refactor: Update all codex commands to use -s danger-full-access and correct syntax

- Move -s parameter to end of command: codex --full-auto exec "..." -s danger-full-access
- Change default sandbox mode from workspace-write to danger-full-access
- Add missing --full-auto parameter to commands requiring autonomous development
- Add missing exec parameter to all codex commands
- Add missing -s danger-full-access parameter to multi-line commands
- Update all documentation and examples to use consistent syntax
- Fix CLAUDE.md detection functionality in detect_changed_modules.sh script

Files updated:
- Core configuration: CLAUDE.md, RELEASE_NOTES_v1.3.0.md
- Documentation: tools-implementation-guide.md, intelligent-tools-strategy.md
- Command files: All .claude/commands/codex/*.md and workflow/*.md files
- Agent templates: action-planning-agent.md
- Scripts: detect_changed_modules.sh

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

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

.claude/commands/workflow/execute.md

@@ -113,7 +113,7 @@ Task(subagent_type="code-developer",
      Output: pattern_analysis
 
      Step 3 (implement): Implement JWT based on analysis
-     Command: codex -s workspace-write --full-auto exec 'Implement JWT using analysis: [pattern_analysis] and context: [dependency_context]'
+     Command: codex --full-auto exec 'Implement JWT using analysis: [pattern_analysis] and context: [dependency_context]' -s danger-full-access
 
      Session Context:
      - Workflow Directory: .workflow/WFS-user-auth/