* 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>
7.9 KiB
SuperClaude Verification and Troubleshooting Guide
Overview
This guide covers how to verify your SuperClaude installation and troubleshoot common issues with context files and configurations.
Important: SuperClaude is a collection of context files, not executable software. This guide focuses on verifying context files are properly installed and accessible to Claude Code.
Table of Contents
- Installation Verification
- Context File Verification
- MCP Server Verification
- Common Issues
- Troubleshooting Commands
Installation Verification
Check Installation Status
# Verify SuperClaude installation system is available
python3 -m SuperClaude --version
# Expected: SuperClaude Framework installation help
# Verify Claude Code CLI integration
claude --version
# Expected: Claude Code version info
# Check if context files were installed
ls ~/.claude/
# Expected: CLAUDE.md, FLAGS.md, RULES.md, agents/, commands/, modes/
# Verify main context file
head ~/.claude/CLAUDE.md
# Expected: Should show import statements
Verify Directory Structure
# Check all directories exist
for dir in agents commands modes; do
if [ -d ~/.claude/$dir ]; then
echo "✅ $dir directory exists"
ls ~/.claude/$dir | wc -l
else
echo "❌ $dir directory missing"
fi
done
Count Installed Components
# Should have 14 agents
ls ~/.claude/agents/*.md | wc -l
# Should have 21 commands
ls ~/.claude/commands/*.md | wc -l
# Should have 5 modes
ls ~/.claude/modes/*.md | wc -l
Context File Verification
Verify Core Files
# Check core context files exist
for file in CLAUDE.md FLAGS.md RULES.md PRINCIPLES.md; do
if [ -f ~/.claude/$file ]; then
echo "✅ $file exists ($(wc -l < ~/.claude/$file) lines)"
else
echo "❌ $file missing"
fi
done
Verify Import System
# Check CLAUDE.md has correct imports
grep "@import" ~/.claude/CLAUDE.md
# Expected output:
# @import commands/*.md
# @import agents/*.md
# @import modes/*.md
# @import FLAGS.md
# @import RULES.md
# @import PRINCIPLES.md
Check File Integrity
# Verify files are readable text files
file ~/.claude/CLAUDE.md
# Expected: ASCII text or UTF-8 text
# Check for corruption
for file in ~/.claude/**/*.md; do
if file "$file" | grep -q "text"; then
echo "✅ $file is valid text"
else
echo "❌ $file may be corrupted"
fi
done
MCP Server Verification
Check MCP Configuration
# Verify .claude.json exists
if [ -f ~/.claude.json ]; then
echo "✅ MCP configuration file exists"
# Check which servers are configured
grep -o '"[^"]*":' ~/.claude.json | grep -v mcpServers
else
echo "❌ No MCP configuration found"
fi
Test MCP Server Availability
# Check if Node.js is available (required for MCP)
node --version
# Expected: v16.0.0 or higher
# Check if npx is available
npx --version
# Expected: Version number
# Test Context7 MCP (if configured)
npx -y @upstash/context7-mcp@latest --help 2>/dev/null && echo "✅ Context7 available" || echo "❌ Context7 not available"
Common Issues
Issue: Commands Not Working
Symptom: /sc: context triggers don't produce expected Claude Code behavior
Verification:
# Check if command file exists
ls ~/.claude/commands/implement.md
# If missing, reinstall SuperClaude
# Verify file content
head -20 ~/.claude/commands/implement.md
# Should show command metadata and instructions
Solution:
# Reinstall commands component
PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components commands --force
Issue: Agents Not Activating
Symptom: @agent- invocations don't work in Claude Code
Verification:
# List all agents
ls ~/.claude/agents/
# Check specific agent
cat ~/.claude/agents/python-expert.md | head -20
Solution:
# Reinstall agents
PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components agents --force
Issue: Context Not Loading
Symptom: Claude Code doesn't seem to read SuperClaude context
Verification:
# Check CLAUDE.md is in correct location
ls -la ~/.claude/CLAUDE.md
# Verify Claude Code can access the directory
# In Claude Code, check if context is loading properly
Solution:
- Restart Claude Code
- Ensure you're in a project directory
- Check file permissions:
chmod 644 ~/.claude/*.md
Issue: MCP Servers Not Working
Symptom: MCP features unavailable
Verification:
# Check Node.js installation
which node
# Verify .claude.json syntax
python3 -c "import json; json.load(open('$HOME/.claude.json'))" && echo "✅ Valid JSON" || echo "❌ Invalid JSON"
Solution:
# Install Node.js if missing
# Ubuntu: sudo apt install nodejs npm
# macOS: brew install node
# Windows: Download from nodejs.org
# Fix JSON syntax if invalid
PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install --components mcp --force
Troubleshooting Commands
Quick Diagnostic
#!/bin/bash
# SuperClaude Quick Diagnostic Script
echo "=== SuperClaude Diagnostic ==="
echo ""
# Check installation system
echo "1. Installation System:"
if command -v SuperClaude &> /dev/null; then
echo " ✅ SuperClaude installation available"
python3 -m SuperClaude --version
else
echo " ❌ SuperClaude not found - install with: pipx install SuperClaude (or pip install SuperClaude)"
fi
# Check context files
echo ""
echo "2. Context Files:"
if [ -d ~/.claude ]; then
echo " ✅ ~/.claude directory exists"
echo " - Agents: $(ls ~/.claude/agents/*.md 2>/dev/null | wc -l)"
echo " - Commands: $(ls ~/.claude/commands/*.md 2>/dev/null | wc -l)"
echo " - Modes: $(ls ~/.claude/modes/*.md 2>/dev/null | wc -l)"
else
echo " ❌ ~/.claude directory not found"
fi
# Check MCP
echo ""
echo "3. MCP Configuration:"
if [ -f ~/.claude.json ]; then
echo " ✅ MCP configuration exists"
else
echo " ❌ No MCP configuration"
fi
# Check Node.js
echo ""
echo "4. Node.js (for MCP):"
if command -v node &> /dev/null; then
echo " ✅ Node.js installed: $(node --version)"
else
echo " ⚠️ Node.js not installed (optional, needed for MCP)"
fi
echo ""
echo "=== Diagnostic Complete ==="
File Permission Fix
# Fix permissions on all context files
chmod 644 ~/.claude/*.md
chmod 644 ~/.claude/**/*.md
chmod 755 ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes
Complete Reinstall
# Backup existing configuration
cp -r ~/.claude ~/.claude.backup.$(date +%Y%m%d)
# Remove existing installation
rm -rf ~/.claude
# Reinstall everything
PYTHONPATH=/path/to/SuperClaude_Framework python3 -m setup install
# Restore any customizations from backup if needed
Important Notes
What We're NOT Verifying
- No Code Execution: Context files don't execute, so no runtime verification needed
- No Performance Metrics: No code runs, so no performance to measure
- No Unit Tests: Context files are instructions, not functions
- No Integration Tests: Claude Code reads files; verification is behavioral
What We ARE Verifying
- File Presence: Context files exist in correct locations
- File Integrity: Files are valid text and readable
- Directory Structure: Proper organization maintained
- Configuration Validity: JSON files are syntactically correct
- Dependencies Available: Node.js for MCP servers (optional)
- Behavioral Testing: Context files produce expected Claude Code behavior
Summary
Verification for SuperClaude focuses on ensuring context files are properly installed and accessible to Claude Code. Since SuperClaude is not software but a configuration framework, verification centers on file presence, integrity, and behavioral testing in Claude Code conversations.