffer: 10 * 1024 * 1024,
+        });
         await writeFile(EXECUTION_FILE, jsonOutput);
         core.setOutput("execution_file", EXECUTION_FILE);
       } catch (e) {

base-action/src/setup-claude-code-settings.ts

@@ -5,7 +5,6 @@ import { readFile } from "fs/promises";
 export async function setupClaudeCodeSettings(
   settingsInput?: string,
   homeDir?: string,
-  slashCommandsDir?: string,
 ) {
   const home = homeDir ?? homedir();
   const settingsPath = `${home}/.claude/settings.json`;
@@ -66,17 +65,4 @@ export async function setupClaudeCodeSettings(
 
   await $`echo ${JSON.stringify(settings, null, 2)} > ${settingsPath}`.quiet();
   console.log(`Settings saved successfully`);
-
-  if (slashCommandsDir) {
-    console.log(
-      `Copying slash commands from ${slashCommandsDir} to ${home}/.claude/`,
-    );
-    try {
-      await $`test -d ${slashCommandsDir}`.quiet();
-      await $`cp ${slashCommandsDir}/*.md ${home}/.claude/ 2>/dev/null || true`.quiet();
-      console.log(`Slash commands copied successfully`);
-    } catch (e) {
-      console.log(`Slash commands directory not found or error copying: ${e}`);
-    }
-  }
 }

base-action/test/run-claude.test.ts

@@ -30,36 +30,6 @@ describe("prepareRunConfig", () => {
     expect(prepared.promptPath).toBe("/custom/prompt/path.txt");
   });
 
-  describe("timeoutMinutes validation", () => {
-    test("should accept valid timeoutMinutes value", () => {
-      const options: ClaudeOptions = { timeoutMinutes: "15" };
-      expect(() =>
-        prepareRunConfig("/tmp/test-prompt.txt", options),
-      ).not.toThrow();
-    });
-
-    test("should throw error for non-numeric timeoutMinutes", () => {
-      const options: ClaudeOptions = { timeoutMinutes: "abc" };
-      expect(() => prepareRunConfig("/tmp/test-prompt.txt", options)).toThrow(
-        "timeoutMinutes must be a positive number, got: abc",
-      );
-    });
-
-    test("should throw error for negative timeoutMinutes", () => {
-      const options: ClaudeOptions = { timeoutMinutes: "-5" };
-      expect(() => prepareRunConfig("/tmp/test-prompt.txt", options)).toThrow(
-        "timeoutMinutes must be a positive number, got: -5",
-      );
-    });
-
-    test("should throw error for zero timeoutMinutes", () => {
-      const options: ClaudeOptions = { timeoutMinutes: "0" };
-      expect(() => prepareRunConfig("/tmp/test-prompt.txt", options)).toThrow(
-        "timeoutMinutes must be a positive number, got: 0",
-      );
-    });
-  });
-
   describe("claudeArgs handling", () => {
     test("should parse and include custom claude arguments", () => {
       const options: ClaudeOptions = {

base-action/test/setup-claude-code-settings.test.ts

@@ -3,7 +3,7 @@
 import { describe, test, expect, beforeEach, afterEach } from "bun:test";
 import { setupClaudeCodeSettings } from "../src/setup-claude-code-settings";
 import { tmpdir } from "os";
-import { mkdir, writeFile, readFile, rm, readdir } from "fs/promises";
+import { mkdir, writeFile, readFile, rm } from "fs/promises";
 import { join } from "path";
 
 const testHomeDir = join(
@@ -147,72 +147,4 @@ describe("setupClaudeCodeSettings", () => {
     expect(settings.newKey).toBe("newValue");
     expect(settings.model).toBe("claude-opus-4-1-20250805");
   });
-
-  test("should copy slash commands to .claude directory when path provided", async () => {
-    const testSlashCommandsDir = join(testHomeDir, "test-slash-commands");
-    await mkdir(testSlashCommandsDir, { recursive: true });
-    await writeFile(
-      join(testSlashCommandsDir, "test-command.md"),
-      "---\ndescription: Test command\n---\nTest content",
-    );
-
-    await setupClaudeCodeSettings(undefined, testHomeDir, testSlashCommandsDir);
-
-    const testCommandPath = join(testHomeDir, ".claude", "test-command.md");
-    const content = await readFile(testCommandPath, "utf-8");
-    expect(content).toContain("Test content");
-  });
-
-  test("should skip slash commands when no directory provided", async () => {
-    await setupClaudeCodeSettings(undefined, testHomeDir);
-
-    const settingsContent = await readFile(settingsPath, "utf-8");
-    const settings = JSON.parse(settingsContent);
-    expect(settings.enableAllProjectMcpServers).toBe(true);
-  });
-
-  test("should handle missing slash commands directory gracefully", async () => {
-    const nonExistentDir = join(testHomeDir, "non-existent");
-
-    await setupClaudeCodeSettings(undefined, testHomeDir, nonExistentDir);
-
-    const settingsContent = await readFile(settingsPath, "utf-8");
-    expect(JSON.parse(settingsContent).enableAllProjectMcpServers).toBe(true);
-  });
-
-  test("should skip non-.md files in slash commands directory", async () => {
-    const testSlashCommandsDir = join(testHomeDir, "test-slash-commands");
-    await mkdir(testSlashCommandsDir, { recursive: true });
-    await writeFile(join(testSlashCommandsDir, "not-markdown.txt"), "ignored");
-    await writeFile(join(testSlashCommandsDir, "valid.md"), "copied");
-    await writeFile(join(testSlashCommandsDir, "another.md"), "also copied");
-
-    await setupClaudeCodeSettings(undefined, testHomeDir, testSlashCommandsDir);
-
-    const copiedFiles = await readdir(join(testHomeDir, ".claude"));
-    expect(copiedFiles).toContain("valid.md");
-    expect(copiedFiles).toContain("another.md");
-    expect(copiedFiles).not.toContain("not-markdown.txt");
-    expect(copiedFiles).toContain("settings.json"); // Settings should also exist
-  });
-
-  test("should handle slash commands path that is a file not directory", async () => {
-    const testFile = join(testHomeDir, "not-a-directory.txt");
-    await writeFile(testFile, "This is a file, not a directory");
-
-    await setupClaudeCodeSettings(undefined, testHomeDir, testFile);
-
-    const settingsContent = await readFile(settingsPath, "utf-8");
-    expect(JSON.parse(settingsContent).enableAllProjectMcpServers).toBe(true);
-  });
-
-  test("should handle empty slash commands directory", async () => {
-    const emptyDir = join(testHomeDir, "empty-slash-commands");
-    await mkdir(emptyDir, { recursive: true });
-
-    await setupClaudeCodeSettings(undefined, testHomeDir, emptyDir);
-
-    const settingsContent = await readFile(settingsPath, "utf-8");
-    expect(JSON.parse(settingsContent).enableAllProjectMcpServers).toBe(true);
-  });
 });

docs/cloud-providers.md

@@ -20,23 +20,25 @@ Use provider-specific model names based on your chosen provider:
 
 ```yaml
 # For direct Anthropic API (default)
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
     # ... other inputs
 
 # For Amazon Bedrock with OIDC
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    model: "anthropic.claude-3-7-sonnet-20250219-beta:0" # Cross-region inference
     use_bedrock: "true"
+    claude_args: |
+      --model anthropic.claude-4-0-sonnet-20250805-v1:0
     # ... other inputs
 
 # For Google Vertex AI with OIDC
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    model: "claude-3-7-sonnet@20250219"
     use_vertex: "true"
+    claude_args: |
+      --model claude-4-0-sonnet@20250805
     # ... other inputs
 ```
 
@@ -59,10 +61,11 @@ Both AWS Bedrock and GCP Vertex AI require OIDC authentication.
     app-id: ${{ secrets.APP_ID }}
     private-key: ${{ secrets.APP_PRIVATE_KEY }}
 
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    model: "anthropic.claude-3-7-sonnet-20250219-beta:0"
     use_bedrock: "true"
+    claude_args: |
+      --model anthropic.claude-4-0-sonnet-20250805-v1:0
     # ... other inputs
 
   permissions:
@@ -84,10 +87,11 @@ Both AWS Bedrock and GCP Vertex AI require OIDC authentication.
     app-id: ${{ secrets.APP_ID }}
     private-key: ${{ secrets.APP_PRIVATE_KEY }}
 
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    model: "claude-3-7-sonnet@20250219"
     use_vertex: "true"
+    claude_args: |
+      --model claude-4-0-sonnet@20250805
     # ... other inputs
 
   permissions:

docs/configuration.md

@@ -160,33 +160,38 @@ jobs:
 
 ## Custom Environment Variables
 
-You can pass custom environment variables to Claude Code execution using the `claude_env` input. This is useful for CI/test setups that require specific environment variables:
+You can pass custom environment variables to Claude Code execution using the `settings` input. This is useful for CI/test setups that require specific environment variables:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    claude_env: |
+    settings: |
-      NODE_ENV: test
+      {
-      CI: true
+        "env": {
-      DATABASE_URL: postgres://test:test@localhost:5432/test_db
+          "NODE_ENV": "test",
+          "CI": "true",
+          "DATABASE_URL": "postgres://test:test@localhost:5432/test_db"
+        }
+      }
     # ... other inputs
 ```
 
-The `claude_env` input accepts YAML format where each line defines a key-value pair. These environment variables will be available to Claude Code during execution, allowing it to run tests, build processes, or other commands that depend on specific environment configurations.
+These environment variables will be available to Claude Code during execution, allowing it to run tests, build processes, or other commands that depend on specific environment configurations.
 
 ## Limiting Conversation Turns
 
-You can use the `max_turns` parameter to limit the number of back-and-forth exchanges Claude can have during task execution. This is useful for:
+You can limit the number of back-and-forth exchanges Claude can have during task execution using the `claude_args` input. This is useful for:
 
 - Controlling costs by preventing runaway conversations
 - Setting time boundaries for automated workflows
 - Ensuring predictable behavior in CI/CD pipelines
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-    max_turns: "5" # Limit to 5 conversation turns
+    claude_args: |
+      --max-turns 5  # Limit to 5 conversation turns
     # ... other inputs
 ```
 
@@ -200,28 +205,50 @@ By default, Claude only has access to:
 - Comment management (creating/updating comments)
 - Basic GitHub operations
 
-Claude does **not** have access to execute arbitrary Bash commands by default. If you want Claude to run specific commands (e.g., npm install, npm test), you must explicitly allow them using the `allowed_tools` configuration:
+Claude does **not** have access to execute arbitrary Bash commands by default. If you want Claude to run specific commands (e.g., npm install, npm test), you must explicitly allow them using the `claude_args` configuration:
 
-**Note**: If your repository has a `.mcp.json` file in the root directory, Claude will automatically detect and use the MCP server tools defined there. However, these tools still need to be explicitly allowed via the `allowed_tools` configuration.
+**Note**: If your repository has a `.mcp.json` file in the root directory, Claude will automatically detect and use the MCP server tools defined there. However, these tools still need to be explicitly allowed.
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    allowed_tools: "Bash(npm install),Bash(npm run test),Edit,Replace,NotebookEditCell"
+    claude_args: |
-    disallowed_tools: "TaskOutput,KillTask"
+      --allowedTools "Bash(npm install),Bash(npm run test),Edit,Replace,NotebookEditCell"
+      --disallowedTools "TaskOutput,KillTask"
     # ... other inputs
 ```
 
-**Note**: The base GitHub tools are always included. Use `allowed_tools` to add additional tools (including specific Bash commands), and `disallowed_tools` to prevent specific tools from being used.
+**Note**: The base GitHub tools are always included. Use `--allowedTools` to add additional tools (including specific Bash commands), and `--disallowedTools` to prevent specific tools from being used.
 
 ## Custom Model
 
-Use a specific Claude model:
+Specify a Claude model using `claude_args`:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    # model: "claude-3-5-sonnet-20241022"  # Optional: specify a different model
+    claude_args: |
+      --model claude-4-0-sonnet-20250805
+    # ... other inputs
+```
+
+For provider-specific models:
+
+```yaml
+# AWS Bedrock
+- uses: anthropics/claude-code-action@v1
+  with:
+    use_bedrock: "true"
+    claude_args: |
+      --model anthropic.claude-4-0-sonnet-20250805-v1:0
+    # ... other inputs
+
+# Google Vertex AI
+- uses: anthropics/claude-code-action@v1
+  with:
+    use_vertex: "true"
+    claude_args: |
+      --model claude-4-0-sonnet@20250805
     # ... other inputs
 ```
 
@@ -232,7 +259,7 @@ You can provide Claude Code settings to customize behavior such as model selecti
 ### Option 1: Settings File
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     settings: "path/to/settings.json"
     # ... other inputs
@@ -241,7 +268,7 @@ You can provide Claude Code settings to customize behavior such as model selecti
 ### Option 2: Inline Settings
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     settings: |
       {
@@ -280,6 +307,20 @@ For a complete list of available settings and their descriptions, see the [Claud
 **Notes**:
 
 - The `enableAllProjectMcpServers` setting is always set to `true` by this action to ensure MCP servers work correctly.
-- If both the `model` input parameter and a `model` in settings are provided, the `model` input parameter takes precedence.
+- The `claude_args` input provides direct access to Claude Code CLI arguments and takes precedence over settings.
-- The `allowed_tools` and `disallowed_tools` input parameters take precedence over `permissions` in settings.
+- We recommend using `claude_args` for simple configurations and `settings` for complex configurations with hooks and environment variables.
-- In a future version, we may deprecate individual input parameters in favor of using the settings file for all configuration.
+
+## Migration from Deprecated Inputs
+
+Many individual input parameters have been consolidated into `claude_args` or `settings`. Here's how to migrate:
+
+| Old Input             | New Approach                                             |
+| --------------------- | -------------------------------------------------------- |
+| `allowed_tools`       | Use `claude_args: "--allowedTools Tool1,Tool2"`          |
+| `disallowed_tools`    | Use `claude_args: "--disallowedTools Tool1,Tool2"`       |
+| `max_turns`           | Use `claude_args: "--max-turns 10"`                      |
+| `model`               | Use `claude_args: "--model claude-4-0-sonnet-20250805"`  |
+| `claude_env`          | Use `settings` with `"env"` object                       |
+| `custom_instructions` | Use `claude_args: "--system-prompt 'Your instructions'"` |
+| `direct_prompt`       | Use `prompt` input instead                               |
+| `override_prompt`     | Use `prompt` with GitHub context variables               |

docs/custom-automations.md

@@ -1,6 +1,6 @@
 # Custom Automations
 
-These examples show how to configure Claude to act automatically based on GitHub events, without requiring manual @mentions.
+These examples show how to configure Claude to act automatically based on GitHub events. When you provide a `prompt` input, the action automatically runs in agent mode without requiring manual @mentions. Without a `prompt`, it runs in interactive mode, responding to @claude mentions.
 
