Ensure all agent executions wait for results before proceeding.
Modified 20 workflow command files with 32 Task call updates.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Dashboards use fetch() API which doesn't work with file:// protocol due to
browser CORS restrictions. Now starts Python HTTP server for proper access.
- review-module-cycle: port 8765
- review-session-cycle: port 8765
- review-fix: port 8766 (different port for concurrent use)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Move specific JSON structure requirements from cli-explore-agent (keep generic)
to review-*-cycle.md prompts. Key requirements now inline in prompts:
- Root must be array [{}] not object {}
- analysis_timestamp field (not timestamp/analyzed_at)
- Flat summary structure (not nested by_severity)
- Lowercase severity/id values
- Correct field names (snippet not code_snippet, impact not exploit_scenario)
- Introduced a new command `/workflow:review-session-cycle` for session-based code reviews across 7 dimensions.
- Implemented hybrid parallel-iterative execution to enhance review efficiency and coverage.
- Added detailed documentation outlining command usage, execution flow, and agent roles.
- Configured specialized dimensions with priority-based allocation and defined severity assessment criteria.
- Established a robust aggregation logic for identifying cross-cutting concerns and critical findings.
- Enabled real-time progress tracking through an interactive HTML dashboard.
- Included mechanisms for deep-dive analysis and remediation planning for critical issues.
