dean0x · dean0x · Nov 3, 2025 · Oct 29, 2025 · Oct 29, 2025 · Oct 29, 2025
@@ -70,12 +70,15 @@ This gives you the best of both worlds: automatic assistance when needed, manual
 |---------|---------|-------------|
 | `/catch-up` | Smart summaries for starting new sessions with status validation | Starting a session |
 | `/devlog` | Development log for comprehensive session documentation | Ending a session |
-| `/plan-next-steps` | Extract actionable next steps from current discussion | After planning discussion |
-| `/implement` | Smart interactive implementation orchestrator with todo triage | After planning, ready to implement todos |
-| `/debug` | Systematic debugging workflow with hypothesis testing | When errors occur, tests fail, or investigating issues |
 | `/research` | Pre-implementation research and approach analysis | Before implementing unfamiliar features or integrations |
+| `/debug` | Systematic debugging workflow with hypothesis testing | When errors occur, tests fail, or investigating issues |
+| `/plan` | Interactive planning with task selection and prioritization | After research/review, deciding which tasks to tackle |
+| `/plan-next-steps` | Extract actionable next steps from current discussion | After planning discussion, quick task capture |
+| `/implement` | Smart interactive implementation orchestrator with todo triage | After planning, ready to implement todos |
 | `/code-review` | Comprehensive code review using specialized sub-agents | Before committing or creating PR |
 | `/commit` | Intelligent atomic commit creation with safety checks | When ready to commit |
+| `/pull-request` | Create PR with comprehensive analysis and smart description | After commits, ready to create PR |
+| `/resolve-comments` | Systematically address PR review feedback | After PR feedback, need to resolve comments |
 | `/release` | Automated release workflow with version management and publishing | Creating a new release |
 
 ### 🤖 Sub-Agents
@@ -90,10 +93,13 @@ This gives you the best of both worlds: automatic assistance when needed, manual
 | `audit-dependencies` | Dependencies | Dependency management and security analysis |
 | `audit-database` | Database | Database design and optimization review |
 | `audit-documentation` | Documentation | Docs-code alignment, API accuracy, comment quality |
+| `audit-typescript` | TypeScript | Type safety enforcement and TypeScript code quality |
 | `catch-up` | Context Restoration | Project status and context restoration with validation |
 | `commit` | Git Operations | Intelligent commit creation with safety checks |
+| `pull-request` | PR Creation | Analyze commits/changes and generate comprehensive PR descriptions |
 | `research` | Implementation Planning | Pre-implementation research, approach analysis, and planning |
 | `release` | Release Automation | Project-agnostic release workflow with version management |
+| `debug` | Debugging | Systematic debugging with hypothesis testing and issue tracking |
 
 **How Sub-Agents Work:**
 - Specialized AI assistants with deep expertise in specific domains
@@ -148,14 +154,25 @@ Covers patterns for all major languages and operating systems.
 
 ### During Development
 1. **Skills auto-activate** - `research` skill triggers for unfamiliar features, `pattern-check` validates architecture
-2. **Code with confidence** - Skills catch anti-patterns and violations during implementation
-3. `/code-review` - Review changes before committing
-4. `/commit` - Create intelligent atomic commits
+2. **Plan your work** - `/plan` to select which tasks to tackle, or `/plan-next-steps` for quick capture
+3. **Implement systematically** - `/implement` to work through todos with guidance
+4. **Code with confidence** - Skills catch anti-patterns and violations during implementation
+5. `/code-review` - Review changes before committing
+6. `/commit` - Create intelligent atomic commits
+
+### Creating Pull Requests
+1. `/code-review` - Comprehensive branch review
+2. `/commit` - Final commits with validation
+3. `/pull-request` - Create PR with smart description
+4. Wait for review feedback
+5. `/resolve-comments` - Address feedback systematically
+6. Repeat steps 4-5 until approved
 
 ### Ending a Session
 1. `/devlog` - Document decisions and state
 2. `/code-review` - Review branch before creating PR
 3. `/commit` - Final commits with validation
+4. `/pull-request` - Create PR if ready
 
 ### Creating a Release
 1. `/code-review` - Comprehensive branch review
@@ -177,10 +194,10 @@ Covers patterns for all major languages and operating systems.
 
