sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
Install / Use
npx skills add spencermarx/open-code-review --skill sparc-methodologyInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of sparc-methodology
sparc-methodology scores 86/100 on our quality scale, 2299th of 4,716 Development & Engineering skills we index (top 49%).
Its SKILL.md is 24 KB long, well organised into 111 sections with 33 code examples: a thorough specification that gives an agent plenty to work with.
It has 368 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-11-03 found the source still online.
- It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
sparc-methodology compared with similar skills
All 4 of these similar skills score higher than sparc-methodology; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| sparc-methodology (this skill)by spencermarx | 86 | 368 | 4mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 118.9k | 11d ago | CLAUDE.md |
| hyperframesby heygen-com | 100 | 87.1k | today | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.6k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.5k | 5d ago | CLAUDE.md |
Frequently asked questions
- How do I install sparc-methodology?
- Run
npx skills add spencermarx/open-code-review --skill sparc-methodology. The install tabs above show the steps for each supported agent. - Which AI agents does sparc-methodology work with?
- It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is sparc-methodology safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is sparc-methodology still maintained?
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubname: sparc-methodology description: SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration version: 2.7.0 category: development tags:
- sparc
- tdd
- architecture
- orchestration
- methodology
- multi-agent author: Claude Flow
SPARC Methodology - Comprehensive Development Framework
Overview
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) is a systematic development methodology integrated with Claude Flow's multi-agent orchestration capabilities. It provides 17 specialized modes for comprehensive software development, from initial research through deployment and monitoring.
Table of Contents
- Core Philosophy
- Development Phases
- Available Modes
- Activation Methods
- Orchestration Patterns
- TDD Workflows
- Best Practices
- Integration Examples
- Common Workflows
Core Philosophy
SPARC methodology emphasizes:
- Systematic Approach: Structured phases from specification to completion
- Test-Driven Development: Tests written before implementation
- Parallel Execution: Concurrent agent coordination for 2.8-4.4x speed improvements
- Memory Integration: Persistent knowledge sharing across agents and sessions
- Quality First: Comprehensive reviews, testing, and validation
- Modular Design: Clean separation of concerns with clear interfaces
Key Principles
- Specification Before Code: Define requirements and constraints clearly
- Design Before Implementation: Plan architecture and components
- Tests Before Features: Write failing tests, then make them pass
- Review Everything: Code quality, security, and performance checks
- Document Continuously: Maintain current documentation throughout
Development Phases
Phase 1: Specification
Goal: Define requirements, constraints, and success criteria
- Requirements analysis
- User story mapping
- Constraint identification
- Success metrics definition
- Pseudocode planning
Key Modes: researcher, analyzer, memory-manager
Phase 2: Architecture
Goal: Design system structure and component interfaces
- System architecture design
- Component interface definition
- Database schema planning
- API contract specification
- Infrastructure planning
Key Modes: architect, designer, orchestrator
Phase 3: Refinement (TDD Implementation)
Goal: Implement features with test-first approach
- Write failing tests
- Implement minimum viable code
- Make tests pass
- Refactor for quality
- Iterate until complete
Key Modes: tdd, coder, tester
Phase 4: Review
Goal: Ensure code quality, security, and performance
- Code quality assessment
- Security vulnerability scanning
- Performance profiling
- Best practices validation
- Documentation review
Key Modes: reviewer, optimizer, debugger
Phase 5: Completion
Goal: Integration, deployment, and monitoring
- System integration
- Deployment automation
- Monitoring setup
- Documentation finalization
- Knowledge capture
Key Modes: workflow-manager, documenter, memory-manager
Available Modes
Core Orchestration Modes
orchestrator
Multi-agent task orchestration with TodoWrite/Task/Memory coordination.
