SuperClaude/docs/Reference/integration-patterns.md
kazuki nakai 050d5ea2ab
refactor: PEP8 compliance - directory rename and code formatting (#425)
* fix(orchestration): add WebFetch auto-trigger for infrastructure configuration

Problem: Infrastructure configuration changes (e.g., Traefik port settings)
were being made based on assumptions without consulting official documentation,
violating the 'Evidence > assumptions' principle in PRINCIPLES.md.

Solution:
- Added Infrastructure Configuration Validation section to MODE_Orchestration.md
- Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.)
- Enforces MODE_DeepResearch activation for investigation
- BLOCKS assumption-based configuration changes

Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default)

This prevents production outages from infrastructure misconfiguration by ensuring
all technical recommendations are backed by official documentation.

* feat: Add PM Agent (Project Manager Agent) for seamless orchestration

Introduces PM Agent as the default orchestration layer that coordinates
all sub-agents and manages workflows automatically.

Key Features:
- Default orchestration: All user interactions handled by PM Agent
- Auto-delegation: Intelligent sub-agent selection based on task analysis
- Docker Gateway integration: Zero-token baseline with dynamic MCP loading
- Self-improvement loop: Automatic documentation of patterns and mistakes
- Optional override: Users can specify sub-agents explicitly if desired

Architecture:
- Agent spec: SuperClaude/Agents/pm-agent.md
- Command: SuperClaude/Commands/pm.md
- Updated docs: README.md (15→16 agents), agents.md (new Orchestration category)

User Experience:
- Default: PM Agent handles everything (seamless, no manual routing)
- Optional: Explicit --agent flag for direct sub-agent access
- Both modes available simultaneously (no user downside)

Implementation Status:
-  Specification complete
-  Documentation complete
-  Prototype implementation needed
-  Docker Gateway integration needed
-  Testing and validation needed

Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration)

* feat: Add Agent Orchestration rules for PM Agent default activation

Implements PM Agent as the default orchestration layer in RULES.md.

Key Changes:
- New 'Agent Orchestration' section (CRITICAL priority)
- PM Agent receives ALL user requests by default
- Manual override with @agent-[name] bypasses PM Agent
- Agent Selection Priority clearly defined:
  1. Manual override → Direct routing
  2. Default → PM Agent → Auto-delegation
  3. Delegation based on keywords, file types, complexity, context

User Experience:
- Default: PM Agent handles everything (seamless)
- Override: @agent-[name] for direct specialist access
- Transparent: PM Agent reports delegation decisions

This establishes PM Agent as the orchestration layer while
respecting existing auto-activation patterns and manual overrides.

Next Steps:
- Local testing in agiletec project
- Iteration based on actual behavior
- Documentation updates as needed

* refactor(pm-agent): redesign as self-improvement meta-layer

Problem Resolution:
PM Agent's initial design competed with existing auto-activation for task routing,
creating confusion about orchestration responsibilities and adding unnecessary complexity.

Design Change:
Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents
complete tasks, focusing on:
- Post-implementation documentation and pattern recording
- Immediate mistake analysis with prevention checklists
- Monthly documentation maintenance and noise reduction
- Pattern extraction and knowledge synthesis

Two-Layer Orchestration System:
1. Task Execution Layer: Existing auto-activation handles task routing (unchanged)
2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new)

Files Modified:
- SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design
  - Category: orchestration → meta
  - Triggers: All user interactions → Post-implementation, mistakes, monthly
  - Behavioral Mindset: Continuous learning system
  - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE

- SuperClaude/Core/RULES.md: Agent Orchestration section updated
  - Split into Task Execution Layer + Self-Improvement Layer
  - Added orchestration flow diagram
  - Clarified PM Agent activates AFTER task completion

- README.md: Updated PM Agent description
  - "orchestrates all interactions" → "ensures continuous learning"

- Docs/User-Guide/agents.md: PM Agent section rewritten
  - Section: Orchestration Agent → Meta-Layer Agent
  - Expertise: Project orchestration → Self-improvement workflow executor
  - Examples: Task coordination → Post-implementation documentation

- PR_DOCUMENTATION.md: Comprehensive PR documentation added
  - Summary, motivation, changes, testing, breaking changes
  - Two-layer orchestration system diagram
  - Verification checklist

Integration Validated:
Tested with agiletec project's self-improvement-workflow.md:
 PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases
 Complements (not competes with) existing workflow
 agiletec workflow defines WHAT, PM Agent defines WHO executes it

Breaking Changes: None
- Existing auto-activation continues unchanged
- Specialist agents unaffected
- User workflows remain the same
- New capability: Automatic documentation and knowledge maintenance

Value Proposition:
Transforms SuperClaude into a continuously learning system that accumulates
knowledge, prevents recurring mistakes, and maintains fresh documentation
without manual intervention.

