External/SuperClaude
1
0
Fork 0
mirror of https://github.com/SuperClaude-Org/SuperClaude_Framework.git synced 2025-12-17 17:56:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
SuperClaude/docs/User-Guide/flags.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

273 lines
11 KiB
Markdown
Raw Blame History

# SuperClaude Flags Guide 🏁
**Most flags activate automatically** - Claude Code reads behavioral instructions to engage appropriate contexts based on keywords and patterns in your requests.
## Essential Auto-Activation Flags (90% of Use Cases)
### Core Analysis Flags
| Flag | When Activated | What It Does |
|------|---------------|--------------|
| `--think` | 5+ files OR complex analysis | Standard structured analysis (~4K tokens) |
| `--think-hard` | Architectural analysis, system dependencies | Deep analysis (~10K tokens) with enhanced tools |
| `--ultrathink` | Critical system redesign, legacy modernization | Maximum depth analysis (~32K tokens) with all tools |
### MCP Server Flags
| Flag | Server | Purpose | Auto-Triggers |
|------|---------|---------|---------------|
| `--c7` / `--context7` | Context7 | Official docs, framework patterns | Library imports, framework questions |
| `--seq` / `--sequential` | Sequential | Multi-step reasoning, debugging | Complex debugging, system design |
| `--magic` | Magic | UI component generation | `/ui` commands, frontend keywords |
| `--play` / `--playwright` | Playwright | Browser testing, E2E validation | Testing requests, visual validation |
| `--chrome` / `--devtools` | Chrome DevTools | Performance analysis, debugging | Performance auditing, debugging, layout issues |
| `--tavily` | Tavily | Web search, real-time info | Web search requests, research queries |
| `--morph` / `--morphllm` | Morphllm | Bulk transformations, pattern edits | Bulk operations, style enforcement |
| `--serena` | Serena | Project memory, symbol operations | Symbol operations, large codebases |
### Behavioral Mode Flags
| Flag | When Activated | What It Does |
|------|---------------|--------------|
| `--brainstorm` | Vague requests, exploration keywords | Collaborative discovery mindset |
| `--introspect` | Self-analysis, error recovery | Expose reasoning process with transparency |
| `--task-manage` | >3 steps, complex scope | Orchestrate through delegation |
| `--orchestrate` | Multi-tool operations, performance needs | Optimize tool selection and parallel execution |
| `--token-efficient` / `--uc` | Context >75%, efficiency needs | Symbol-enhanced communication, 30-50% reduction |
### Execution Control Flags
| Flag | When Activated | What It Does |
|------|---------------|--------------|
| `--loop` | "improve", "polish", "refine" keywords | Iterative enhancement cycles |
| `--safe-mode` | Production, >85% resource usage | Maximum validation, conservative execution |
| `--validate` | Risk >0.7, production environment | Pre-execution risk assessment |
| `--delegate` | >7 directories OR >50 files | Sub-agent parallel processing |
## Command-Specific Flags
### Analysis Command Flags (`/sc:analyze`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--focus` | Target specific domain | `security`, `performance`, `quality`, `architecture` |
| `--depth` | Analysis thoroughness | `quick`, `deep` |
| `--format` | Output format | `text`, `json`, `report` |
### Build Command Flags (`/sc:build`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Build configuration | `dev`, `prod`, `test` |
| `--clean` | Clean before build | Boolean |
| `--optimize` | Enable optimizations | Boolean |
| `--verbose` | Detailed output | Boolean |
### Design Command Flags (`/sc:design`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Design target | `architecture`, `api`, `component`, `database` |
| `--format` | Output format | `diagram`, `spec`, `code` |
### Explain Command Flags (`/sc:explain`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--level` | Complexity level | `basic`, `intermediate`, `advanced` |
| `--format` | Explanation style | `text`, `examples`, `interactive` |
| `--context` | Domain context | Any domain (e.g., `react`, `security`) |
### Improve Command Flags (`/sc:improve`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Improvement focus | `quality`, `performance`, `maintainability`, `style`, `security` |
| `--safe` | Conservative approach | Boolean |
| `--interactive` | User guidance | Boolean |
| `--preview` | Show without executing | Boolean |
### Task Command Flags (`/sc:task`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--strategy` | Task approach | `systematic`, `agile`, `enterprise` |
| `--parallel` | Parallel execution | Boolean |
| `--delegate` | Sub-agent coordination | Boolean |
### Workflow Command Flags (`/sc:workflow`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--strategy` | Workflow approach | `systematic`, `agile`, `enterprise` |
| `--depth` | Analysis depth | `shallow`, `normal`, `deep` |
| `--parallel` | Parallel coordination | Boolean |
### Troubleshoot Command Flags (`/sc:troubleshoot`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Issue category | `bug`, `build`, `performance`, `deployment` |
| `--trace` | Include trace analysis | Boolean |
| `--fix` | Apply fixes | Boolean |
### Cleanup Command Flags (`/sc:cleanup`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Cleanup target | `code`, `imports`, `files`, `all` |
| `--safe` / `--aggressive` | Cleanup intensity | Boolean |
| `--interactive` | User guidance | Boolean |
| `--preview` | Show without executing | Boolean |
### Estimate Command Flags (`/sc:estimate`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Estimate focus | `time`, `effort`, `complexity` |
| `--unit` | Time unit | `hours`, `days`, `weeks` |
