SuperClaude/docs/Reference/diagnostic-reference.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

8.6 KiB

SuperClaude Diagnostic Reference Guide

Overview

This guide provides procedures for diagnosing issues with SuperClaude context files and configurations. Since SuperClaude is a collection of text files (not running software), diagnostics focus on file verification and configuration checking.

Important: There are no processes to monitor, no performance metrics to measure, and no system resources to analyze. SuperClaude is purely configuration files that Claude Code reads.

Quick Diagnostics

One-Line Health Check

# Quick status check
ls ~/.claude/CLAUDE.md && echo "✅ SuperClaude installed" || echo "❌ Not installed"

Basic Diagnostic Commands

# Check if SuperClaude is installed
python3 -m SuperClaude --version

# Count context files
find ~/.claude -name "*.md" -type f | wc -l
# Expected: 40+ files

# Check file sizes (context files should have content)
find ~/.claude -name "*.md" -type f -size 0
# Expected: No output (no empty files)

# Verify directory structure
tree -L 2 ~/.claude/
# Or without tree command:
ls -la ~/.claude/

File System Diagnostics

Context File Verification

#!/bin/bash
# Comprehensive context file check

echo "=== SuperClaude Context File Diagnostic ==="

# Define expected counts
EXPECTED_AGENTS=14
EXPECTED_COMMANDS=21
EXPECTED_MODES=6

# Count actual files
ACTUAL_AGENTS=$(ls ~/.claude/agents/*.md 2>/dev/null | wc -l)
ACTUAL_COMMANDS=$(ls ~/.claude/commands/*.md 2>/dev/null | wc -l)
ACTUAL_MODES=$(ls ~/.claude/modes/*.md 2>/dev/null | wc -l)

# Report findings
echo "Agents: $ACTUAL_AGENTS/$EXPECTED_AGENTS $([ $ACTUAL_AGENTS -ge $EXPECTED_AGENTS ] && echo|| echo ⚠️)"
echo "Commands: $ACTUAL_COMMANDS/$EXPECTED_COMMANDS $([ $ACTUAL_COMMANDS -ge $EXPECTED_COMMANDS ] && echo|| echo ⚠️)"
echo "Modes: $ACTUAL_MODES/$EXPECTED_MODES $([ $ACTUAL_MODES -ge $EXPECTED_MODES ] && echo|| echo ⚠️)"

# Check core files
for file in CLAUDE.md FLAGS.md RULES.md PRINCIPLES.md; do
    if [ -f ~/.claude/$file ]; then
        SIZE=$(wc -c < ~/.claude/$file)
        echo "$file: $SIZE bytes ✅"
    else
        echo "$file: MISSING ❌"
    fi
done

Import System Check

# Verify import statements in CLAUDE.md
echo "=== Import System Check ==="
if [ -f ~/.claude/CLAUDE.md ]; then
    echo "Imports found in CLAUDE.md:"
    grep "^@import" ~/.claude/CLAUDE.md
    
    # Count import statements
    IMPORT_COUNT=$(grep -c "^@import" ~/.claude/CLAUDE.md)
    echo "Total imports: $IMPORT_COUNT"
    
    if [ $IMPORT_COUNT -ge 5 ]; then
        echo "✅ Import system configured correctly"
    else
        echo "⚠️ Some imports may be missing"
    fi
else
    echo "❌ CLAUDE.md not found"
fi

Configuration Diagnostics

MCP Server Configuration Check

# Check MCP configuration
echo "=== MCP Configuration Diagnostic ==="

CONFIG_FILE=~/.claude.json

if [ -f "$CONFIG_FILE" ]; then
    echo "✅ Configuration file exists"
    
    # Validate JSON syntax
    if python3 -c "import json; json.load(open('$CONFIG_FILE'))" 2>/dev/null; then
        echo "✅ Valid JSON syntax"
        
        # List configured servers
        echo "Configured MCP servers:"
        python3 -c "
import json
with open('$HOME/.claude.json') as f:
    config = json.load(f)
    if 'mcpServers' in config:
        for server in config['mcpServers']:
            print(f'  - {server}')
    else:
        print('  No servers configured')
        "
    else
        echo "❌ Invalid JSON syntax in $CONFIG_FILE"
    fi
else
    echo "⚠️ No MCP configuration file found"
    echo "  This is OK if you don't use MCP servers"
fi

Permission Diagnostics

# Check file permissions
echo "=== File Permission Check ==="

# Check if files are readable
UNREADABLE_COUNT=0
for file in ~/.claude/**/*.md; do
    if [ ! -r "$file" ]; then
        echo "❌ Cannot read: $file"
        ((UNREADABLE_COUNT++))
    fi
done

if [ $UNREADABLE_COUNT -eq 0 ]; then
    echo "✅ All context files are readable"
else
    echo "⚠️ Found $UNREADABLE_COUNT unreadable files"
    echo "Fix with: chmod 644 ~/.claude/**/*.md"
fi