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

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

* docs: add Claude Code conversation history management research

Research covering .jsonl file structure, performance impact, and retention policies.

Content:
- Claude Code .jsonl file format and message types
- Performance issues from GitHub (memory leaks, conversation compaction)
- Retention policies (consumer vs enterprise)
- Rotation recommendations based on actual data
- File history snapshot tracking mechanics

Source: Moved from agiletec project (research applicable to all Claude Code projects)

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

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

* feat: add Development documentation structure

Phase 1: Documentation Structure complete

- Add Docs/Development/ directory for development documentation
- Add ARCHITECTURE.md - System architecture with PM Agent meta-layer
- Add ROADMAP.md - 5-phase development plan with checkboxes
- Add TASKS.md - Daily task tracking with progress indicators
- Add PROJECT_STATUS.md - Current status dashboard and metrics
- Add pm-agent-integration.md - Implementation guide for PM Agent mode

This establishes comprehensive documentation foundation for:
- System architecture understanding
- Development planning and tracking
- Implementation guidance
- Progress visibility

Related: #pm-agent-mode #documentation #phase-1

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

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

* feat: PM Agent session lifecycle and PDCA implementation

Phase 2: PM Agent Mode Integration (Design Phase)

Commands/pm.md updates:
- Add "Always-Active Foundation Layer" concept
- Add Session Lifecycle (Session Start/During Work/Session End)
- Add PDCA Cycle (Plan/Do/Check/Act) automation
- Add Serena MCP Memory Integration (list/read/write_memory)
- Document auto-activation triggers

Agents/pm-agent.md updates:
- Add Session Start Protocol (MANDATORY auto-activation)
- Add During Work PDCA Cycle with example workflows
- Add Session End Protocol with state preservation
- Add PDCA Self-Evaluation Pattern
- Add Documentation Strategy (temp → patterns/mistakes)
- Add Memory Operations Reference

Key Features:
- Session start auto-activation for context restoration
- 30-minute checkpoint saves during work
- Self-evaluation with think_about_* operations
- Systematic documentation lifecycle
- Knowledge evolution to CLAUDE.md

Implementation Status:
-  Design complete (Commands/pm.md, Agents/pm-agent.md)
-  Implementation pending (Core components)
-  Serena MCP integration pending

Salvaged from mistaken development in ~/.claude directory

Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2

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

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

* fix: disable Serena MCP auto-browser launch

Disable web dashboard and GUI log window auto-launch in Serena MCP server
to prevent intrusive browser popups on startup. Users can still manually
access the dashboard at http://localhost:24282/dashboard/ if needed.

Changes:
- Add CLI flags to Serena run command:
  - --enable-web-dashboard false
  - --enable-gui-log-window false
- Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml)
- Aligns with AIRIS MCP Gateway integration approach

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

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

* refactor: rename directories to lowercase for PEP8 compliance

- Rename superclaude/Agents -> superclaude/agents
- Rename superclaude/Commands -> superclaude/commands
- Rename superclaude/Core -> superclaude/core
- Rename superclaude/Examples -> superclaude/examples
- Rename superclaude/MCP -> superclaude/mcp
- Rename superclaude/Modes -> superclaude/modes

This change follows Python PEP8 naming conventions for package directories.

* style: fix PEP8 violations and update package name to lowercase

Changes:
- Format all Python files with black (43 files reformatted)
- Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml
- Fix import statements to use lowercase package name
- Add missing imports (timedelta, __version__)
- Remove old SuperClaude.egg-info directory

PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit).