| `--breakdown` | Detailed breakdown | Boolean |
### Index Command Flags (`/sc:index`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Index target | `docs`, `api`, `structure`, `readme` |
| `--format` | Output format | `md`, `json`, `yaml` |
### Reflect Command Flags (`/sc:reflect`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--type` | Reflection scope | `task`, `session`, `completion` |
| `--analyze` | Include analysis | Boolean |
| `--validate` | Validate completeness | Boolean |
### Spawn Command Flags (`/sc:spawn`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--strategy` | Coordination approach | `sequential`, `parallel`, `adaptive` |
| `--depth` | Analysis depth | `normal`, `deep` |
### Git Command Flags (`/sc:git`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--smart-commit` | Generate commit message | Boolean |
| `--interactive` | Guided operations | Boolean |
### Select-Tool Command Flags (`/sc:select-tool`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--analyze` | Tool analysis | Boolean |
| `--explain` | Explain selection | Boolean |
### Test Command Flags (`/sc:test`)
| Flag | Purpose | Values |
|------|---------|--------|
| `--coverage` | Include coverage | Boolean |
| `--type` | Test type | `unit`, `integration`, `e2e` |
| `--watch` | Watch mode | Boolean |
## Advanced Control Flags
### Scope and Focus
| Flag | Purpose | Values |
|------|---------|--------|
| `--scope` | Analysis boundary | `file`, `module`, `project`, `system` |
| `--focus` | Domain targeting | `performance`, `security`, `quality`, `architecture`, `accessibility`, `testing` |
### Execution Control
| Flag | Purpose | Values |
|------|---------|--------|
| `--concurrency [n]` | Control parallel ops | 1-15 |
| `--iterations [n]` | Improvement cycles | 1-10 |
| `--all-mcp` | Enable all MCP servers | Boolean |
| `--no-mcp` | Native tools only | Boolean |
| `--frontend-verify` | UI testing, frontend debugging, layout validation | Enable Playwright + Chrome DevTools + Serena |
### System Flags (SuperClaude Installation)
| Flag | Purpose | Values |
|------|---------|--------|
| `--verbose` / `-v` | Verbose logging | Boolean |
| `--quiet` / `-q` | Suppress output | Boolean |
| `--dry-run` | Simulate operation | Boolean |
| `--force` | Skip checks | Boolean |
| `--yes` / `-y` | Auto-confirm | Boolean |
| `--install-dir` | Target directory | Path |
| `--legacy` | Use legacy script | Boolean |
| `--version` | Show version | Boolean |
| `--help` | Show help | Boolean |
## Common Usage Patterns
### Frontend Development
```bash
/sc:implement "responsive dashboard" --magic --c7
/sc:design component-library --type component --format code
/sc:test ui-components/ --magic --play
/sc:improve legacy-ui/ --magic --morph --validate
```
### Backend Development
```bash
/sc:analyze api/ --focus performance --seq --think
/sc:design payment-api --type api --format spec
/sc:troubleshoot "API timeout" --type performance --trace
/sc:improve auth-service --type security --validate
```
### Large Projects
```bash
/sc:analyze . --ultrathink --all-mcp --safe-mode
/sc:workflow enterprise-system --strategy enterprise --depth deep
/sc:cleanup . --type all --safe --interactive
/sc:estimate "migrate to microservices" --type complexity --breakdown
```
### Quality & Maintenance
```bash
/sc:improve src/ --type quality --safe --interactive
/sc:cleanup imports --type imports --preview
/sc:reflect --type completion --validate
/sc:git commit --smart-commit
```
## Flag Interactions
### Compatible Combinations
- `--think` + `--c7`: Analysis with documentation
- `--magic` + `--play`: UI generation with testing
- `--serena` + `--morph`: Project memory with transformations
- `--safe-mode` + `--validate`: Maximum safety
- `--loop` + `--validate`: Iterative improvement with validation
### Conflicting Flags
- `--all-mcp` vs individual MCP flags (use one or the other)
- `--no-mcp` vs any MCP flags (--no-mcp wins)
- `--safe` vs `--aggressive` (cleanup intensity)
- `--quiet` vs `--verbose` (output level)
### Auto-Enabling Relationships
- `--safe-mode` auto-enables `--uc` and `--validate`
- `--ultrathink` auto-enables all MCP servers
- `--think-hard` auto-enables `--seq` + `--c7`
- `--magic` triggers UI-focused agents
## Troubleshooting Flags
### Common Issues
- **Too many tools**: Use `--no-mcp` to test with native tools only
- **Operation too slow**: Add `--uc` to compress output
- **Validation blocking**: Use `--validate` instead of `--safe-mode` in development
- **Context pressure**: Auto-activates `--token-efficient` at >75% usage
### Debug Flags
```bash
/sc:analyze . --verbose # Shows decision logic and flag activation
/sc:select-tool "operation" --explain # Explains tool selection process
/sc:reflect --type session --analyze # Reviews current session decisions
```
### Quick Fixes
```bash
/sc:analyze . --help # Shows available flags for command
/sc:analyze . --no-mcp # Native execution only
/sc:cleanup . --preview # Shows what would be cleaned
```
## Flag Priority Rules
1. **Safety First**: `--safe-mode` > `--validate` > optimization flags
2. **Explicit Override**: User flags > auto-detection
3. **Depth Hierarchy**: `--ultrathink` > `--think-hard` > `--think`
4. **MCP Control**: `--no-mcp` overrides all individual MCP flags
5. **Scope Precedence**: system > project > module > file
## Related Resources
- [Commands Guide](commands.md) - Commands that use these flags
- [MCP Servers Guide](mcp-servers.md) - Understanding MCP flag activation
- [Session Management](session-management.md) - Using flags with persistent sessions
Reference in New Issue View Git Blame Copy Permalink