# Check directory permissions
for dir in ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes; do
    if [ -d "$dir" ]; then
        if [ -x "$dir" ]; then
            echo "✅ $dir is accessible"
        else
            echo "❌ $dir is not accessible"
        fi
    else
        echo "❌ $dir does not exist"
    fi
done

Common Issue Diagnostics

Issue: Commands Not Recognized

# Diagnose command issues
COMMAND="implement"  # Change to test different commands

echo "=== Diagnosing command: $COMMAND ==="

FILE=~/.claude/commands/$COMMAND.md

if [ -f "$FILE" ]; then
    echo "✅ Command file exists"
    
    # Check file size
    SIZE=$(wc -c < "$FILE")
    if [ $SIZE -gt 100 ]; then
        echo "✅ File has content ($SIZE bytes)"
    else
        echo "⚠️ File seems too small ($SIZE bytes)"
    fi
    
    # Check for metadata
    if head -10 "$FILE" | grep -q "^---"; then
        echo "✅ Has metadata header"
    else
        echo "⚠️ Missing metadata header"
    fi
    
    # Check for command pattern
    if grep -q "/sc:$COMMAND" "$FILE"; then
        echo "✅ Contains command pattern"
    else
        echo "⚠️ Missing command pattern"
    fi
else
    echo "❌ Command file not found: $FILE"
    echo "Available commands:"
    ls ~/.claude/commands/ | sed 's/.md$//'
fi

Issue: Agent Not Activating

# Diagnose agent issues
AGENT="python-expert"  # Change to test different agents

echo "=== Diagnosing agent: $AGENT ==="

FILE=~/.claude/agents/$AGENT.md

if [ -f "$FILE" ]; then
    echo "✅ Agent file exists"
    
    # Check for trigger keywords
    echo "Trigger keywords found:"
    grep -A 5 "## Triggers" "$FILE" | tail -n +2
    
    # Check for metadata
    if head -10 "$FILE" | grep -q "^name:"; then
        echo "✅ Has metadata"
    else
        echo "⚠️ Missing metadata"
    fi
else
    echo "❌ Agent file not found: $FILE"
    echo "Available agents:"
    ls ~/.claude/agents/ | sed 's/.md$//'
fi

Installation Repair

Quick Fix Script

#!/bin/bash
# SuperClaude Quick Fix Script

echo "=== SuperClaude Quick Fix ==="

# Check for common issues and fix them
ISSUES_FOUND=0

# Fix permissions
echo "Fixing file permissions..."
chmod 644 ~/.claude/*.md 2>/dev/null
chmod 644 ~/.claude/**/*.md 2>/dev/null
chmod 755 ~/.claude ~/.claude/agents ~/.claude/commands ~/.claude/modes 2>/dev/null

# Check for missing directories
for dir in agents commands modes; do
    if [ ! -d ~/.claude/$dir ]; then
        echo "⚠️ Missing directory: $dir"
        echo "  Run: SuperClaude install --components $dir"
        ((ISSUES_FOUND++))
    fi
done

# Check for empty files
EMPTY_FILES=$(find ~/.claude -name "*.md" -type f -size 0 2>/dev/null)
if [ -n "$EMPTY_FILES" ]; then
    echo "⚠️ Found empty files:"
    echo "$EMPTY_FILES"
    echo "  Run: SuperClaude install --force"
    ((ISSUES_FOUND++))
fi

if [ $ISSUES_FOUND -eq 0 ]; then
    echo "✅ No issues found"
else
    echo "Found $ISSUES_FOUND issues - see recommendations above"
fi

Complete Reinstallation

# Complete clean reinstall
echo "=== Clean Reinstall ==="

# Backup current installation
BACKUP_DIR=~/.claude.backup.$(date +%Y%m%d_%H%M%S)
if [ -d ~/.claude ]; then
    cp -r ~/.claude "$BACKUP_DIR"
    echo "✅ Backed up to $BACKUP_DIR"
fi

# Remove current installation
rm -rf ~/.claude

# Reinstall
SuperClaude install

# Verify installation
if [ -f ~/.claude/CLAUDE.md ]; then
    echo "✅ Reinstallation successful"
else
    echo "❌ Reinstallation failed"
    echo "Restoring backup..."
    cp -r "$BACKUP_DIR" ~/.claude
fi

What These Diagnostics DON'T Do

Not Applicable Concepts

  • CPU/Memory Monitoring: No processes to monitor
  • Performance Metrics: No code execution to measure
  • Network Analysis: No network operations (except MCP)
  • Process Management: No running processes
  • Resource Optimization: No resources consumed
  • Execution Timing: No code executes

Focus on What Matters

  • File Presence: Are context files installed?
  • File Integrity: Are files readable and complete?
  • Configuration Validity: Is JSON syntax correct?
  • Directory Structure: Is organization correct?
  • Permissions: Can Claude Code read the files?

Summary

SuperClaude diagnostics are simple: verify files exist, check they're readable, and ensure configurations are valid. Since it's just text files that Claude Code reads, there's no complex system monitoring or performance analysis needed. If files are present and readable, SuperClaude is working.