Enable claude reviews. (#27)

At least... trying to. Using the example from
https://github.com/anthropics/claude-code-action/blob/main/examples/pr-review-comprehensive.yml

Author: joce

.github/workflows/claude.yml

@@ -0,0 +1,70 @@
+name: PR Review with Progress Tracking
+
+# This example demonstrates how to use the track_progress feature to get
+# visual progress tracking for PR reviews, similar to v0.x agent mode.
+
+on:
+  pull_request:
+    types: [opened, synchronize, ready_for_review, reopened]
+
+jobs:
+  review-with-tracking:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 1
+
+      - name: PR Review with Progress Tracking
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # Enable progress tracking
+          track_progress: true
+
+          show_full_output: true
+
+          # Your custom review instructions
+          prompt: |
+            REPO: ${{ github.repository }}
+            PR NUMBER: ${{ github.event.pull_request.number }}
+
+            Perform a comprehensive code review with the following focus areas:
+
+            1. **Code Quality**
+               - Clean code principles and best practices
+               - Proper error handling and edge cases
+               - Code readability and maintainability
+
+            2. **Security**
+               - Check for potential security vulnerabilities
+               - Validate input sanitization
+               - Review authentication/authorization logic
+
+            3. **Performance**
+               - Identify potential performance bottlenecks
+               - Review database queries for efficiency
+               - Check for memory leaks or resource issues
+
+            4. **Testing**
+               - Verify adequate test coverage
+               - Review test quality and edge cases
+               - Check for missing test scenarios
+
+            5. **Documentation**
+               - Ensure code is properly documented
+               - Verify README updates for new features
+               - Check API documentation accuracy
+
+            Provide detailed feedback using inline comments for specific issues.
+            Use top-level comments for general observations or praise.
+
+          # Tools for comprehensive PR review
+          claude_args: |
+            --allowedTools "mcp__github_inline_comment__create_inline_comment,Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*)"

AGENTS.md

@@ -1,18 +1,23 @@
 # Cursor AI Rules for the Doubloon Project (Python Textual TUI)
 
+## PRIME DIRECTIVES
+
+- **MUST NEVER BE OBSEQUIOUS OR SYCOPHANTIC**
+- **MUST NEVER LIE OR DECEIVE: TRUTH IS PARAMOUNT**
+
 ## General Guidelines
 
 - You are an expert Python developer with extensive experience in building text-based user interfaces (TUIs) using the Textual framework.
 - You MUST adhere to best practices in Python programming, including code readability, maintainability, and performance.
 - You MUST follow the specific coding standards and guidelines outlined in this document.
+- You MUST always write **elegant and beautiful code** and strive to be as **concise and parsimonious** as possible.
 - You MUST write clear, concise, and informative docstrings for all public classes, functions, and methods.
 - You MUST write comprehensive unit tests using pytest to ensure code quality and reliability.
 - You MUST follow the principles of clean code and software design patterns.
 - You MUST prioritize user experience in the TUI design, ensuring intuitive navigation and responsiveness.
 - You MUST communicate clearly and effectively, providing explanations and justifications for your code decisions.
 - You MUST be proactive in identifying potential issues and suggesting improvements.
 - You MUST be collaborative and open to feedback from other developers.
-- **MUST NEVER BE OBSEQUIOUS OR SYCOPHANTIC**
 
 ## Technology Stack
 
@@ -27,6 +32,8 @@ Run tests and linters using `uv run <command>`.
 
 If you need to run python directly, use `uv run python <args>` to ensure the correct environment is used.
 
+IMPORTANT: Whenever you run a uv command, you need to set the UV_CACHE_DIR pointing to the local `.uv_cache` directory of the project. This is due to an issue out of our control.
+
 ## Project Structure and Architecture
 
 ### Textual TUI Integration

CLAUDE.md

@@ -1 +1 @@
-@AGENTS.md
+Follow rules from @AGENTS.md