 ## Supported GitHub Events
 
@@ -26,14 +26,15 @@ on:
       - "src/api/**/*.ts"
 
 steps:
-  - uses: anthropics/claude-code-action@beta
+  - uses: anthropics/claude-code-action@v1
     with:
-      direct_prompt: |
+      prompt: |
         Update the API documentation in README.md to reflect
         the changes made to the API endpoints in this PR.
+      anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
-When API files are modified, Claude automatically updates your README with the latest endpoint documentation and pushes the changes back to the PR, keeping your docs in sync with your code.
+When API files are modified, the action automatically detects that a `prompt` is provided and runs in agent mode. Claude updates your README with the latest endpoint documentation and pushes the changes back to the PR, keeping your docs in sync with your code.
 
 ## Author-Specific Code Reviews
 
@@ -50,28 +51,26 @@ jobs:
       github.event.pull_request.user.login == 'developer1' ||
       github.event.pull_request.user.login == 'external-contributor'
     steps:
-      - uses: anthropics/claude-code-action@beta
+      - uses: anthropics/claude-code-action@v1
         with:
-          direct_prompt: |
+          prompt: |
             Please provide a thorough review of this pull request.
             Pay extra attention to coding standards, security practices,
             and test coverage since this is from an external contributor.
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
-Perfect for automatically reviewing PRs from new team members, external contributors, or specific developers who need extra guidance.
+Perfect for automatically reviewing PRs from new team members, external contributors, or specific developers who need extra guidance. The action automatically runs in agent mode when a `prompt` is provided.
 
 ## Custom Prompt Templates
 
-Use `override_prompt` for complete control over Claude's behavior with variable substitution:
+Use the `prompt` input with GitHub context variables for dynamic automation:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    override_prompt: |
+    prompt: |
-      Analyze PR #$PR_NUMBER in $REPOSITORY for security vulnerabilities.
+      Analyze PR #${{ github.event.pull_request.number }} in ${{ github.repository }} for security vulnerabilities.
-
-      Changed files:
-      $CHANGED_FILES
 
       Focus on:
       - SQL injection risks
@@ -80,12 +79,35 @@ Use `override_prompt` for complete control over Claude's behavior with variable
       - Exposed secrets or credentials
 
       Provide severity ratings (Critical/High/Medium/Low) for any issues found.
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
-The `override_prompt` feature supports these variables:
+You can access any GitHub context variable using the standard GitHub Actions syntax:
 
-- `$REPOSITORY`, `$PR_NUMBER`, `$ISSUE_NUMBER`
+- `${{ github.repository }}` - The repository name
-- `$PR_TITLE`, `$ISSUE_TITLE`, `$PR_BODY`, `$ISSUE_BODY`
+- `${{ github.event.pull_request.number }}` - PR number
-- `$PR_COMMENTS`, `$ISSUE_COMMENTS`, `$REVIEW_COMMENTS`
+- `${{ github.event.issue.number }}` - Issue number
-- `$CHANGED_FILES`, `$TRIGGER_COMMENT`, `$TRIGGER_USERNAME`
+- `${{ github.event.pull_request.title }}` - PR title
-- `$BRANCH_NAME`, `$BASE_BRANCH`, `$EVENT_TYPE`, `$IS_PR`
+- `${{ github.event.pull_request.body }}` - PR description
+- `${{ github.event.comment.body }}` - Comment text
+- `${{ github.actor }}` - User who triggered the workflow
+- `${{ github.base_ref }}` - Base branch for PRs
+- `${{ github.head_ref }}` - Head branch for PRs
+
+## Advanced Configuration with claude_args
+
+For more control over Claude's behavior, use the `claude_args` input to pass CLI arguments directly:
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    prompt: "Review this PR for performance issues"
+    claude_args: |
+      --max-turns 15
+      --model claude-4-0-sonnet-20250805
+      --allowedTools Edit,Read,Write,Bash
+      --system-prompt "You are a performance optimization expert. Focus on identifying bottlenecks and suggesting improvements."
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+```
+
+This provides full access to Claude Code CLI capabilities while maintaining the simplified action interface.

docs/experimental.md

@@ -2,65 +2,66 @@
 
 **Note:** Experimental features are considered unstable and not supported for production use. They may change or be removed at any time.
 
-## Execution Modes
+## Automatic Mode Detection
 
-The action supports three execution modes, each optimized for different use cases:
+The action intelligently detects the appropriate execution mode based on your workflow context, eliminating the need for manual mode configuration.
 
-### Tag Mode (Default)
+### Interactive Mode (Tag Mode)
 
-The traditional implementation mode that responds to @claude mentions, issue assignments, or labels.
+Activated when Claude detects @mentions, issue assignments, or labels—without an explicit `prompt`.
 
-- **Triggers**: `@claude` mentions, issue assignment, label application
+- **Triggers**: `@claude` mentions in comments, issue assignment to claude user, label application
 - **Features**: Creates tracking comments with progress checkboxes, full implementation capabilities
-- **Use case**: General-purpose code implementation and Q&A
+- **Use case**: Interactive code assistance, Q&A, and implementation requests
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-    # mode: tag is the default
+    # No prompt needed - responds to @claude mentions
 ```
 
-### Agent Mode
+### Automation Mode (Agent Mode)
 
-**Note: Agent mode is currently in active development and may undergo breaking changes.**
+Automatically activated when you provide a `prompt` input.
 
-For direct automation when an explicit prompt is provided.
+- **Triggers**: Any GitHub event when `prompt` input is provided
-
+- **Features**: Direct execution without requiring @claude mentions, streamlined for automation
-- **Triggers**: Works with any event when `prompt` input is provided
-- **Features**: Direct execution without @claude mentions, no tracking comments
 - **Use case**: Automated PR reviews, scheduled tasks, workflow automation
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
     prompt: |
       Check for outdated dependencies and create an issue if any are found.
-    # Mode is auto-detected when prompt is provided
+    # Automatically runs in agent mode when prompt is provided
 ```
 
-### Experimental Review Mode
+### How It Works
 
-**Warning: This is an experimental feature that may change or be removed at any time.**
+The action uses this logic to determine the mode:
 
-For automated code reviews on pull requests.
+1. **If `prompt` is provided** → Runs in **agent mode** for automation
+2. **If no `prompt` but @claude is mentioned** → Runs in **tag mode** for interaction
+3. **If neither** → No action is taken
 
-- **Triggers**: Pull request events (`opened`, `synchronize`) or `@claude review` comments
+This automatic detection ensures your workflows are simpler and more intuitive, without needing to understand or configure different modes.
-- **Features**: Provides detailed code reviews with inline comments and suggestions
+
-- **Use case**: Automated PR reviews, code quality checks
+### Advanced Mode Control
+
+For specialized use cases, you can fine-tune behavior using `claude_args`:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
-    mode: experimental-review
+    prompt: "Review this PR"
+    claude_args: |
+      --max-turns 20
+      --system-prompt "You are a code review specialist"
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-    custom_instructions: |
-      Focus on code quality, security, and best practices.
 ```
 
-See [`examples/claude-modes.yml`](../examples/claude-modes.yml) and [`examples/claude-experimental-review-mode.yml`](../examples/claude-experimental-review-mode.yml) for complete examples of each mode.
-
 ## Network Restrictions
 
 For enhanced security, you can restrict Claude's network access to specific domains only. This feature is particularly useful for:
@@ -76,7 +77,7 @@ When `experimental_allowed_domains` is set, Claude can only access the domains y
 #### If using Anthropic API or subscription
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
     # Or: claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
@@ -87,7 +88,7 @@ When `experimental_allowed_domains` is set, Claude can only access the domains y
 #### If using AWS Bedrock
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     use_bedrock: "true"
     experimental_allowed_domains: |
@@ -98,7 +99,7 @@ When `experimental_allowed_domains` is set, Claude can only access the domains y
 #### If using Google Vertex AI
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     use_vertex: "true"
     experimental_allowed_domains: |
@@ -111,7 +112,7 @@ When `experimental_allowed_domains` is set, Claude can only access the domains y
 In addition to your provider domains, you may need to include GitHub-related domains. For GitHub.com users, common domains include:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
     experimental_allowed_domains: |

docs/faq.md

@@ -41,10 +41,11 @@ By default, Claude only uses commit tools for non-destructive changes to the bra
 - Never push to branches other than where it was invoked (either its own branch or the PR branch)
 - Never force push or perform destructive operations
 
-You can grant additional tools via the `allowed_tools` input if needed:
+You can grant additional tools via the `claude_args` input if needed:
 
 ```yaml
-allowed_tools: "Bash(git rebase:*)" # Use with caution
+claude_args: |
+  --allowedTools "Bash(git rebase:*)"  # Use with caution
 ```
 
 ### Why won't Claude create a pull request?
@@ -67,7 +68,7 @@ Yes! Claude can access GitHub Actions workflow runs, job logs, and test results
 
 2. Configure the action with additional permissions:
    ```yaml
-   - uses: anthropics/claude-code-action@beta
+   - uses: anthropics/claude-code-action@v1
      with:
        additional_permissions: |
          actions: read
@@ -105,30 +106,51 @@ If you need full history, you can configure this in your workflow before calling
 
 ## Configuration and Tools
 
-### What's the difference between `direct_prompt` and `custom_instructions`?
+### How does automatic mode detection work?
 
-These inputs serve different purposes in how Claude responds:
+The action intelligently detects whether to run in interactive mode or automation mode:
 
-- **`direct_prompt`**: Bypasses trigger detection entirely. When provided, Claude executes this exact instruction regardless of comments or mentions. Perfect for automated workflows where you want Claude to perform a specific task on every run (e.g., "Update the API documentation based on changes in this PR").
+- **With `prompt` input**: Runs in automation mode - executes immediately without waiting for @claude mentions
+- **Without `prompt` input**: Runs in interactive mode - waits for @claude mentions in comments
 
-- **`custom_instructions`**: Additional context added to Claude's system prompt while still respecting normal triggers. These instructions modify Claude's behavior but don't replace the triggering comment. Use this to give Claude standing instructions like "You have been granted additional tools for ...".
+This automatic detection eliminates the need to manually configure modes.
 
 Example:
 
 ```yaml
-# Using direct_prompt - runs automatically without @claude mention
+# Automation mode - runs automatically
-direct_prompt: "Review this PR for security vulnerabilities"
+prompt: "Review this PR for security vulnerabilities"
+# Interactive mode - waits for @claude mention
+# (no prompt provided)
+```
 
-# Using custom_instructions - still requires @claude trigger
+### What happened to `direct_prompt` and `custom_instructions`?
-custom_instructions: "Focus on performance implications and suggest optimizations"
+
+**These inputs are deprecated in v1.0:**
+
+- **`direct_prompt`** → Use `prompt` instead
+- **`custom_instructions`** → Use `claude_args` with `--system-prompt`
+
+Migration examples:
+
+```yaml
+# Old (v0.x)
+direct_prompt: "Review this PR"
+custom_instructions: "Focus on security"
+
+# New (v1.0)
+prompt: "Review this PR"
+claude_args: |
+  --system-prompt "Focus on security"
 ```
 
 ### Why doesn't Claude execute my bash commands?
 
-The Bash tool is **disabled by default** for security. To enable individual bash commands:
+The Bash tool is **disabled by default** for security. To enable individual bash commands using `claude_args`:
 