* docs: add PM Agent development documentation

Add comprehensive PM Agent development documentation:
- PM Agent ideal workflow (7-phase autonomous cycle)
- Project structure understanding (Git vs installed environment)
- Installation flow understanding (CommandsComponent behavior)
- Task management system (current-tasks.md)

Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles

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

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

* feat(pm-agent): add self-correcting execution and warning investigation culture

## Changes

### superclaude/commands/pm.md
- Add "Self-Correcting Execution" section with root cause analysis protocol
- Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal
- Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute
- Document anti-patterns (retry without understanding) and correct patterns (research-first)

### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md
- Add PDCA workflow hypothesis document for PM Agent autonomous enhancement

## Rationale

PM Agent must never retry failed operations without understanding root causes.
All warnings and errors require investigation via context7/WebFetch/documentation
to ensure production-quality code and prevent technical debt accumulation.

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

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

* feat(installer): add airis-mcp-gateway MCP server option

## Changes

- Add airis-mcp-gateway to MCP server options in installer
- Configuration: GitHub-based installation via uvx
- Repository: https://github.com/oraios/airis-mcp-gateway
- Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading

## Implementation

Added to setup/components/mcp.py self.mcp_servers dictionary with:
- install_method: github
- install_command: uvx test installation
- run_command: uvx runtime execution
- required: False (optional server)

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

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

---------

Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local>
Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 08:47:09 +05:30