Capabilities:
- Task decomposition into manageable units
- Agent coordination and resource allocation
- Progress tracking and result synthesis
- Adaptive strategy selection
- Cross-agent communication
Usage:
mcp__claude-flow__sparc_mode {
mode: "orchestrator",
task_description: "coordinate feature development",
options: { parallel: true, monitor: true }
}
swarm-coordinator
Specialized swarm management for complex multi-agent workflows.
Capabilities:
- Topology optimization (mesh, hierarchical, ring, star)
- Agent lifecycle management
- Dynamic scaling based on workload
- Fault tolerance and recovery
- Performance monitoring
workflow-manager
Process automation and workflow orchestration.
Capabilities:
- Workflow definition and execution
- Event-driven triggers
- Sequential and parallel pipelines
- State management
- Error handling and retry logic
batch-executor
Parallel task execution for high-throughput operations.
Capabilities:
- Concurrent file operations
- Batch processing optimization
- Resource pooling
- Load balancing
- Progress aggregation
Development Modes
coder
Autonomous code generation with batch file operations.
Capabilities:
- Feature implementation
- Code refactoring
- Bug fixes and patches
- API development
- Algorithm implementation
Quality Standards:
- ES2022+ standards
- TypeScript type safety
- Comprehensive error handling
- Performance optimization
- Security best practices
Usage:
mcp__claude-flow__sparc_mode {
mode: "coder",
task_description: "implement user authentication with JWT",
options: {
test_driven: true,
parallel_edits: true,
typescript: true
}
}
architect
System design with Memory-based coordination.
Capabilities:
- Microservices architecture
- Event-driven design
- Domain-driven design (DDD)
- Hexagonal architecture
- CQRS and Event Sourcing
Memory Integration:
- Store architectural decisions
- Share component specifications
- Maintain design consistency
- Track architectural evolution
Design Patterns:
- Layered architecture
- Microservices patterns
- Event-driven patterns
- Domain modeling
- Infrastructure as Code
Usage:
mcp__claude-flow__sparc_mode {
mode: "architect",
task_description: "design scalable e-commerce platform",
options: {
detailed: true,
memory_enabled: true,
patterns: ["microservices", "event-driven"]
}
}
tdd
Test-driven development with comprehensive testing.
Capabilities:
- Test-first development
- Red-green-refactor cycle
- Test suite design
- Coverage optimization (target: 90%+)
- Continuous testing
TDD Workflow:
- Write failing test (RED)
- Implement minimum code
- Make test pass (GREEN)
- Refactor for quality (REFACTOR)
- Repeat cycle
Testing Strategies:
- Unit testing (Jest, Mocha, Vitest)
- Integration testing
- End-to-end testing (Playwright, Cypress)
- Performance testing
- Security testing
Usage:
mcp__claude-flow__sparc_mode {
mode: "tdd",
task_description: "shopping cart feature with payment integration",
options: {
coverage_target: 90,
test_framework: "jest",
e2e_framework: "playwright"
}
}
reviewer
Code review using batch file analysis.
Capabilities:
- Code quality assessment
- Security vulnerability detection
- Performance analysis
- Best practices validation
- Documentation review
Review Criteria:
- Code correctness and logic
- Design pattern adherence
- Comprehensive error handling
- Test coverage adequacy
- Maintainability and readability
- Security vulnerabilities
- Performance bottlenecks
Batch Analysis:
- Parallel file review
- Pattern detection
- Dependency checking
- Consistency validation
- Automated reporting
Usage:
mcp__claude-flow__sparc_mode {
mode: "reviewer",
task_description: "review authentication module PR #123",
options: {
security_check: true,
performance_check: true,
test_coverage_check: true
}
}
Analysis and Research Modes
researcher
Deep research with parallel WebSearch/WebFetch and Memory coordination.