 ```yaml
-allowed_tools: "Bash(npm:*),Bash(git:*)" # Allows only npm and git commands
+claude_args: |
+  --allowedTools "Bash(npm:*),Bash(git:*)"  # Allows only npm and git commands
 ```
 
 ### Can Claude work across multiple repositories?
@@ -152,7 +174,7 @@ Claude Code Action automatically configures two MCP servers:
 1. **GitHub MCP server**: For GitHub API operations
 2. **File operations server**: For advanced file manipulation
 
-However, tools from these servers still need to be explicitly allowed via `allowed_tools`.
+However, tools from these servers still need to be explicitly allowed via `claude_args` with `--allowedTools`.
 
 ## Troubleshooting
 
@@ -168,7 +190,7 @@ The trigger uses word boundaries, so `@claude` must be a complete word. Variatio
 
 1. **Always specify permissions explicitly** in your workflow file
 2. **Use GitHub Secrets** for API keys - never hardcode them
-3. **Be specific with `allowed_tools`** - only enable what's necessary
+3. **Be specific with tool permissions** - only enable what's necessary via `claude_args`
 4. **Test in a separate branch** before using on important PRs
 5. **Monitor Claude's token usage** to avoid hitting API limits
 6. **Review Claude's changes** carefully before merging

docs/migration-guide.md

@@ -0,0 +1,219 @@
+# Migration Guide: v0.x to v1.0
+
+This guide helps you migrate from Claude Code Action v0.x to v1.0. The new version introduces intelligent mode detection and simplified configuration while maintaining backward compatibility for most use cases.
+
+## Overview of Changes
+
+### 🎯 Key Improvements in v1.0
+
+1. **Automatic Mode Detection** - No more manual `mode` configuration
+2. **Simplified Configuration** - Unified `prompt` and `claude_args` inputs
+3. **Better SDK Alignment** - Closer integration with Claude Code CLI
+
+### ⚠️ Breaking Changes
+
+The following inputs have been deprecated and replaced:
+
+| Deprecated Input      | Replacement                      | Notes                                         |
+| --------------------- | -------------------------------- | --------------------------------------------- |
+| `mode`                | Auto-detected                    | Action automatically chooses based on context |
+| `direct_prompt`       | `prompt`                         | Direct drop-in replacement                    |
+| `override_prompt`     | `prompt`                         | Use GitHub context variables instead          |
+| `custom_instructions` | `claude_args: --system-prompt`   | Move to CLI arguments                         |
+| `max_turns`           | `claude_args: --max-turns`       | Use CLI format                                |
+| `model`               | `claude_args: --model`           | Specify via CLI                               |
+| `allowed_tools`       | `claude_args: --allowedTools`    | Use CLI format                                |
+| `disallowed_tools`    | `claude_args: --disallowedTools` | Use CLI format                                |
+| `claude_env`          | `settings` with env object       | Use settings JSON                             |
+
+## Migration Examples
+
+### Basic Interactive Workflow (@claude mentions)
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    mode: "tag"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    custom_instructions: "Follow our coding standards"
+    max_turns: "10"
+    allowed_tools: "Edit,Read,Write"
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --max-turns 10
+      --system-prompt "Follow our coding standards"
+      --allowedTools Edit,Read,Write
+```
+
+### Automation Workflow
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    mode: "agent"
+    direct_prompt: "Review this PR for security issues"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    model: "claude-3-5-sonnet-20241022"
+    allowed_tools: "Edit,Read,Write"
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    prompt: "Review this PR for security issues"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --model claude-4-0-sonnet-20250805
+      --allowedTools Edit,Read,Write
+```
+
+### Custom Template with Variables
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    override_prompt: |
+      Analyze PR #$PR_NUMBER in $REPOSITORY
+      Changed files: $CHANGED_FILES
+      Focus on security vulnerabilities
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    prompt: |
+      Analyze PR #${{ github.event.pull_request.number }} in ${{ github.repository }}
+      Focus on security vulnerabilities in the changed files
+```
+
+### Environment Variables
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    claude_env: |
+      NODE_ENV: test
+      CI: true
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    settings: |
+      {
+        "env": {
+          "NODE_ENV": "test",
+          "CI": "true"
+        }
+      }
+```
+
+## How Mode Detection Works
+
+The action now automatically detects the appropriate mode:
+
+1. **If `prompt` is provided** → Runs in **automation mode**
+
+   - Executes immediately without waiting for @claude mentions
+   - Perfect for scheduled tasks, PR automation, etc.
+
+2. **If no `prompt` but @claude is mentioned** → Runs in **interactive mode**
+
+   - Waits for and responds to @claude mentions
+   - Creates tracking comments with progress
+
+3. **If neither** → No action is taken
+
+## Advanced Configuration with claude_args
+
+The `claude_args` input provides direct access to Claude Code CLI arguments:
+
+```yaml
+claude_args: |
+  --max-turns 15
+  --model claude-4-0-sonnet-20250805
+  --allowedTools Edit,Read,Write,Bash
+  --disallowedTools WebSearch
+  --system-prompt "You are a senior engineer focused on code quality"
+```
+
+### Common claude_args Options
+
+| Option              | Description              | Example                               |
+| ------------------- | ------------------------ | ------------------------------------- |
+| `--max-turns`       | Limit conversation turns | `--max-turns 10`                      |
+| `--model`           | Specify Claude model     | `--model claude-4-0-sonnet-20250805`  |
+| `--allowedTools`    | Enable specific tools    | `--allowedTools Edit,Read,Write`      |
+| `--disallowedTools` | Disable specific tools   | `--disallowedTools WebSearch`         |
+| `--system-prompt`   | Add system instructions  | `--system-prompt "Focus on security"` |
+
+## Provider-Specific Updates
+
+### AWS Bedrock
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    use_bedrock: "true"
+    claude_args: |
+      --model anthropic.claude-4-0-sonnet-20250805-v1:0
+```
+
+### Google Vertex AI
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    use_vertex: "true"
+    claude_args: |
+      --model claude-4-0-sonnet@20250805
+```
+
+## Step-by-Step Migration Checklist
+
+- [ ] Update action version from `@beta` to `@v1`
+- [ ] Remove `mode` input (auto-detected now)
+- [ ] Replace `direct_prompt` with `prompt`
+- [ ] Replace `override_prompt` with `prompt` using GitHub context
+- [ ] Move `custom_instructions` to `claude_args` with `--system-prompt`
+- [ ] Convert `max_turns` to `claude_args` with `--max-turns`
+- [ ] Convert `model` to `claude_args` with `--model`
+- [ ] Convert `allowed_tools` to `claude_args` with `--allowedTools`
+- [ ] Convert `disallowed_tools` to `claude_args` with `--disallowedTools`
+- [ ] Move `claude_env` to `settings` JSON format
+- [ ] Test workflow in a non-production environment
+
+## Getting Help
+
+If you encounter issues during migration:
+
+1. Check the [FAQ](./faq.md) for common questions
+2. Review [example workflows](../examples/) for reference
+3. Open an [issue](https://github.com/anthropics/claude-code-action/issues) for support
+
+## Version Compatibility
+
+- **v0.x workflows** will continue to work but with deprecation warnings
+- **v1.0** is the recommended version for all new workflows
+- Future versions may remove deprecated inputs entirely

docs/usage.md

@@ -18,27 +18,26 @@ jobs:
   claude-response:
     runs-on: ubuntu-latest
     steps:
-      - uses: anthropics/claude-code-action@beta
+      - uses: anthropics/claude-code-action@v1
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           # Or use OAuth token instead:
           # claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
-          github_token: ${{ secrets.GITHUB_TOKEN }}
+
-          # Optional: set execution mode (default: tag)
+          # Optional: provide a prompt for automation workflows
-          # mode: "tag"
+          # prompt: "Review this PR for security issues"
+
+          # Optional: pass advanced arguments to Claude CLI
+          # claude_args: |
+          #   --max-turns 10
+          #   --model claude-4-0-sonnet-20250805
+
           # Optional: add custom trigger phrase (default: @claude)
           # trigger_phrase: "/claude"
           # Optional: add assignee trigger for issues
           # assignee_trigger: "claude"
           # Optional: add label trigger for issues
           # label_trigger: "claude"
-          # Optional: add custom environment variables (YAML format)
-          # claude_env: |
-          #   NODE_ENV: test
-          #   DEBUG: true
-          #   API_URL: https://api.example.com
-          # Optional: limit the number of conversation turns
-          # max_turns: "5"
           # Optional: grant additional permissions (requires corresponding GitHub token permissions)
           # additional_permissions: |
           #   actions: read
@@ -49,41 +48,126 @@ jobs:
 ## Inputs
 
 | Input                          | Description                                                                                                          | Required | Default   |
-| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- |
+| ------------------------------ | -------------------------------------------------------------------------------------------------------------------- | -------- | --------- |
-| `mode`                         | Execution mode: 'tag' (default - triggered by mentions/assignments), 'agent' (for automation), 'experimental-review' (for PR reviews) | No       | `tag`     |
 | `anthropic_api_key`            | Anthropic API key (required for direct API, not needed for Bedrock/Vertex)                                           | No\*     | -         |
 | `claude_code_oauth_token`      | Claude Code OAuth token (alternative to anthropic_api_key)                                                           | No\*     | -         |
-| `direct_prompt`                | Direct prompt for Claude to execute automatically without needing a trigger (for automated workflows)                                 | No       | -         |
+| `prompt`                       | Instructions for Claude. Can be a direct prompt or custom template for automation workflows                          | No       | -         |
-| `override_prompt`              | Complete replacement of Claude's prompt with custom template (supports variable substitution)                                         | No       | -         |
+| `claude_args`                  | Additional arguments to pass directly to Claude CLI (e.g., `--max-turns 10 --model claude-4-0-sonnet-20250805`)      | No       | ""        |
 | `base_branch`                  | The base branch to use for creating new branches (e.g., 'main', 'develop')                                           | No       | -         |
-| `max_turns`                    | Maximum number of conversation turns Claude can take (limits back-and-forth exchanges)                                                | No       | -         |
-| `timeout_minutes`              | Timeout in minutes for execution                                                                                                      | No       | `30`      |
 | `use_sticky_comment`           | Use just one comment to deliver PR comments (only applies for pull_request event workflows)                          | No       | `false`   |
 | `github_token`                 | GitHub token for Claude to operate with. **Only include this if you're connecting a custom GitHub app of your own!** | No       | -         |
-| `model`                        | Model to use (provider-specific format required for Bedrock/Vertex)                                                                   | No       | -         |
-| `fallback_model`               | Enable automatic fallback to specified model when primary model is unavailable                                                        | No       | -         |
-| `anthropic_model`              | **DEPRECATED**: Use `model` instead. Kept for backward compatibility.                                                                 | No       | -         |
 | `use_bedrock`                  | Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API                                          | No       | `false`   |
 | `use_vertex`                   | Use Google Vertex AI with OIDC authentication instead of direct Anthropic API                                        | No       | `false`   |
-| `allowed_tools`                | Additional tools for Claude to use (the base GitHub tools will always be included)                                                    | No       | ""        |
-| `disallowed_tools`             | Tools that Claude should never use                                                                                                    | No       | ""        |
-| `custom_instructions`          | Additional custom instructions to include in the prompt for Claude                                                                    | No       | ""        |
 | `mcp_config`                   | Additional MCP configuration (JSON string) that merges with the built-in GitHub MCP servers                          | No       | ""        |
 | `assignee_trigger`             | The assignee username that triggers the action (e.g. @claude). Only used for issue assignment                        | No       | -         |
 | `label_trigger`                | The label name that triggers the action when applied to an issue (e.g. "claude")                                     | No       | -         |