319 lines
8.2 KiB
Markdown

# SuperClaude Integration Patterns Collection
**Status**: ✅ **Status: Current** - Context patterns for framework integration and tool coordination.
**Context Integration Guide**: Patterns for using SuperClaude commands effectively with different frameworks and tools. Remember: SuperClaude provides context to Claude Code - all actual work is done by Claude.
## Overview and Usage Guide
**Purpose**: Effective patterns for using SuperClaude context with various development frameworks and tools.
**What This Is**: Command combinations and flag patterns that work well for specific technologies
**What This Isn't**: Performance optimization or parallel execution (no code runs)
**Key Principle**: SuperClaude tells Claude Code WHAT to do and HOW to think about it. Claude Code does the actual work.
## Framework Context Patterns
### React Development Patterns
```bash
# React development with appropriate context
/sc:implement "React 18 application with TypeScript" --c7
# Context7 MCP can provide React documentation if available
# Magic MCP can help with UI components if configured
# What Actually Happens:
# 1. Claude reads implement.md for implementation patterns
# 2. --c7 flag suggests using Context7 MCP for documentation
# 3. Claude generates React code based on these contexts
# Component development pattern
@agent-frontend-architect "design component architecture"
/sc:implement "reusable component library"
# Testing pattern for React
/sc:test --focus react
# Claude will suggest React Testing Library patterns
```
### Node.js Backend Patterns
```bash
# Node.js backend development patterns
/sc:implement "Express.js API with TypeScript" --c7
# Claude will create Express API following Node.js patterns
# What This Means:
# - Claude reads context about backend patterns
# - Suggests appropriate middleware and structure
# - NOT running or optimizing any code
# Database integration pattern
/sc:implement "database models with Prisma"
@agent-backend-architect "review database schema"
# API testing pattern
/sc:test --focus api
# Claude suggests API testing approaches
```
### Python Development Patterns
```bash
# Python web development
/sc:implement "FastAPI application" --c7
@agent-python-expert "review implementation"
# What Happens:
# - Claude uses Python-specific context
# - Follows FastAPI patterns from context
# - Generates code (doesn't run it)
# Data science context
/sc:implement "data analysis pipeline"
@agent-python-expert "optimize pandas operations"
# Claude provides optimization suggestions (not actual optimization)
# Testing patterns
/sc:test --focus python
# Claude suggests pytest patterns
```
### Full-Stack Development Patterns
```bash
# Full-stack application pattern
/sc:brainstorm "full-stack application architecture"
@agent-system-architect "design system components"
# Frontend implementation
/sc:implement "React frontend with TypeScript"
@agent-frontend-architect "review component structure"
# Backend implementation
/sc:implement "Node.js API with authentication"
@agent-backend-architect "review API design"
# Integration
/sc:implement "connect frontend to backend API"
```
## Tool Coordination Patterns
### Using MCP Servers Effectively
```bash
# Context7 for documentation
/sc:explain "React hooks" --c7
# If Context7 is configured, it may fetch React docs
# Sequential for complex reasoning
/sc:troubleshoot "complex bug" --seq
# Sequential MCP helps with structured problem-solving
# Magic for UI components
/sc:implement "UI components" --magic
# Magic MCP can help generate modern UI patterns
# No MCP for simple tasks
/sc:implement "utility function" --no-mcp
# Uses only Claude's built-in knowledge
```
### Agent and Command Combinations
```bash
# Security-focused development
@agent-security "review authentication requirements"
/sc:implement "secure authentication system"
/sc:analyze --focus security
# Quality-focused workflow
/sc:implement "new feature"
@agent-quality-engineer "review code quality"
/sc:test --focus quality
# Architecture-focused approach
@agent-system-architect "design microservices"
/sc:design "service boundaries"
/sc:implement "service communication"
```
## Common Integration Patterns
### API Development Pattern
```bash
# Step 1: Design
/sc:design "REST API structure"
# Step 2: Implementation
/sc:implement "API endpoints with validation"
# Step 3: Documentation
/sc:document --type api
# Step 4: Testing
/sc:test --focus api
```
### Database Integration Pattern
```bash
# Schema design
@agent-backend-architect "design database schema"
# Model implementation
/sc:implement "database models"
# Migration creation
/sc:implement "database migrations"
# Query optimization suggestions
@agent-backend-architect "suggest query optimizations"
# Note: Claude suggests optimizations, doesn't actually optimize
```
### Testing Strategy Pattern
```bash
# Test planning
/sc:design "testing strategy"
# Unit tests
/sc:test --type unit
# Integration tests
/sc:test --type integration
# E2E test suggestions
/sc:test --type e2e
# Claude provides test code, not execution
```
## Technology-Specific Patterns
### React + TypeScript Pattern
```bash
# Project setup guidance
/sc:implement "React TypeScript project structure"
# Component development
/sc:implement "TypeScript React components with props validation"
# State management
@agent-frontend-architect "recommend state management approach"
/sc:implement "state management with Zustand/Redux"
# Testing
/sc:test --focus react --type unit
```
### Python FastAPI Pattern
```bash
# API structure
/sc:implement "FastAPI project structure"
# Endpoint development
@agent-python-expert "implement async endpoints"
# Database integration
/sc:implement "SQLAlchemy models with Alembic"
# Testing
/sc:test --focus python --type integration
```
### Node.js Microservices Pattern
```bash
# Architecture design
@agent-system-architect "design microservices architecture"
# Service implementation
/sc:implement "user service with Express"
/sc:implement "auth service with JWT"
# Inter-service communication
/sc:implement "service communication patterns"
# Testing approach
/sc:test --focus microservices
```
## Troubleshooting Patterns
### Debugging Workflow
```bash
# Problem analysis
/sc:troubleshoot "describe the issue"
# Root cause investigation
@agent-root-cause-analyst "analyze symptoms"
# Solution implementation
/sc:implement "fix based on analysis"
# Verification
/sc:test --validate
```
### Code Review Pattern
```bash
# Code analysis
/sc:analyze code/ --focus quality
# Security review
@agent-security "review for vulnerabilities"
# Performance review
@agent-performance-engineer "suggest improvements"
# Note: Suggestions only, no actual performance measurement
# Implementation of improvements
/sc:improve code/ --fix
```
## Important Clarifications
### What These Patterns DO
- ✅ Provide structured approaches to development tasks
- ✅ Combine commands and agents effectively
- ✅ Suggest appropriate tools and frameworks
- ✅ Guide Claude to generate better code
### What These Patterns DON'T DO
- ❌ Execute code or measure performance
- ❌ Run tests or deploy applications
- ❌ Optimize actual execution speed
- ❌ Provide real monitoring or metrics
- ❌ Coordinate parallel processes (everything is sequential text)
## Best Practices
### Effective Pattern Usage
1. **Start with context**: Use `/sc:load` to establish project understanding
2. **Layer expertise**: Combine general commands with specific agents
3. **Focus appropriately**: Use `--focus` flags for targeted results
4. **Manage scope**: Work on specific modules rather than entire codebases
5. **Document decisions**: Use `/sc:save` to create summaries
### Pattern Selection
- **Simple tasks**: Use basic commands without MCP
- **Complex tasks**: Add appropriate agents and MCP servers
- **Security-critical**: Always include `@agent-security`
- **UI development**: Consider `--magic` flag if configured
- **Documentation needs**: Use `--c7` for framework docs
## Summary
These integration patterns show how to combine SuperClaude commands, agents, and flags effectively for different development scenarios. Remember that all patterns are about providing better context to Claude Code - the actual code generation, not execution, is what Claude does based on these contexts.