Capabilities:
- Comprehensive information gathering
- Source credibility evaluation
- Trend analysis and forecasting
- Competitive research
- Technology assessment
Research Methods:
- Parallel web searches
- Academic paper analysis
- Industry report synthesis
- Expert opinion gathering
- Statistical data compilation
Memory Integration:
- Store research findings with citations
- Build knowledge graphs
- Track information sources
- Cross-reference insights
- Maintain research history
Usage:
mcp__claude-flow__sparc_mode {
mode: "researcher",
task_description: "research microservices best practices 2024",
options: {
depth: "comprehensive",
sources: ["academic", "industry", "news"],
citations: true
}
}
analyzer
Code and data analysis with pattern recognition.
Capabilities:
- Static code analysis
- Dependency analysis
- Performance profiling
- Security scanning
- Data pattern recognition
optimizer
Performance optimization and bottleneck resolution.
Capabilities:
- Algorithm optimization
- Database query tuning
- Caching strategy design
- Bundle size reduction
- Memory leak detection
Creative and Support Modes
designer
UI/UX design with accessibility focus.
Capabilities:
- Interface design
- User experience optimization
- Accessibility compliance (WCAG 2.1)
- Design system creation
- Responsive layout design
innovator
Creative problem-solving and novel solutions.
Capabilities:
- Brainstorming and ideation
- Alternative approach generation
- Technology evaluation
- Proof of concept development
- Innovation feasibility analysis
documenter
Comprehensive documentation generation.
Capabilities:
- API documentation (OpenAPI/Swagger)
- Architecture diagrams
- User guides and tutorials
- Code comments and JSDoc
- README and changelog maintenance
debugger
Systematic debugging and issue resolution.
Capabilities:
- Bug reproduction
- Root cause analysis
- Fix implementation
- Regression prevention
- Debug logging optimization
tester
Comprehensive testing beyond TDD.
Capabilities:
- Test suite expansion
- Edge case identification
- Performance testing
- Load testing
- Chaos engineering
memory-manager
Knowledge management and context preservation.
Capabilities:
- Cross-session memory persistence
- Knowledge graph construction
- Context restoration
- Learning pattern extraction
- Decision tracking
Activation Methods
Method 1: MCP Tools (Preferred in Claude Code)
Best for: Integrated Claude Code workflows with full orchestration capabilities
// Basic mode execution
mcp__claude-flow__sparc_mode {
mode: "<mode-name>",
task_description: "<task description>",
options: {
// mode-specific options
}
}
// Initialize swarm for complex tasks
mcp__claude-flow__swarm_init {
topology: "hierarchical", // or "mesh", "ring", "star"
strategy: "auto", // or "balanced", "specialized", "adaptive"
maxAgents: 8
}
// Spawn specialized agents
mcp__claude-flow__agent_spawn {
type: "<agent-type>",
capabilities: ["<capability1>", "<capability2>"]
}
// Monitor execution
mcp__claude-flow__swarm_monitor {
swarmId: "current",
interval: 5000
}
Method 2: NPX CLI (Fallback)
Best for: Terminal usage or when MCP tools unavailable
# Execute specific mode
npx claude-flow sparc run <mode> "task description"
# Use alpha features
npx claude-flow@alpha sparc run <mode> "task description"
# List all available modes
npx claude-flow sparc modes
# Get help for specific mode
npx claude-flow sparc help <mode>
# Run with options
npx claude-flow sparc run <mode> "task" --parallel --monitor
# Execute TDD workflow
npx claude-flow sparc tdd "feature description"
# Batch execution
npx claude-flow sparc batch <mode1,mode2,mode3> "task"
# Pipeline execution
npx claude-flow sparc pipeline "task description"
Method 3: Local Installation
Best for: Projects with local claude-flow installation
# If claude-flow is installed locally
./claude-flow sparc run <mode> "task description"
Orchestration Patterns
Pattern 1: Hierarc
Truncated for display — read the full file on GitHub.
Related Skills
taste-skill
118.9kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
hyperframes
87.1kAI video you can actually edit. HyperFrames is a free, open-source AI video editor. Describe any video and get a real project you can change down to the frame.
ai-job-search
72.6kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.5kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