 | `trigger_phrase`               | The trigger phrase to look for in comments, issue/PR bodies, and issue titles                                        | No       | `@claude` |
 | `branch_prefix`                | The prefix to use for Claude branches (defaults to 'claude/', use 'claude-' for dash format)                         | No       | `claude/` |
-| `claude_env`                   | Custom environment variables to pass to Claude Code execution (YAML format)                                                           | No       | ""        |
 | `settings`                     | Claude Code settings as JSON string or path to settings JSON file                                                    | No       | ""        |
 | `additional_permissions`       | Additional permissions to enable. Currently supports 'actions: read' for viewing workflow results                    | No       | ""        |
 | `experimental_allowed_domains` | Restrict network access to these domains only (newline-separated).                                                   | No       | ""        |
 | `use_commit_signing`           | Enable commit signing using GitHub's commit signature verification. When false, Claude uses standard git commands    | No       | `false`   |
 | `allowed_bots`                 | Comma-separated list of allowed bot usernames, or '\*' to allow all bots. Empty string (default) allows no bots      | No       | ""        |
 
+### Deprecated Inputs
+
+These inputs are deprecated and will be removed in a future version:
+
+| Input                 | Description                                                                                  | Migration Path                                                 |
+| --------------------- | -------------------------------------------------------------------------------------------- | -------------------------------------------------------------- |
+| `mode`                | **DEPRECATED**: Mode is now automatically detected based on workflow context                 | Remove this input; the action auto-detects the correct mode    |
+| `direct_prompt`       | **DEPRECATED**: Use `prompt` instead                                                         | Replace with `prompt`                                          |
+| `override_prompt`     | **DEPRECATED**: Use `prompt` with template variables or `claude_args` with `--system-prompt` | Use `prompt` for templates or `claude_args` for system prompts |
+| `custom_instructions` | **DEPRECATED**: Use `claude_args` with `--system-prompt` or include in `prompt`              | Move instructions to `prompt` or use `claude_args`             |
+| `max_turns`           | **DEPRECATED**: Use `claude_args` with `--max-turns` instead                                 | Use `claude_args: "--max-turns 5"`                             |
+| `model`               | **DEPRECATED**: Use `claude_args` with `--model` instead                                     | Use `claude_args: "--model claude-4-0-sonnet-20250805"`        |
+| `fallback_model`      | **DEPRECATED**: Use `claude_args` with fallback configuration                                | Configure fallback in `claude_args` or `settings`              |
+| `allowed_tools`       | **DEPRECATED**: Use `claude_args` with `--allowedTools` instead                              | Use `claude_args: "--allowedTools Edit,Read,Write"`            |
+| `disallowed_tools`    | **DEPRECATED**: Use `claude_args` with `--disallowedTools` instead                           | Use `claude_args: "--disallowedTools WebSearch"`               |
+| `claude_env`          | **DEPRECATED**: Use `settings` with env configuration                                        | Configure environment in `settings` JSON                       |
+
 \*Required when using direct Anthropic API (default and when not using Bedrock or Vertex)
 
 > **Note**: This action is currently in beta. Features and APIs may change as we continue to improve the integration.
 
+## Upgrading from v0.x?
+
+For a comprehensive guide on migrating from v0.x to v1.0, including step-by-step instructions and examples, see our **[Migration Guide](./migration-guide.md)**.
+
+### Quick Migration Examples
+
+#### Interactive Workflows (with @claude mentions)
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    mode: "tag"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    custom_instructions: "Focus on security"
+    max_turns: "10"
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --max-turns 10
+      --system-prompt "Focus on security"
+```
+
+#### Automation Workflows
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    mode: "agent"
+    direct_prompt: "Update the API documentation"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    model: "claude-4-0-sonnet-20250805"
+    allowed_tools: "Edit,Read,Write"
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    prompt: "Update the API documentation"
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --model claude-4-0-sonnet-20250805
+      --allowedTools Edit,Read,Write
+```
+
+#### Custom Templates
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    override_prompt: |
+      Analyze PR #$PR_NUMBER for security issues.
+      Focus on: $CHANGED_FILES
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    prompt: |
+      Analyze PR #${{ github.event.pull_request.number }} for security issues.
+      Focus on the changed files in this PR.
+```
+
 ## Ways to Tag @claude
 
 These examples show how to interact with Claude using comments in PRs and issues. By default, Claude will be triggered anytime you mention `@claude`, but you can customize the exact trigger phrase using the `trigger_phrase` input in the workflow.

examples/auto-fix-ci-signed/auto-fix-ci-signed.yml

@@ -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'"

examples/auto-fix-ci-signed/commands/fix-ci-signed.md

@@ -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.

examples/auto-fix-ci/auto-fix-ci.yml

@@ -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:*)'"

examples/auto-fix-ci/commands/fix-ci.md

@@ -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.

examples/claude-args-example.yml

@@ -15,15 +15,13 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Run Claude with custom arguments
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@v1-dev
         with:
-          mode: agent
           prompt: ${{ github.event.inputs.prompt }}
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
 
-          # New claudeArgs input allows direct CLI argument control
+          # claude_args provides direct CLI argument control
-          # Order: -p [claudeArgs] [legacy options] [BASE_ARGS]
+          # This allows full customization of Claude's behavior
-          # Note: BASE_ARGS (--verbose --output-format stream-json) cannot be overridden
           claude_args: |
             --max-turns 15
             --model claude-opus-4-1-20250805

examples/claude-auto-review.yml

@@ -1,4 +1,4 @@
-name: Claude Auto Review
+name: Claude PR Auto Review
 
 on:
   pull_request:
@@ -18,10 +18,9 @@ jobs:
           fetch-depth: 1
 
       - name: Automatic PR Review
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@v1-dev
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          timeout_minutes: "60"
           prompt: |
             Please review this pull request and provide comprehensive feedback.
 
@@ -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"

examples/claude-experimental-review-mode.yml

@@ -27,11 +27,10 @@ jobs:
           fetch-depth: 0 # Full history for better diff analysis
 
       - name: Code Review with Claude
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@v1-dev
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           # github_token not needed - uses default GITHUB_TOKEN for GitHub operations
-          timeout_minutes: "30"
           prompt: |
             Review this pull request comprehensively.
 

examples/claude-modes.yml

@@ -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
+  # Interactive Mode - Activated automatically when no prompt is provided
-  tag-mode-example:
+  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
+  # Automation Mode - Activated automatically when prompt is provided
-  agent-mode-scheduled-task:
+  automation-mode-scheduled-task:
-    # Only works with workflow_dispatch or schedule events
     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:
+          # Automation mode (auto-detected when prompt provided):
-          # - ONLY works with workflow_dispatch and schedule events
+          # - Works with any GitHub event
-          # - Does NOT work with pull_request, issues, or issue_comment events
+          # - Executes immediately without waiting for @claude mentions
-          # - No @claude mention needed for supported events
+          # - No tracking comments created
-          # - Perfect for: scheduled maintenance, manual automation runs
+          # - Perfect for: scheduled maintenance, automated reviews, CI/CD tasks

examples/claude-pr-path-specific.yml

@@ -24,10 +24,9 @@ jobs:
           fetch-depth: 1
 
       - name: Claude Code Review
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@v1-dev
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          timeout_minutes: "60"
           prompt: |
             Please review this pull request focusing on the changed files.
             Provide feedback on:

examples/claude-review-from-author.yml

@@ -23,10 +23,9 @@ jobs:
           fetch-depth: 1
 
       - name: Review PR from Specific Author
-        uses: anthropics/claude-code-action@v1
+        uses: anthropics/claude-code-action@v1-dev
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          timeout_minutes: "60"
           prompt: |
             Please provide a thorough review of this pull request.
 

examples/claude.yml

@@ -1,4 +1,4 @@
-name: Claude PR Assistant
+name: Claude Code
 
 on:
   issue_comment:
@@ -11,38 +11,52 @@ on:
     types: [submitted]
 
 jobs:
-  claude-code-action:
+  claude:
     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'))
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
     runs-on: ubuntu-latest
     permissions:
-      contents: read
+      contents: write
-      pull-requests: read
+      pull-requests: write
-      issues: read
+      issues: write
       id-token: write
+      actions: read # Required for Claude to read CI results on PRs
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
           fetch-depth: 1
 
-      - name: Run Claude PR Action
+      - name: Run Claude Code
-        uses: anthropics/claude-code-action@beta
+        id: claude
+        uses: anthropics/claude-code-action@v1-dev
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          # Or use OAuth token instead:
+
-          # claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          # This is an optional setting that allows Claude to read CI results on PRs
-          timeout_minutes: "60"
+          additional_permissions: |
-          # mode: tag  # Default: responds to @claude mentions
+            actions: read
-          # Optional: Restrict network access to specific domains only
+
-          # experimental_allowed_domains: |
+          # Optional: Customize the trigger phrase (default: @claude)
-          #   .anthropic.com
+          # trigger_phrase: "/claude"
-          #   .github.com
+
-          #   api.github.com
+          # Optional: Trigger when specific user is assigned to an issue
-          #   .githubusercontent.com
+          # assignee_trigger: "claude-bot"
-          #   bun.sh
+
-          #   registry.npmjs.org
+          # Optional: Configure Claude's behavior with CLI arguments
-          #   .blob.core.windows.net
+          # 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: Advanced settings configuration
+          # settings: |
+          #   {
+          #     "env": {
+          #       "NODE_ENV": "test"
+          #     }
+          #   }

examples/issue-deduplication.yml

@@ -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"

examples/issue-triage.yml

@@ -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"

examples/workflow-dispatch-agent.yml

@@ -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.' || '' }}

src/create-prompt/index.ts

@@ -750,7 +750,7 @@ export async function createPrompt(
       modeContext.claudeBranch,
     );
 
-    await mkdir(`${process.env.RUNNER_TEMP}/claude-prompts`, {
+    await mkdir(`${process.env.RUNNER_TEMP || "/tmp"}/claude-prompts`, {
       recursive: true,
     });
 
@@ -769,7 +769,7 @@ export async function createPrompt(
 
     // Write the prompt file
     await writeFile(
-      `${process.env.RUNNER_TEMP}/claude-prompts/claude-prompt.txt`,
+      `${process.env.RUNNER_TEMP || "/tmp"}/claude-prompts/claude-prompt.txt`,
       promptContent,
     );
 

src/entrypoints/collect-inputs.ts

@@ -0,0 +1,59 @@
+import * as core from "@actions/core";
+
+export function collectActionInputsPresence(): void {
+  const inputDefaults: Record<string, string> = {
+    trigger_phrase: "@claude",
+    assignee_trigger: "",
+    label_trigger: "claude",
+    base_branch: "",
+    branch_prefix: "claude/",
+    allowed_bots: "",
+    mode: "tag",
+    model: "",
+    anthropic_model: "",
+    fallback_model: "",
+    allowed_tools: "",
+    disallowed_tools: "",
+    custom_instructions: "",
+    direct_prompt: "",
+    override_prompt: "",
+    mcp_config: "",
+    additional_permissions: "",
+    claude_env: "",
+    settings: "",
+    anthropic_api_key: "",
+    claude_code_oauth_token: "",
+    github_token: "",
+    max_turns: "",
+    use_sticky_comment: "false",
+    use_commit_signing: "false",
+    experimental_allowed_domains: "",
+  };
+
+  const allInputsJson = process.env.ALL_INPUTS;
+  if (!allInputsJson) {
+    console.log("ALL_INPUTS environment variable not found");
+    core.setOutput("action_inputs_present", JSON.stringify({}));
+    return;
+  }
+
+  let allInputs: Record<string, string>;
+  try {
+    allInputs = JSON.parse(allInputsJson);
+  } catch (e) {
+    console.error("Failed to parse ALL_INPUTS JSON:", e);
+    core.setOutput("action_inputs_present", JSON.stringify({}));