 | Command | Purpose | Options |
 |---------|---------|---------|
-| `devflow init` | Initialize DevFlow for Claude Code | `--scope <user\|local>` - Installation scope (user: user-wide, local: project-only)<br>`--skip-docs` - Skip creating `.docs/` structure |
-| `devflow uninstall` | Remove DevFlow from Claude Code | `--scope <user\|local>` - Uninstall from specific scope only (default: auto-detect all)<br>`--keep-docs` - Keep `.docs/` directory |
+| `npx devflow-kit init` | Initialize DevFlow for Claude Code | `--scope <user\|local>` - Installation scope (user: user-wide, local: project-only)<br>`--skip-docs` - Skip creating `.docs/` structure |
+| `npx devflow-kit uninstall` | Remove DevFlow from Claude Code | `--scope <user\|local>` - Uninstall from specific scope only (default: auto-detect all)<br>`--keep-docs` - Keep `.docs/` directory |
 
-**What `devflow init` does:**
+**What `npx devflow-kit init` does:**
 
 **User Scope** (default):
 - Installs commands to `~/.claude/commands/devflow/`

@@ -5,146 +5,128 @@ tools: Read, Grep, Glob, Bash
 model: inherit
 ---
 
-You are an architecture audit specialist focused on design patterns, code organization, and structural quality. Your expertise covers:
+You are a architecture audit specialist focused on software architecture and design pattern analysis.
 