+    return;
+  }
+
+  const presentInputs: Record<string, boolean> = {};
+
+  for (const [name, defaultValue] of Object.entries(inputDefaults)) {
+    const actualValue = allInputs[name] || "";
+
+    const isSet = actualValue !== defaultValue;
+    presentInputs[name] = isSet;
+  }
+
+  core.setOutput("action_inputs_present", JSON.stringify(presentInputs));
+}

src/entrypoints/prepare.ts

@@ -12,9 +12,12 @@ import { createOctokit } from "../github/api/client";
 import { parseGitHubContext, isEntityContext } from "../github/context";
 import { getMode } from "../modes/registry";
 import { prepare } from "../prepare";
+import { collectActionInputsPresence } from "./collect-inputs";
 
 async function run() {
   try {
+    collectActionInputsPresence();
+
     // Parse GitHub context first to enable mode detection
     const context = parseGitHubContext();
 
@@ -41,11 +44,18 @@ async function run() {
     // Check trigger conditions
     const containsTrigger = mode.shouldTrigger(context);
 
+    // Debug logging
+    console.log(`Mode: ${mode.name}`);
+    console.log(`Context prompt: ${context.inputs?.prompt || "NO PROMPT"}`);
+    console.log(`Trigger result: ${containsTrigger}`);
+
     // Set output for action.yml to check
     core.setOutput("contains_trigger", containsTrigger.toString());
 
     if (!containsTrigger) {
       console.log("No trigger found, skipping remaining steps");
+      // Still set github_token output even when skipping
+      core.setOutput("github_token", githubToken);
       return;
     }
 
@@ -56,10 +66,12 @@ async function run() {
       mode,
       githubToken,
     });
-    core.setOutput("GITHUB_TOKEN", githubToken);
 
     // MCP config is handled by individual modes (tag/agent) and included in their claude_args output
 
+    // Expose the GitHub token (Claude App token) as an output
+    core.setOutput("github_token", githubToken);
+
     // Step 6: Get system prompt from mode if available
     if (mode.getSystemPrompt) {
       const modeContext = mode.prepareContext(context, {

src/github/context.ts

@@ -6,6 +6,7 @@ import type {
   PullRequestEvent,
   PullRequestReviewEvent,
   PullRequestReviewCommentEvent,
+  WorkflowRunEvent,
 } from "@octokit/webhooks-types";
 // Custom types for GitHub Actions events that aren't webhooks
 export type WorkflowDispatchEvent = {
@@ -44,7 +45,11 @@ const ENTITY_EVENT_NAMES = [
   "pull_request_review_comment",
 ] as const;
 
-const AUTOMATION_EVENT_NAMES = ["workflow_dispatch", "schedule"] as const;
+const AUTOMATION_EVENT_NAMES = [
+  "workflow_dispatch",
+  "schedule",
+  "workflow_run",
+] as const;
 
 // Derive types from constants for better maintainability
 type EntityEventName = (typeof ENTITY_EVENT_NAMES)[number];
@@ -86,10 +91,10 @@ export type ParsedGitHubContext = BaseContext & {
   isPR: boolean;
 };
 
-// Context for automation events (workflow_dispatch, schedule)
+// Context for automation events (workflow_dispatch, schedule, workflow_run)
 export type AutomationContext = BaseContext & {
   eventName: AutomationEventName;
-  payload: WorkflowDispatchEvent | ScheduleEvent;
+  payload: WorkflowDispatchEvent | ScheduleEvent | WorkflowRunEvent;
 };
 
 // Union type for all contexts
@@ -185,6 +190,13 @@ export function parseGitHubContext(): GitHubContext {
         payload: context.payload as unknown as ScheduleEvent,
       };
     }
+    case "workflow_run": {
+      return {
+        ...commonFields,
+        eventName: "workflow_run",
+        payload: context.payload as unknown as WorkflowRunEvent,
+      };
+    }
     default:
       throw new Error(`Unsupported event type: ${context.eventName}`);
   }

src/github/operations/git-config.ts

@@ -6,7 +6,7 @@
  */
 
 import { $ } from "bun";
-import type { ParsedGitHubContext } from "../context";
+import type { GitHubContext } from "../context";
 import { GITHUB_SERVER_URL } from "../api/config";
 
 type GitUser = {
@@ -16,7 +16,7 @@ type GitUser = {
 
 export async function configureGitAuth(
   githubToken: string,
-  context: ParsedGitHubContext,
+  context: GitHubContext,
   user: GitUser | null,
 ) {
   console.log("Configuring git authentication for non-signing mode");

src/github/token.ts

@@ -31,8 +31,30 @@ async function exchangeForAppToken(oidcToken: string): Promise<string> {
     const responseJson = (await response.json()) as {
       error?: {
         message?: string;
+        details?: {
+          error_code?: string;
         };
       };
+      type?: string;
+      message?: string;
+    };
+
+    // Check for specific workflow validation error codes that should skip the action
+    const errorCode = responseJson.error?.details?.error_code;
+
+    if (errorCode === "workflow_not_found_on_default_branch") {
+      const message =
+        responseJson.message ??
+        responseJson.error?.message ??
+        "Workflow validation failed";
+      core.warning(`Skipping action due to workflow validation: ${message}`);
+      console.log(
+        "Action skipped due to workflow validation error. This is expected when adding Claude Code workflows to new repositories or on PRs with workflow changes. If you're seeing this, your workflow will begin working once you merge your PR.",
+      );
+      core.setOutput("skipped_due_to_workflow_validation_mismatch", "true");
+      process.exit(0);
+    }
+
     console.error(
       `App token exchange failed: ${response.status} ${response.statusText} - ${responseJson?.error?.message ?? "Unknown error"}`,
     );
@@ -77,8 +99,9 @@ export async function setupGitHubToken(): Promise<string> {
     core.setOutput("GITHUB_TOKEN", appToken);
     return appToken;
   } catch (error) {
+    // Only set failed if we get here - workflow validation errors will exit(0) before this
     core.setFailed(
-      `Failed to setup GitHub token: ${error}.\n\nIf you instead wish to use this action with a custom GitHub token or custom GitHub app, provide a \`github_token\` in the \`uses\` section of the app in your workflow yml file.`,
+      `Failed to setup GitHub token: ${error}\n\nIf you instead wish to use this action with a custom GitHub token or custom GitHub app, provide a \`github_token\` in the \`uses\` section of the app in your workflow yml file.`,
     );
     process.exit(1);
   }

src/github/utils/sanitizer.ts

@@ -58,6 +58,41 @@ export function sanitizeContent(content: string): string {
   content = stripMarkdownLinkTitles(content);
   content = stripHiddenAttributes(content);
   content = normalizeHtmlEntities(content);
+  content = redactGitHubTokens(content);
+  return content;
+}
+
+export function redactGitHubTokens(content: string): string {
+  // GitHub Personal Access Tokens (classic): ghp_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX (40 chars)
+  content = content.replace(
+    /\bghp_[A-Za-z0-9]{36}\b/g,
+    "[REDACTED_GITHUB_TOKEN]",
+  );
+
+  // GitHub OAuth tokens: gho_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX (40 chars)
+  content = content.replace(
+    /\bgho_[A-Za-z0-9]{36}\b/g,
+    "[REDACTED_GITHUB_TOKEN]",
+  );
+
+  // GitHub installation tokens: ghs_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX (40 chars)
+  content = content.replace(
+    /\bghs_[A-Za-z0-9]{36}\b/g,
+    "[REDACTED_GITHUB_TOKEN]",
+  );
+
+  // GitHub refresh tokens: ghr_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX (40 chars)
+  content = content.replace(
+    /\bghr_[A-Za-z0-9]{36}\b/g,
+    "[REDACTED_GITHUB_TOKEN]",
+  );
+
+  // GitHub fine-grained personal access tokens: github_pat_XXXXXXXXXX (up to 255 chars)
+  content = content.replace(
+    /\bgithub_pat_[A-Za-z0-9_]{11,221}\b/g,
+    "[REDACTED_GITHUB_TOKEN]",
+  );
+
   return content;
 }
 

src/mcp/github-comment-server.ts

@@ -6,6 +6,7 @@ import { z } from "zod";
 import { GITHUB_API_URL } from "../github/api/config";
 import { Octokit } from "@octokit/rest";
 import { updateClaudeComment } from "../github/operations/comments/update-claude-comment";
+import { sanitizeContent } from "../github/utils/sanitizer";
 
 // Get repository information from environment variables
 const REPO_OWNER = process.env.REPO_OWNER;
@@ -54,11 +55,13 @@ server.tool(
       const isPullRequestReviewComment =
         eventName === "pull_request_review_comment";
 
+      const sanitizedBody = sanitizeContent(body);
+
       const result = await updateClaudeComment(octokit, {
         owner,
         repo,
         commentId,
-        body,
+        body: sanitizedBody,
         isPullRequestReviewComment,
       });
 

src/mcp/github-file-ops-server.ts

@@ -3,8 +3,9 @@
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { z } from "zod";
-import { readFile } from "fs/promises";
+import { readFile, stat } from "fs/promises";
 import { join } from "path";
+import { constants } from "fs";
 import fetch from "node-fetch";
 import { GITHUB_API_URL } from "../github/api/config";
 import { retryWithBackoff } from "../utils/retry";
@@ -162,6 +163,34 @@ async function getOrCreateBranchRef(
   return baseSha;
 }
 
+// Get the appropriate Git file mode for a file
+async function getFileMode(filePath: string): Promise<string> {
+  try {
+    const fileStat = await stat(filePath);
+    if (fileStat.isFile()) {
+      // Check if execute bit is set for user
+      if (fileStat.mode & constants.S_IXUSR) {
+        return "100755"; // Executable file
+      } else {
+        return "100644"; // Regular file
+      }
+    } else if (fileStat.isDirectory()) {
+      return "040000"; // Directory (tree)
+    } else if (fileStat.isSymbolicLink()) {
+      return "120000"; // Symbolic link
+    } else {
+      // Fallback for unknown file types
+      return "100644";
+    }
+  } catch (error) {
+    // If we can't stat the file, default to regular file
+    console.warn(
+      `Could not determine file mode for ${filePath}, using default: ${error}`,
+    );
+    return "100644";
+  }
+}
+
 // Commit files tool
 server.tool(
   "commit_files",
@@ -223,6 +252,9 @@ server.tool(
             ? filePath
             : join(REPO_DIR, filePath);
 
+          // Get the proper file mode based on file permissions
+          const fileMode = await getFileMode(fullPath);
+
           // Check if file is binary (images, etc.)
           const isBinaryFile =
             /\.(png|jpg|jpeg|gif|webp|ico|pdf|zip|tar|gz|exe|bin|woff|woff2|ttf|eot)$/i.test(
@@ -261,7 +293,7 @@ server.tool(
             // Return tree entry with blob SHA
             return {
               path: filePath,
-              mode: "100644",
+              mode: fileMode,
               type: "blob",
               sha: blobData.sha,
             };
@@ -270,7 +302,7 @@ server.tool(
             const content = await readFile(fullPath, "utf-8");
             return {
               path: filePath,
-              mode: "100644",
+              mode: fileMode,
               type: "blob",
               content: content,
             };
@@ -353,15 +385,22 @@ server.tool(
 
           if (!updateRefResponse.ok) {
             const errorText = await updateRefResponse.text();
+
+            // Provide a more helpful error message for 403 permission errors
+            if (updateRefResponse.status === 403) {
+              const permissionError = new Error(
+                `Permission denied: Unable to push commits to branch '${branch}'. ` +
+                  `Please rebase your branch from the main/master branch to allow Claude to commit.\n\n` +
+                  `Original error: ${errorText}`,
+              );
+              throw permissionError;
+            }
+
+            // For other errors, use the original message
             const error = new Error(
               `Failed to update reference: ${updateRefResponse.status} - ${errorText}`,
             );
 
-            // Only retry on 403 errors - these are the intermittent failures we're targeting
-            if (updateRefResponse.status === 403) {
-              throw error;
-            }
-
             // For non-403 errors, fail immediately without retry
             console.error("Non-retryable error:", updateRefResponse.status);
             throw error;
@@ -559,16 +598,23 @@ server.tool(
 
           if (!updateRefResponse.ok) {
             const errorText = await updateRefResponse.text();
+
+            // Provide a more helpful error message for 403 permission errors
+            if (updateRefResponse.status === 403) {
+              console.log("Received 403 error, will retry...");
+              const permissionError = new Error(
+                `Permission denied: Unable to push commits to branch '${branch}'. ` +
+                  `Please rebase your branch from the main/master branch to allow Claude to commit.\n\n` +
+                  `Original error: ${errorText}`,
+              );
+              throw permissionError;
+            }
+
+            // For other errors, use the original message
             const error = new Error(
               `Failed to update reference: ${updateRefResponse.status} - ${errorText}`,
             );
 
-            // Only retry on 403 errors - these are the intermittent failures we're targeting
-            if (updateRefResponse.status === 403) {
-              console.log("Received 403 error, will retry...");
-              throw error;
-            }
-
             // For non-403 errors, fail immediately without retry
             console.error("Non-retryable error:", updateRefResponse.status);
             throw error;

src/mcp/github-inline-comment-server.ts

@@ -3,6 +3,7 @@ import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { z } from "zod";
 import { createOctokit } from "../github/api/client";
+import { sanitizeContent } from "../github/utils/sanitizer";
 
 // Get repository and PR information from environment variables
 const REPO_OWNER = process.env.REPO_OWNER;
@@ -81,6 +82,9 @@ server.tool(
 
       const octokit = createOctokit(githubToken).rest;
 
+      // Sanitize the comment body to remove any potential GitHub tokens
+      const sanitizedBody = sanitizeContent(body);
+
       // Validate that either line or both startLine and line are provided
       if (!line && !startLine) {
         throw new Error(
@@ -104,7 +108,7 @@ server.tool(
         owner,
         repo,
         pull_number,
-        body,
+        body: sanitizedBody,
         path,
         side: side || "RIGHT",
         commit_id: commit_id || pr.data.head.sha,

src/mcp/install-mcp-server.ts

@@ -1,6 +1,7 @@
 import * as core from "@actions/core";
 import { GITHUB_API_URL, GITHUB_SERVER_URL } from "../github/api/config";
-import type { ParsedGitHubContext } from "../github/context";
+import type { GitHubContext } from "../github/context";
+import { isEntityContext } from "../github/context";
 import { Octokit } from "@octokit/rest";
 
 type PrepareConfigParams = {
@@ -9,10 +10,9 @@ type PrepareConfigParams = {
   repo: string;
   branch: string;
   baseBranch: string;
-  additionalMcpConfig?: string;
   claudeCommentId?: string;
   allowedTools: string[];
-  context: ParsedGitHubContext;
+  context: GitHubContext;
 };
 
 async function checkActionsReadPermission(
@@ -56,7 +56,6 @@ export async function prepareMcpConfig(
     repo,
     branch,
     baseBranch,
-    additionalMcpConfig,
     claudeCommentId,
     allowedTools,
     context,
@@ -68,6 +67,10 @@ export async function prepareMcpConfig(
       tool.startsWith("mcp__github__"),
     );
 
+    const hasInlineCommentTools = allowedToolsList.some((tool) =>
+      tool.startsWith("mcp__github_inline_comment__"),
+    );
+
     const baseMcpConfig: { mcpServers: Record<string, unknown> } = {
       mcpServers: {},
     };
@@ -111,8 +114,12 @@ export async function prepareMcpConfig(
       };
     }
 
-    // Include inline comment server for experimental review mode
+    // Include inline comment server for PRs when requested via allowed tools
-    if (context.inputs.mode === "experimental-review" && context.isPR) {
+    if (
+      isEntityContext(context) &&
+      context.isPR &&
+      (hasGitHubMcpTools || hasInlineCommentTools)
+    ) {
       baseMcpConfig.mcpServers.github_inline_comment = {
         command: "bun",
         args: [
@@ -129,11 +136,10 @@ export async function prepareMcpConfig(
       };
     }
 
-    // Only add CI server if we have actions:read permission and we're in a PR context
+    // CI server is included when we have a workflow token and context is a PR
-    const hasActionsReadPermission =
+    const hasWorkflowToken = !!process.env.DEFAULT_WORKFLOW_TOKEN;
-      context.inputs.additionalPermissions.get("actions") === "read";
 
-    if (context.isPR && hasActionsReadPermission) {
+    if (isEntityContext(context) && context.isPR && hasWorkflowToken) {
       // Verify the token actually has actions:read permission
       const actuallyHasPermission = await checkActionsReadPermission(
         process.env.DEFAULT_WORKFLOW_TOKEN || "",
@@ -185,38 +191,8 @@ export async function prepareMcpConfig(
       };
     }
 
-    // Merge with additional MCP config if provided
+    // Return only our GitHub servers config
-    if (additionalMcpConfig && additionalMcpConfig.trim()) {
+    // User's config will be passed as separate --mcp-config flags
-      try {
-        const additionalConfig = JSON.parse(additionalMcpConfig);
-
-        // Validate that parsed JSON is an object
-        if (typeof additionalConfig !== "object" || additionalConfig === null) {
-          throw new Error("MCP config must be a valid JSON object");
-        }
-
-        core.info(
-          "Merging additional MCP server configuration with built-in servers",
-        );
-
-        // Merge configurations with user config overriding built-in servers
-        const mergedConfig = {
-          ...baseMcpConfig,
-          ...additionalConfig,
-          mcpServers: {
-            ...baseMcpConfig.mcpServers,
-            ...additionalConfig.mcpServers,
-          },
-        };
-
-        return JSON.stringify(mergedConfig, null, 2);
-      } catch (parseError) {
-        core.warning(
-          `Failed to parse additional MCP config: ${parseError}. Using base config only.`,
-        );
-      }
-    }
-
     return JSON.stringify(baseMcpConfig, null, 2);
   } catch (error) {
     core.setFailed(`Install MCP server failed with error: ${error}`);

src/modes/agent/index.ts

@@ -2,16 +2,9 @@ import * as core from "@actions/core";
 import { mkdir, writeFile } from "fs/promises";
 import type { Mode, ModeOptions, ModeResult } from "../types";
 import type { PreparedContext } from "../../create-prompt/types";
-import { GITHUB_API_URL, GITHUB_SERVER_URL } from "../../github/api/config";
+import { prepareMcpConfig } from "../../mcp/install-mcp-server";
-import { fetchGitHubData } from "../../github/data/fetcher";
+import { parseAllowedTools } from "./parse-tools";
-import { 
+import { configureGitAuth } from "../../github/operations/git-config";
-  formatContext, 
-  formatBody, 
-  formatComments,
-  formatReviewComments,
-  formatChangedFilesWithSHA 
-} from "../../github/data/formatter";
-import { isEntityContext } from "../../github/context";
 
 /**
  * Agent mode implementation.
@@ -49,172 +42,103 @@ export const agentMode: Mode = {
     return false;
   },
 
-  async prepare({ context, githubToken, octokit }: ModeOptions): Promise<ModeResult> {
+  async prepare({
-    // Agent mode handles automation events and any event with explicit prompts
+    context,
+    githubToken,
+    octokit,
+  }: ModeOptions): Promise<ModeResult> {
+    // Configure git authentication for agent mode (same as tag mode)
+    if (!context.inputs.useCommitSigning) {
+      try {
+        // Get the authenticated user (will be claude[bot] when using Claude App token)
+        const { data: authenticatedUser } =
+          await octokit.rest.users.getAuthenticated();
+        const user = {
+          login: authenticatedUser.login,
+          id: authenticatedUser.id,
+        };
 
-    console.log(`Agent mode: githubToken provided: ${!!githubToken}, length: ${githubToken?.length || 0}`);
+        // Use the shared git configuration function
+        await configureGitAuth(githubToken, context, user);
+      } catch (error) {
+        console.error("Failed to configure git authentication:", error);
+        // Continue anyway - git operations may still work with default config
+      }
+    }
 
     // Create prompt directory
-    await mkdir(`${process.env.RUNNER_TEMP}/claude-prompts`, {
+    await mkdir(`${process.env.RUNNER_TEMP || "/tmp"}/claude-prompts`, {
       recursive: true,
     });
 
-    // Fetch GitHub context data if we're in an entity context (PR/issue)
+    // Write the prompt file - use the user's prompt directly
-    let githubContextPrefix = '';
+    const promptContent =
-    if (isEntityContext(context)) {
+      context.inputs.prompt ||
-      try {
-        const githubData = await fetchGitHubData({
-          octokits: octokit,
-          repository: `${context.repository.owner}/${context.repository.repo}`,
-          prNumber: context.entityNumber.toString(),
-          isPR: context.isPR,
-          triggerUsername: context.actor,
-        });
-        
-        // Format the GitHub data into a readable context
-        const formattedContext = formatContext(githubData.contextData, context.isPR);
-        const formattedBody = githubData.contextData?.body 
-          ? formatBody(githubData.contextData.body, githubData.imageUrlMap)
-          : "No description provided";
-        const formattedComments = formatComments(githubData.comments, githubData.imageUrlMap);
-        
-        // Build the context prefix
-        githubContextPrefix = `## GitHub Context
-
-${formattedContext}
-
-### Description
-${formattedBody}`;
-        
-        if (formattedComments && formattedComments.trim()) {
-          githubContextPrefix += `\n\n### Comments\n${formattedComments}`;
-        }
-        
-        if (context.isPR && githubData.changedFilesWithSHA) {
-          const formattedFiles = formatChangedFilesWithSHA(githubData.changedFilesWithSHA);
-          githubContextPrefix += `\n\n### Changed Files\n${formattedFiles}`;
-        }
-        
-        githubContextPrefix += '\n\n## Your Task\n\n';
-      } catch (error) {
-        console.warn('Failed to fetch GitHub context:', error);
-        // Continue without GitHub context if fetching fails
-      }
-    }
-    
-    // Write the prompt file with GitHub context prefix
-    const userPrompt = context.inputs.prompt || 
       `Repository: ${context.repository.owner}/${context.repository.repo}`;
-    const promptContent = githubContextPrefix + userPrompt;
 
     await writeFile(
-      `${process.env.RUNNER_TEMP}/claude-prompts/claude-prompt.txt`,
+      `${process.env.RUNNER_TEMP || "/tmp"}/claude-prompts/claude-prompt.txt`,
       promptContent,
     );
 
-    // Agent mode: User has full control via claudeArgs
+    // Parse allowed tools from user's claude_args
-    // No default tools are enforced - Claude Code's defaults will apply
-
-    // Include both GitHub comment server and main GitHub MCP server by default
-    // This ensures comprehensive GitHub tools work out of the box
-    const mcpConfig: any = {
-      mcpServers: {
-        // GitHub comment server for updating Claude comments
-        github_comment: {
-          command: "bun",
-          args: [
-            "run",
-            `${process.env.GITHUB_ACTION_PATH}/src/mcp/github-comment-server.ts`,
-          ],
-          env: {
-            GITHUB_TOKEN: githubToken || "",
-            REPO_OWNER: context.repository.owner,
-            REPO_NAME: context.repository.repo,
-            CLAUDE_COMMENT_ID: process.env.CLAUDE_COMMENT_ID || "",
-            PR_NUMBER: (context as any).entityNumber?.toString() || process.env.GITHUB_EVENT_PULL_REQUEST_NUMBER || "",
-            ISSUE_NUMBER: (context as any).entityNumber?.toString() || "",
-            GITHUB_EVENT_NAME: process.env.GITHUB_EVENT_NAME || "",
-            GITHUB_API_URL:
-              process.env.GITHUB_API_URL || "https://api.github.com",
-          },
-        },
-        // Main GitHub MCP server for comprehensive GitHub operations
-        github: {
-          command: "docker",
-          args: [
-            "run",
-            "-i",
-            "--rm",
-            "-e",
-            "GITHUB_PERSONAL_ACCESS_TOKEN",
-            "-e",
-            "GITHUB_HOST",
-            "ghcr.io/github/github-mcp-server:sha-efef8ae", // https://github.com/github/github-mcp-server/releases/tag/v0.9.0
-          ],
-          env: {
-            GITHUB_PERSONAL_ACCESS_TOKEN: githubToken || "",
-            GITHUB_HOST: GITHUB_SERVER_URL,
-          },
-        },
-      },
-    };
-    
-    // Include inline comment server for PR contexts
-    if (context.eventName === "pull_request" || context.eventName === "pull_request_review") {
-      // Get PR number from the context payload
-      const prNumber = (context as any).payload?.pull_request?.number || 
-                      (context as any).entityNumber || 
-                      "";
-      
-      mcpConfig.mcpServers.github_inline_comment = {
-        command: "bun",
-        args: [
-          "run",
-          `${process.env.GITHUB_ACTION_PATH}/src/mcp/github-inline-comment-server.ts`,
-        ],
-        env: {
-          GITHUB_TOKEN: githubToken || "",
-          REPO_OWNER: context.repository.owner,
-          REPO_NAME: context.repository.repo,
-          PR_NUMBER: prNumber.toString(),
-          GITHUB_API_URL: process.env.GITHUB_API_URL || "https://api.github.com",
-        },
-      };
-    }
-
-    // Add user-provided additional MCP config if any
-    const additionalMcpConfig = process.env.MCP_CONFIG || "";
-    if (additionalMcpConfig.trim()) {
-      try {
-        const additional = JSON.parse(additionalMcpConfig);
-        if (additional && typeof additional === "object") {
-          // Merge mcpServers if both have them
-          if (additional.mcpServers && mcpConfig.mcpServers) {
-            Object.assign(mcpConfig.mcpServers, additional.mcpServers);
-          } else {
-            Object.assign(mcpConfig, additional);
-          }
-        }
-      } catch (error) {
-        core.warning(`Failed to parse additional MCP config: ${error}`);
-      }
-    }
-
-    // Agent mode: pass through user's claude_args with MCP config
     const userClaudeArgs = process.env.CLAUDE_ARGS || "";
-    const escapedMcpConfig = JSON.stringify(mcpConfig).replace(/'/g, "'\\''");
+    const allowedTools = parseAllowedTools(userClaudeArgs);
-    const claudeArgs =
+
-      `--mcp-config '${escapedMcpConfig}' ${userClaudeArgs}`.trim();
+    // Check for branch info from environment variables (useful for auto-fix workflows)
+    const claudeBranch = process.env.CLAUDE_BRANCH || undefined;
+    const baseBranch =
+      process.env.BASE_BRANCH || context.inputs.baseBranch || "main";
+
+    // Detect current branch from GitHub environment
+    const currentBranch =
+      claudeBranch ||
+      process.env.GITHUB_HEAD_REF ||
+      process.env.GITHUB_REF_NAME ||
+      "main";
+
+    // Get our GitHub MCP servers config
+    const ourMcpConfig = await prepareMcpConfig({
+      githubToken,
+      owner: context.repository.owner,
+      repo: context.repository.repo,
+      branch: currentBranch,
+      baseBranch: baseBranch,
+      claudeCommentId: undefined, // No tracking comment in agent mode
+      allowedTools,
+      context,
+    });
+
+    // Build final claude_args with multiple --mcp-config flags
+    let claudeArgs = "";
+
+    // Add our GitHub servers config if we have any
+    const ourConfig = JSON.parse(ourMcpConfig);
+    if (ourConfig.mcpServers && Object.keys(ourConfig.mcpServers).length > 0) {
+      const escapedOurConfig = ourMcpConfig.replace(/'/g, "'\\''");
+      claudeArgs = `--mcp-config '${escapedOurConfig}'`;
+    }
+
+    // Add user's MCP_CONFIG env var as separate --mcp-config
+    const userMcpConfig = process.env.MCP_CONFIG;
+    if (userMcpConfig?.trim()) {
+      const escapedUserConfig = userMcpConfig.replace(/'/g, "'\\''");
+      claudeArgs = `${claudeArgs} --mcp-config '${escapedUserConfig}'`.trim();
+    }
+
+    // Append user's claude_args (which may have more --mcp-config flags)
+    claudeArgs = `${claudeArgs} ${userClaudeArgs}`.trim();
+
     core.setOutput("claude_args", claudeArgs);
 
     return {
       commentId: undefined,