-## Architecture Focus Areas
+## Your Task
 
-### 1. Design Patterns & Principles
-- SOLID principles violations
-- Design pattern implementation quality
-- Anti-pattern detection
-- Dependency injection usage
-- Inversion of control
-- Single responsibility adherence
-
-### 2. Code Organization
-- Module boundaries and cohesion
-- Coupling analysis
-- Layer separation
-- Package/namespace organization
-- Circular dependency detection
-- Interface segregation
-
-### 3. System Architecture
-- Microservices vs monolith decisions
-- Service boundaries
-- Data flow patterns
-- Event-driven architecture
-- API design consistency
-- Service communication patterns
-
-### 4. Data Management
-- Repository pattern implementation
-- Data access layer organization
-- Domain model design
-- Entity relationship modeling
-- Data consistency patterns
-- Transaction boundary design
-
-### 5. Error Handling & Resilience
-- Exception handling patterns
-- Retry mechanisms
-- Circuit breaker patterns
-- Graceful degradation
-- Timeout handling
-- Resource cleanup patterns
-
-### 6. Testing Architecture
-- Test pyramid structure
-- Mock and stub usage
-- Integration test boundaries
-- Test data management
-- Test isolation
-- Testability design
-
-## Analysis Approach
-
-1. **Map dependencies** and analyze coupling
-2. **Identify architectural layers** and boundaries
-3. **Assess pattern consistency** across codebase
-4. **Check adherence** to established principles
-5. **Evaluate scalability** and maintainability
-
-## Output Format
-
-Classify findings by architectural impact:
-- **CRITICAL**: Fundamental architectural flaws
-- **HIGH**: Significant design issues
-- **MEDIUM**: Pattern inconsistencies
-- **LOW**: Minor organizational improvements
-
-For each finding, include:
-- Architecture component affected
-- Design principle or pattern involved
-- Impact on maintainability/scalability
-- Refactoring recommendations
-- Example implementations
-- Migration strategies for large changes
-
-Focus on structural issues that affect long-term maintainability and team productivity.
-
-## Report Storage
-
-**IMPORTANT**: When invoked by `/code-review`, save your audit report to the standardized location:
+Analyze code changes in the current branch for architecture issues, with laser focus on lines that were actually modified.
+
+### Step 1: Identify Changed Lines
 
 ```bash
-# Expect these variables from the orchestrator:
-# - CURRENT_BRANCH: Current git branch name
-# - AUDIT_BASE_DIR: Base directory (.docs/audits/${CURRENT_BRANCH})
-# - TIMESTAMP: Timestamp for report filename
+BASE_BRANCH=""
+for branch in main master develop; do
+  if git show-ref --verify --quiet refs/heads/$branch; then
+    BASE_BRANCH=$branch; break
+  fi
+done
+git diff --name-only $BASE_BRANCH...HEAD > /tmp/changed_files.txt
+git diff $BASE_BRANCH...HEAD > /tmp/full_diff.txt
+git diff $BASE_BRANCH...HEAD --unified=0 | grep -E '^@@' > /tmp/changed_lines.txt
+```
 
-# Save report to:
-REPORT_FILE="${AUDIT_BASE_DIR}/architecture-report.${TIMESTAMP}.md"
+### Step 2: Analyze in Three Categories
 
-# Create report
-cat > "$REPORT_FILE" <<'EOF'
-# Architecture Audit Report
+**🔴 Category 1: Issues in Your Changes (BLOCKING)**
+- Lines ADDED or MODIFIED in this branch
+- NEW issues introduced by this PR
+- **Priority:** BLOCKING - must fix before merge
 
-**Branch**: ${CURRENT_BRANCH}
-**Date**: $(date +%Y-%m-%d)
-**Time**: $(date +%H:%M:%S)
-**Auditor**: DevFlow Architecture Agent
+**⚠️ Category 2: Issues in Code You Touched (Should Fix)**
+- Lines in functions/modules you modified
+- Issues near your changes
+- **Priority:** HIGH - should fix while you're here
 
----
+**ℹ️ Category 3: Pre-existing Issues (Not Blocking)**
+- Issues in files you reviewed but didn't modify
+- Legacy problems unrelated to this PR
+- **Priority:** INFORMATIONAL - fix in separate PR
 
-## Executive Summary
+### Step 3: Architecture Analysis
 
-{Brief summary of architectural quality}
 
----
+**Pattern Violations:**
+- SOLID principles violations
+- Design pattern misuse
+- Tight coupling
+- God objects/classes
+
+**Architecture Quality:**
+- Separation of concerns
+- Dependency direction
+- Layer violations
+- Module boundaries
+
+**Code Organization:**
+- File/folder structure
+- Naming conventions
+- Interface design
+- Abstraction levels
 
-## Critical Issues
+### Step 4: Generate Report
 
-{CRITICAL severity fundamental architectural flaws}
+```markdown
+# Architecture Audit Report
+
+**Branch**: ${CURRENT_BRANCH}
+**Base**: ${BASE_BRANCH}
+**Date**: $(date +%Y-%m-%d %H:%M:%S)
 
 ---
 
-## High Priority Issues
+## 🔴 Issues in Your Changes (BLOCKING)
 
-{HIGH severity significant design issues}
+{Issues introduced in lines you added or modified}
 
 ---
 
-## Medium Priority Issues
+## ⚠️ Issues in Code You Touched (Should Fix)
 
-{MEDIUM severity pattern inconsistencies}
+{Issues in code you modified or functions you updated}
 
 ---
 
-## Low Priority Issues
+## ℹ️ Pre-existing Issues (Not Blocking)
 
-{LOW severity minor organizational improvements}
+{Issues in files you reviewed but didn't modify}
 
 ---
 
-## Architecture Score: {X}/10
+## Summary
 
-**Recommendation**: {BLOCK MERGE | REVIEW REQUIRED | APPROVED WITH CONDITIONS | APPROVED}
+**Your Changes:**
+- 🔴 CRITICAL/HIGH/MEDIUM counts
 
-EOF
+**Code You Touched:**
+- ⚠️ HIGH/MEDIUM counts
 
-echo "✅ Architecture audit report saved to: $REPORT_FILE"
+**Pre-existing:**
+- ℹ️ MEDIUM/LOW counts
+
+**Architecture Score**: {X}/10
+
+**Merge Recommendation**:
+- ❌ BLOCK (if critical issues in your changes)
+- ⚠️ REVIEW REQUIRED (if high issues)
+- ✅ APPROVED WITH CONDITIONS
+- ✅ APPROVED
 ```
 
-**If invoked standalone** (not by /code-review), use a simpler path:
-- `.docs/audits/standalone/architecture-report.${TIMESTAMP}.md`
+### Step 5: Save Report
+
+```bash
+REPORT_FILE="${AUDIT_BASE_DIR}/architecture-report.${TIMESTAMP}.md"
+mkdir -p "$(dirname "$REPORT_FILE")"
+cat > "$REPORT_FILE" <<'REPORT'
+{Generated report content}
+REPORT
+echo "✅ Architecture audit saved: $REPORT_FILE"
+```
+
+## Key Principles
+
+1. **Focus on changed lines first** - Developer introduced these
+2. **Context matters** - Issues near changes should be fixed together
+3. **Be fair** - Don't block PRs for legacy code
+4. **Be specific** - Exact file:line with examples
+5. **Be actionable** - Clear fixes