       branchInfo: {
-        baseBranch: "",
+        baseBranch: baseBranch,
-        currentBranch: "",
+        currentBranch: baseBranch, // Use base branch as current when creating new branch
-        claudeBranch: undefined,
+        claudeBranch: claudeBranch,
       },
-      mcpConfig: JSON.stringify(mcpConfig),
+      mcpConfig: ourMcpConfig,
     };
   },
 

src/modes/agent/parse-tools.ts

@@ -0,0 +1,22 @@
+export function parseAllowedTools(claudeArgs: string): string[] {
+  // Match --allowedTools followed by the value
+  // Handle both quoted and unquoted values
+  const patterns = [
+    /--allowedTools\s+"([^"]+)"/, // Double quoted
+    /--allowedTools\s+'([^']+)'/, // Single quoted
+    /--allowedTools\s+([^\s]+)/, // Unquoted
+  ];
+
+  for (const pattern of patterns) {
+    const match = claudeArgs.match(pattern);
+    if (match && match[1]) {
+      // Don't return if the value starts with -- (another flag)
+      if (match[1].startsWith("--")) {
+        return [];
+      }
+      return match[1].split(",").map((t) => t.trim());
+    }
+  }
+
+  return [];
+}

src/modes/tag/index.ts

@@ -100,15 +100,13 @@ export const tagMode: Mode = {
 
     await createPrompt(tagMode, modeContext, githubData, context);
 
-    // Get MCP configuration
+    // Get our GitHub MCP servers configuration
-    const additionalMcpConfig = process.env.MCP_CONFIG || "";
+    const ourMcpConfig = await prepareMcpConfig({
-    const mcpConfig = await prepareMcpConfig({
       githubToken,
       owner: context.repository.owner,
       repo: context.repository.repo,
       branch: branchInfo.claudeBranch || branchInfo.currentBranch,
       baseBranch: branchInfo.baseBranch,
-      additionalMcpConfig,
       claudeCommentId: commentId.toString(),
       allowedTools: [],
       context,
@@ -150,14 +148,26 @@ export const tagMode: Mode = {
 
     const userClaudeArgs = process.env.CLAUDE_ARGS || "";
 
-    // Build complete claude_args with MCP config (as JSON string), tools, and user args
+    // Build complete claude_args with multiple --mcp-config flags
-    // Note: Once Claude supports multiple --mcp-config flags, we can pass as file path
+    let claudeArgs = "";
-    // Escape single quotes in JSON to prevent shell injection
+
-    const escapedMcpConfig = mcpConfig.replace(/'/g, "'\\''");
+    // Add our GitHub servers config
-    let claudeArgs = `--mcp-config '${escapedMcpConfig}' `;
+    const escapedOurConfig = ourMcpConfig.replace(/'/g, "'\\''");
+    claudeArgs = `--mcp-config '${escapedOurConfig}'`;
+
+    // Add user's MCP_CONFIG env var as separate --mcp-config
+    const userMcpConfig = process.env.MCP_CONFIG;
+    if (userMcpConfig?.trim()) {
+      const escapedUserConfig = userMcpConfig.replace(/'/g, "'\\''");
+      claudeArgs = `${claudeArgs} --mcp-config '${escapedUserConfig}'`;
+    }
+
+    // Add required tools for tag mode
     claudeArgs += ` --allowedTools "${tagModeTools.join(",")}"`;
+
+    // Append user's claude_args (which may have more --mcp-config flags)
     if (userClaudeArgs) {
-      claudeArgs += userClaudeArgs;
+      claudeArgs += ` ${userClaudeArgs}`;
     }
 
     core.setOutput("claude_args", claudeArgs.trim());
@@ -165,7 +175,7 @@ export const tagMode: Mode = {
     return {
       commentId,
       branchInfo,
-      mcpConfig,
+      mcpConfig: ourMcpConfig,
     };
   },
 

test/install-mcp-server.test.ts

@@ -50,14 +50,6 @@ describe("prepareMcpConfig", () => {
     },
   };
 
-  const mockPRContextWithSigning: ParsedGitHubContext = {
-    ...mockPRContext,
-    inputs: {
-      ...mockPRContext.inputs,
-      useCommitSigning: true,
-    },
-  };
-
   beforeEach(() => {
     consoleInfoSpy = spyOn(core, "info").mockImplementation(() => {});
     consoleWarningSpy = spyOn(core, "warning").mockImplementation(() => {});
@@ -98,19 +90,9 @@ describe("prepareMcpConfig", () => {
     expect(parsed.mcpServers.github_comment.env.GITHUB_TOKEN).toBe(
       "test-token",
     );
-    expect(parsed.mcpServers.github_comment.env.REPO_OWNER).toBe("test-owner");
-    expect(parsed.mcpServers.github_comment.env.REPO_NAME).toBe("test-repo");
   });
 
-  test("should return file ops server when commit signing is enabled", async () => {
+  test("should include file ops server when commit signing is enabled", async () => {
-    const contextWithSigning = {
-      ...mockContext,
-      inputs: {
-        ...mockContext.inputs,
-        useCommitSigning: true,
-      },
-    };
-
     const result = await prepareMcpConfig({
       githubToken: "test-token",
       owner: "test-owner",
@@ -118,19 +100,16 @@ describe("prepareMcpConfig", () => {
       branch: "test-branch",
       baseBranch: "main",
       allowedTools: [],
-      context: contextWithSigning,
+      context: mockContextWithSigning,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers).toBeDefined();
     expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_comment).toBeDefined();
     expect(parsed.mcpServers.github_file_ops).toBeDefined();
     expect(parsed.mcpServers.github_file_ops.env.GITHUB_TOKEN).toBe(
       "test-token",
     );
-    expect(parsed.mcpServers.github_file_ops.env.REPO_OWNER).toBe("test-owner");
-    expect(parsed.mcpServers.github_file_ops.env.REPO_NAME).toBe("test-repo");
     expect(parsed.mcpServers.github_file_ops.env.BRANCH_NAME).toBe(
       "test-branch",
     );
@@ -143,49 +122,37 @@ describe("prepareMcpConfig", () => {
       repo: "test-repo",
       branch: "test-branch",
       baseBranch: "main",
-      allowedTools: [
+      allowedTools: ["mcp__github__create_issue", "mcp__github__create_pr"],
-        "mcp__github__create_issue",
-        "mcp__github_file_ops__commit_files",
-      ],
       context: mockContext,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers).toBeDefined();
     expect(parsed.mcpServers.github).toBeDefined();
-    expect(parsed.mcpServers.github_comment).toBeDefined();
+    expect(parsed.mcpServers.github.command).toBe("docker");
-    expect(parsed.mcpServers.github_file_ops).not.toBeDefined();
     expect(parsed.mcpServers.github.env.GITHUB_PERSONAL_ACCESS_TOKEN).toBe(
       "test-token",
     );
   });
 
-  test("should not include github MCP server when only file_ops tools are allowed", async () => {
+  test("should include inline comment server for PRs when tools are allowed", async () => {
-    const contextWithSigning = {
-      ...mockContext,
-      inputs: {
-        ...mockContext.inputs,
-        useCommitSigning: true,
-      },
-    };
-
     const result = await prepareMcpConfig({
       githubToken: "test-token",
       owner: "test-owner",
       repo: "test-repo",
       branch: "test-branch",
       baseBranch: "main",
-      allowedTools: [
+      allowedTools: ["mcp__github_inline_comment__create_inline_comment"],
-        "mcp__github_file_ops__commit_files",
+      context: mockPRContext,
-        "mcp__github_file_ops__update_claude_comment",
-      ],
-      context: contextWithSigning,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers).toBeDefined();
-    expect(parsed.mcpServers.github).not.toBeDefined();
+    expect(parsed.mcpServers.github_inline_comment).toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
+    expect(parsed.mcpServers.github_inline_comment.env.GITHUB_TOKEN).toBe(
+      "test-token",
+    );
+    expect(parsed.mcpServers.github_inline_comment.env.PR_NUMBER).toBe("456");
   });
 
   test("should include comment server when no GitHub tools are allowed and signing disabled", async () => {
@@ -195,7 +162,7 @@ describe("prepareMcpConfig", () => {
       repo: "test-repo",
       branch: "test-branch",
       baseBranch: "main",
-      allowedTools: ["Edit", "Read", "Write"],
+      allowedTools: [],
       context: mockContext,
     });
 
@@ -206,301 +173,7 @@ describe("prepareMcpConfig", () => {
     expect(parsed.mcpServers.github_comment).toBeDefined();
   });
 
-  test("should return base config when additional config is empty string", async () => {
+  test("should set GITHUB_ACTION_PATH correctly", async () => {
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: "",
-      allowedTools: [],
-      context: mockContext,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.mcpServers).toBeDefined();
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_comment).toBeDefined();
-    expect(consoleWarningSpy).not.toHaveBeenCalled();
-  });
-
-  test("should return base config when additional config is whitespace only", async () => {
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: "   \n\t  ",
-      allowedTools: [],
-      context: mockContext,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.mcpServers).toBeDefined();
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_comment).toBeDefined();
-    expect(consoleWarningSpy).not.toHaveBeenCalled();
-  });
-
-  test("should merge valid additional config with base config", async () => {
-    const additionalConfig = JSON.stringify({
-      mcpServers: {
-        custom_server: {
-          command: "custom-command",
-          args: ["arg1", "arg2"],
-          env: {
-            CUSTOM_ENV: "custom-value",
-          },
-        },
-      },
-    });
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: additionalConfig,
-      allowedTools: [
-        "mcp__github__create_issue",
-        "mcp__github_file_ops__commit_files",
-      ],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(consoleInfoSpy).toHaveBeenCalledWith(
-      "Merging additional MCP server configuration with built-in servers",
-    );
-    expect(parsed.mcpServers.github).toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-    expect(parsed.mcpServers.custom_server).toBeDefined();
-    expect(parsed.mcpServers.custom_server.command).toBe("custom-command");
-    expect(parsed.mcpServers.custom_server.args).toEqual(["arg1", "arg2"]);
-    expect(parsed.mcpServers.custom_server.env.CUSTOM_ENV).toBe("custom-value");
-  });
-
-  test("should override built-in servers when additional config has same server names", async () => {
-    const additionalConfig = JSON.stringify({
-      mcpServers: {
-        github: {
-          command: "overridden-command",
-          args: ["overridden-arg"],
-          env: {
-            OVERRIDDEN_ENV: "overridden-value",
-          },
-        },
-      },
-    });
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: additionalConfig,
-      allowedTools: [
-        "mcp__github__create_issue",
-        "mcp__github_file_ops__commit_files",
-      ],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(consoleInfoSpy).toHaveBeenCalledWith(
-      "Merging additional MCP server configuration with built-in servers",
-    );
-    expect(parsed.mcpServers.github.command).toBe("overridden-command");
-    expect(parsed.mcpServers.github.args).toEqual(["overridden-arg"]);
-    expect(parsed.mcpServers.github.env.OVERRIDDEN_ENV).toBe(
-      "overridden-value",
-    );
-    expect(
-      parsed.mcpServers.github.env.GITHUB_PERSONAL_ACCESS_TOKEN,
-    ).toBeUndefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-  });
-
-  test("should merge additional root-level properties", async () => {
-    const additionalConfig = JSON.stringify({
-      customProperty: "custom-value",
-      anotherProperty: {
-        nested: "value",
-      },
-      mcpServers: {
-        custom_server: {
-          command: "custom",
-        },
-      },
-    });
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: additionalConfig,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.customProperty).toBe("custom-value");
-    expect(parsed.anotherProperty).toEqual({ nested: "value" });
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.custom_server).toBeDefined();
-  });
-
-  test("should handle invalid JSON gracefully", async () => {
-    const invalidJson = "{ invalid json }";
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: invalidJson,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining("Failed to parse additional MCP config:"),
-    );
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-  });
-
-  test("should handle non-object JSON values", async () => {
-    const nonObjectJson = JSON.stringify("string value");
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: nonObjectJson,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining("Failed to parse additional MCP config:"),
-    );
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining("MCP config must be a valid JSON object"),
-    );
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-  });
-
-  test("should handle null JSON value", async () => {
-    const nullJson = JSON.stringify(null);
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: nullJson,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining("Failed to parse additional MCP config:"),
-    );
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining("MCP config must be a valid JSON object"),
-    );
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-  });
-
-  test("should handle array JSON value", async () => {
-    const arrayJson = JSON.stringify([1, 2, 3]);
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: arrayJson,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    // Arrays are objects in JavaScript, so they pass the object check
-    // But they'll fail when trying to spread or access mcpServers property
-    expect(consoleInfoSpy).toHaveBeenCalledWith(
-      "Merging additional MCP server configuration with built-in servers",
-    );
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-    // The array will be spread into the config (0: 1, 1: 2, 2: 3)
-    expect(parsed[0]).toBe(1);
-    expect(parsed[1]).toBe(2);
-    expect(parsed[2]).toBe(3);
-  });
-
-  test("should merge complex nested configurations", async () => {
-    const additionalConfig = JSON.stringify({
-      mcpServers: {
-        server1: {
-          command: "cmd1",
-          env: { KEY1: "value1" },
-        },
-        server2: {
-          command: "cmd2",
-          env: { KEY2: "value2" },
-        },
-        github_file_ops: {
-          command: "overridden",
-          env: { CUSTOM: "value" },
-        },
-      },
-      otherConfig: {
-        nested: {
-          deeply: "value",
-        },
-      },
-    });
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      additionalMcpConfig: additionalConfig,
-      allowedTools: [],
-      context: mockContextWithSigning,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.mcpServers.server1).toBeDefined();
-    expect(parsed.mcpServers.server2).toBeDefined();
-    expect(parsed.mcpServers.github).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops.command).toBe("overridden");
-    expect(parsed.mcpServers.github_file_ops.env.CUSTOM).toBe("value");
-    expect(parsed.otherConfig.nested.deeply).toBe("value");
-  });
-
-  test("should preserve GITHUB_ACTION_PATH in file_ops server args", async () => {
-    const oldEnv = process.env.GITHUB_ACTION_PATH;
     process.env.GITHUB_ACTION_PATH = "/test/action/path";
 
     const result = await prepareMcpConfig({
@@ -514,15 +187,12 @@ describe("prepareMcpConfig", () => {
     });
 
     const parsed = JSON.parse(result);
-    expect(parsed.mcpServers.github_file_ops.args[1]).toBe(
+    expect(parsed.mcpServers.github_file_ops.args).toContain(
       "/test/action/path/src/mcp/github-file-ops-server.ts",
     );
-
-    process.env.GITHUB_ACTION_PATH = oldEnv;
   });
 
-  test("should use process.cwd() when GITHUB_WORKSPACE is not set", async () => {
+  test("should use current working directory when GITHUB_WORKSPACE is not set", async () => {
-    const oldEnv = process.env.GITHUB_WORKSPACE;
     delete process.env.GITHUB_WORKSPACE;
 
     const result = await prepareMcpConfig({
@@ -537,22 +207,11 @@ describe("prepareMcpConfig", () => {
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers.github_file_ops.env.REPO_DIR).toBe(process.cwd());
-
-    process.env.GITHUB_WORKSPACE = oldEnv;
   });
 
-  test("should include github_ci server when context.isPR is true and workflow token is present", async () => {
+  test("should include CI server when context.isPR is true and DEFAULT_WORKFLOW_TOKEN exists", async () => {
-    const oldEnv = process.env.DEFAULT_WORKFLOW_TOKEN;
     process.env.DEFAULT_WORKFLOW_TOKEN = "workflow-token";
 
-    const contextWithPermissions = {
-      ...mockPRContext,
-      inputs: {
-        ...mockPRContext.inputs,
-        useCommitSigning: true,
-      },
-    };
-
     const result = await prepareMcpConfig({
       githubToken: "test-token",
       owner: "test-owner",
@@ -560,16 +219,15 @@ describe("prepareMcpConfig", () => {
       branch: "test-branch",
       baseBranch: "main",
       allowedTools: [],
-      context: contextWithPermissions,
+      context: mockPRContext,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers.github_ci).toBeDefined();
     expect(parsed.mcpServers.github_ci.env.GITHUB_TOKEN).toBe("workflow-token");
     expect(parsed.mcpServers.github_ci.env.PR_NUMBER).toBe("456");
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
 
-    process.env.DEFAULT_WORKFLOW_TOKEN = oldEnv;
+    delete process.env.DEFAULT_WORKFLOW_TOKEN;
   });
 
   test("should not include github_ci server when context.isPR is false", async () => {
@@ -580,16 +238,14 @@ describe("prepareMcpConfig", () => {
       branch: "test-branch",
       baseBranch: "main",
       allowedTools: [],
-      context: mockContextWithSigning,
+      context: mockContext,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers.github_ci).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
   });
 
-  test("should not include github_ci server when workflow token is not present", async () => {
+  test("should not include github_ci server when DEFAULT_WORKFLOW_TOKEN is missing", async () => {
-    const oldTokenEnv = process.env.DEFAULT_WORKFLOW_TOKEN;
     delete process.env.DEFAULT_WORKFLOW_TOKEN;
 
     const result = await prepareMcpConfig({
@@ -599,73 +255,10 @@ describe("prepareMcpConfig", () => {
       branch: "test-branch",
       baseBranch: "main",
       allowedTools: [],
-      context: mockPRContextWithSigning,
+      context: mockPRContext,
     });
 
     const parsed = JSON.parse(result);
     expect(parsed.mcpServers.github_ci).not.toBeDefined();
-    expect(parsed.mcpServers.github_file_ops).toBeDefined();
-
-    process.env.DEFAULT_WORKFLOW_TOKEN = oldTokenEnv;
-  });
-
-  test("should include github_ci server when workflow token is present for PR context", async () => {
-    const oldTokenEnv = process.env.DEFAULT_WORKFLOW_TOKEN;
-    process.env.DEFAULT_WORKFLOW_TOKEN = "workflow-token";
-
-    const contextWithPermissions = {
-      ...mockPRContext,
-      inputs: {
-        ...mockPRContext.inputs,
-      },
-    };
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      allowedTools: [],
-      context: contextWithPermissions,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.mcpServers.github_ci).toBeDefined();
-    expect(parsed.mcpServers.github_ci.env.GITHUB_TOKEN).toBe("workflow-token");
-
-    process.env.DEFAULT_WORKFLOW_TOKEN = oldTokenEnv;
-  });
-
-  test("should warn when workflow token lacks actions:read permission", async () => {
-    const oldTokenEnv = process.env.DEFAULT_WORKFLOW_TOKEN;
-    process.env.DEFAULT_WORKFLOW_TOKEN = "invalid-token";
-
-    const contextWithPermissions = {
-      ...mockPRContext,
-      inputs: {
-        ...mockPRContext.inputs,
-      },
-    };
-
-    const result = await prepareMcpConfig({
-      githubToken: "test-token",
-      owner: "test-owner",
-      repo: "test-repo",
-      branch: "test-branch",
-      baseBranch: "main",
-      allowedTools: [],
-      context: contextWithPermissions,
-    });
-
-    const parsed = JSON.parse(result);
-    expect(parsed.mcpServers.github_ci).toBeDefined();
-    expect(consoleWarningSpy).toHaveBeenCalledWith(
-      expect.stringContaining(
-        "The github_ci MCP server requires 'actions: read' permission",
-      ),
-    );
-
-    process.env.DEFAULT_WORKFLOW_TOKEN = oldTokenEnv;
   });
 });

test/modes/agent.test.ts

@@ -104,6 +104,12 @@ describe("Agent Mode", () => {
       eventName: "workflow_dispatch",
     });
 
+    // Save original env vars and set test values
+    const originalHeadRef = process.env.GITHUB_HEAD_REF;
+    const originalRefName = process.env.GITHUB_REF_NAME;
+    delete process.env.GITHUB_HEAD_REF;
+    delete process.env.GITHUB_REF_NAME;
+
     // Set CLAUDE_ARGS environment variable
     process.env.CLAUDE_ARGS = "--model claude-sonnet-4 --max-turns 10";
 
@@ -120,12 +126,12 @@ describe("Agent Mode", () => {
     expect(callArgs[1]).toContain("--mcp-config");
     expect(callArgs[1]).toContain("--model claude-sonnet-4 --max-turns 10");
 
-    // Verify return structure
+    // Verify return structure - should use "main" as fallback when no env vars set
     expect(result).toEqual({
       commentId: undefined,
       branchInfo: {
-        baseBranch: "",
+        baseBranch: "main",
-        currentBranch: "",
+        currentBranch: "main",
         claudeBranch: undefined,
       },
       mcpConfig: expect.any(String),
@@ -133,6 +139,10 @@ describe("Agent Mode", () => {
 
     // Clean up
     delete process.env.CLAUDE_ARGS;
+    if (originalHeadRef !== undefined)
+      process.env.GITHUB_HEAD_REF = originalHeadRef;
+    if (originalRefName !== undefined)
+      process.env.GITHUB_REF_NAME = originalRefName;
   });
 
   test("prepare method creates prompt file with correct content", async () => {

test/modes/parse-tools.test.ts

@@ -0,0 +1,71 @@
+import { describe, test, expect } from "bun:test";
+import { parseAllowedTools } from "../../src/modes/agent/parse-tools";
+
+describe("parseAllowedTools", () => {
+  test("parses unquoted tools", () => {
+    const args = "--allowedTools mcp__github__*,mcp__github_comment__*";
+    expect(parseAllowedTools(args)).toEqual([
+      "mcp__github__*",
+      "mcp__github_comment__*",
+    ]);
+  });
+
+  test("parses double-quoted tools", () => {
+    const args = '--allowedTools "mcp__github__*,mcp__github_comment__*"';
+    expect(parseAllowedTools(args)).toEqual([
+      "mcp__github__*",
+      "mcp__github_comment__*",
+    ]);
+  });
+
+  test("parses single-quoted tools", () => {
+    const args = "--allowedTools 'mcp__github__*,mcp__github_comment__*'";
+    expect(parseAllowedTools(args)).toEqual([
+      "mcp__github__*",
+      "mcp__github_comment__*",
+    ]);
+  });
+
+  test("returns empty array when no allowedTools", () => {
+    const args = "--someOtherFlag value";
+    expect(parseAllowedTools(args)).toEqual([]);
+  });
+
+  test("handles empty string", () => {
+    expect(parseAllowedTools("")).toEqual([]);
+  });
+
+  test("handles duplicate --allowedTools flags", () => {
+    const args = "--allowedTools --allowedTools mcp__github__*";
+    // Should not match the first one since the value is another flag
+    expect(parseAllowedTools(args)).toEqual([]);
+  });
+
+  test("handles typo --alloedTools", () => {
+    const args = "--alloedTools mcp__github__*";
+    expect(parseAllowedTools(args)).toEqual([]);
+  });
+
+  test("handles multiple flags with allowedTools in middle", () => {
+    const args =
+      '--flag1 value1 --allowedTools "mcp__github__*" --flag2 value2';
+    expect(parseAllowedTools(args)).toEqual(["mcp__github__*"]);
+  });
+
+  test("trims whitespace from tool names", () => {
+    const args = "--allowedTools 'mcp__github__* , mcp__github_comment__* '";
+    expect(parseAllowedTools(args)).toEqual([
+      "mcp__github__*",
+      "mcp__github_comment__*",
+    ]);
+  });
+
+  test("handles tools with special characters", () => {
+    const args =
+      '--allowedTools "mcp__github__create_issue,mcp__github_comment__update"';
+    expect(parseAllowedTools(args)).toEqual([
+      "mcp__github__create_issue",
+      "mcp__github_comment__update",
+    ]);
+  });
+});

test/sanitizer.test.ts

@@ -7,6 +7,7 @@ import {
   normalizeHtmlEntities,
   sanitizeContent,
   stripHtmlComments,
+  redactGitHubTokens,
 } from "../src/github/utils/sanitizer";
 
 describe("stripInvisibleCharacters", () => {
@@ -242,6 +243,109 @@ describe("sanitizeContent", () => {
   });
 });
 
+describe("redactGitHubTokens", () => {
+  it("should redact personal access tokens (ghp_)", () => {
+    const token = "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";
+    expect(redactGitHubTokens(`Token: ${token}`)).toBe(
+      "Token: [REDACTED_GITHUB_TOKEN]",
+    );
+    expect(redactGitHubTokens(`Here's a token: ${token} in text`)).toBe(
+      "Here's a token: [REDACTED_GITHUB_TOKEN] in text",
+    );
+  });
+
+  it("should redact OAuth tokens (gho_)", () => {
+    const token = "gho_16C7e42F292c6912E7710c838347Ae178B4a";
+    expect(redactGitHubTokens(`OAuth: ${token}`)).toBe(
+      "OAuth: [REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should redact installation tokens (ghs_)", () => {
+    const token = "ghs_xz7yzju2SZjGPa0dUNMAx0SH4xDOCS31LXQW";
+    expect(redactGitHubTokens(`Install token: ${token}`)).toBe(
+      "Install token: [REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should redact refresh tokens (ghr_)", () => {
+    const token = "ghr_1B4a2e77838347a253e56d7b5253e7d11667";
+    expect(redactGitHubTokens(`Refresh: ${token}`)).toBe(
+      "Refresh: [REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should redact fine-grained tokens (github_pat_)", () => {
+    const token =
+      "github_pat_11ABCDEFG0example5of9_2nVwvsylpmOLboQwTPTLewDcE621dQ0AAaBBCCDDEEFFHH";
+    expect(redactGitHubTokens(`Fine-grained: ${token}`)).toBe(
+      "Fine-grained: [REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should handle tokens in code blocks", () => {
+    const content = `\`\`\`bash
+export GITHUB_TOKEN=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
+\`\`\``;
+    const expected = `\`\`\`bash
+export GITHUB_TOKEN=[REDACTED_GITHUB_TOKEN]
+\`\`\``;
+    expect(redactGitHubTokens(content)).toBe(expected);
+  });
+
+  it("should handle multiple tokens in one text", () => {
+    const content =
+      "Token 1: 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 and token 2: gho_16C7e42F292c6912E7710c838347Ae178B4a";
+    expect(redactGitHubTokens(content)).toBe(
+      "Token 1: [REDACTED_GITHUB_TOKEN] and token 2: [REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should handle tokens in URLs", () => {
+    const content =
+      "https://api.github.com/user?access_token=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";
+    expect(redactGitHubTokens(content)).toBe(
+      "https://api.github.com/user?access_token=[REDACTED_GITHUB_TOKEN]",
+    );
+  });
+
+  it("should not redact partial matches or invalid tokens", () => {
+    const content =
+      "This is not a token: ghp_short or gho_toolong1234567890123456789012345678901234567890";
+    expect(redactGitHubTokens(content)).toBe(content);
+  });
+
+  it("should preserve normal text", () => {
+    const content = "Normal text with no tokens";
+    expect(redactGitHubTokens(content)).toBe(content);
+  });
+
+  it("should handle edge cases", () => {
+    expect(redactGitHubTokens("")).toBe("");
+    expect(redactGitHubTokens("ghp_")).toBe("ghp_");
+    expect(redactGitHubTokens("github_pat_short")).toBe("github_pat_short");
+  });
+});
+
+describe("sanitizeContent with token redaction", () => {
+  it("should redact tokens as part of full sanitization", () => {
+    const content = `
+      <!-- Hidden comment with token: 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 -->
+      Here's some text with a token: gho_16C7e42F292c6912E7710c838347Ae178B4a
+      And invisible chars: test\u200Btoken
+    `;
+
+    const sanitized = sanitizeContent(content);
+
+    expect(sanitized).not.toContain("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");
+    expect(sanitized).not.toContain("gho_16C7e42F292c6912E7710c838347Ae178B4a");
+    expect(sanitized).not.toContain("<!-- Hidden comment");
+    expect(sanitized).not.toContain("\u200B");
+    expect(sanitized).toContain("[REDACTED_GITHUB_TOKEN]");
+    expect(sanitized).toContain("Here's some text with a token:");
+  });
+});
+
 describe("stripHtmlComments (legacy)", () => {
   it("should remove HTML comments", () => {
     expect(stripHtmlComments("Hello <!-- example -->World")).toBe(

undefined/claude-prompts/claude-prompt.txt

@@ -1 +0,0 @@
-Custom prompt content