Execute Spec-Driven Development (SDD) workflows to build features: generate EARS requirements docs, technical designs, hierarchical TDD tasks, implement with Red-Green-Refactor cycles and SOLID principles, run code reviews, OWASP security audits, and Conventional Commits.
System design and architecture specialist
Implementation-focused agent for writing quality code
Planning and roadmap agent for project organization
Code reviewer with direct, Linus-style feedback applying 5-layer thinking
Security specialist for OWASP-aligned vulnerability assessment
Guide commit message and PR creation for SDD workflow. Use when committing changes, creating pull requests, or documenting changes. Invoked via /sdd-commit.
Create technical design specifications for SDD workflow. Use when designing architecture, defining components, or creating system design documents after requirements are approved. Invoked via /sdd-design <feature-name>.
Implementation guidelines for SDD workflow. Use when implementing features, applying TDD, checking security, or ensuring code quality. Invoked via /sdd-implement <feature-name>.
Generate EARS-formatted requirements for SDD workflow. Use when starting a new feature specification, creating requirements documents, or defining acceptance criteria. Invoked via /sdd-requirements <feature-name>.
Perform thorough Linus-style code review focusing on correctness, maintainability, and adherence to project conventions. Use after completing implementation to ensure code quality. Invoked via /sdd-review [file-path or PR-number].
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Model Context Protocol (MCP) server implementing Spec-Driven Development (SDD) workflows for AI-agent CLIs and IDEs like Claude Code, Cursor, and others.
v3.3 - Multi-tool install support:
--codex(AGENTS.md for OpenAI Codex CLI),--antigravity(.agent/ symlinks for Google Antigravity),--all-tools. See CHANGELOG.md for full version history.
# No installation required - use directly with npx
npx -y sdd-mcp-server@latest
# Pin exact version (optional)
npx -y sdd-mcp-server@1.6.0
# For Claude Code MCP integration, add to your configuration:
# "sdd-mcp-server": {
# "command": "npx",
# "args": ["-y", "sdd-mcp-server@latest"]
# }
# Install globally for persistent usage
npm install -g sdd-mcp-server@latest
# Pin exact version (optional)
npm install -g sdd-mcp-server@1.6.0
# Start the server
sdd-mcp-server
# Clone the repository
git clone https://github.com/yi-john-huang/sdd-mcp.git
cd sdd-mcp
# Install and start
npm install
npm run build
npm start
# Build distroless image locally
docker build --target production -t sdd-mcp-server .
# Run with Docker (secure distroless image)
docker run -p 3000:3000 sdd-mcp-server
# Or with Docker Compose (includes security hardening)
curl -O https://raw.githubusercontent.com/yi-john-huang/sdd-mcp/develop/docker-compose.yml
docker-compose up -d
gcr.io/distroless/nodejs18-debian11 for minimal attack surfaceno-new-privileges prevents privilege escalationAdd to your MCP settings using the command line:
# Option 1: Use npx (no installation required)
claude mcp add sdd -s local -- npx -y sdd-mcp-server@latest
# Option 2: Install globally first
npm install -g sdd-mcp-server@latest
claude mcp add sdd "sdd-mcp-server" -s local
# Verify connection
claude mcp list
# Should show: sdd: ✓ Connected
# For development (local repo):
git clone https://github.com/yi-john-huang/sdd-mcp.git
cd sdd-mcp
# Use the dedicated MCP entry
claude mcp add sdd "$(pwd)/mcp-server.js" -s local
Manual configuration in ~/.claude.json:
{
"mcpServers": {
"sdd": {
"command": "sdd-mcp-server",
"args": [],
"env": {}
}
}
}
Add to your MCP configuration:
{
"sdd-server": {
"command": "npx",
"args": ["-y", "sdd-mcp-server@latest"],
"env": {}
}
}
Or with global installation:
{
"sdd-server": {
"command": "sdd-mcp-server",
"args": [],
"env": {}
}
}
Any MCP-compatible client can connect using stdio transport:
# Use npx (no installation required)
npx -y sdd-mcp-server@latest
# Or install globally first
npm install -g sdd-mcp-server@latest
sdd-mcp-server
SDD now uses a hybrid architecture for better token efficiency:
# Recommended: Install ALL components (skills, steering, rules, contexts, agents, hooks)
npx sdd-mcp-server install --all
# Install specific component types
npx sdd-mcp-server install --skills # Skills to .claude/skills/
npx sdd-mcp-server install --steering # Steering to .spec/steering/
npx sdd-mcp-server install --rules # Rules to .claude/rules/
npx sdd-mcp-server install --contexts # Contexts to .claude/contexts/
npx sdd-mcp-server install --agents # Agents to .claude/agents/
npx sdd-mcp-server install --hooks # Hooks to .claude/hooks/
# Install multiple component types
npx sdd-mcp-server install --skills --rules --agents
# Default: Install skills + steering (backward compatible)
npx sdd-mcp-server install
# List all available components
npx sdd-mcp-server install --list
# Legacy: Install skills only
npx sdd-mcp-server install-skills
npx claudepluginhub yi-john-huang/sdd-mcpSpec-driven development methodology for full-stack teams
Spec-Driven Development Workflow for Claude Code. A 6-step pipeline: Requirements → Code Analysis → Design → Implement → Verify → Self-Improve. Specifications are the source of truth, code is a verified artifact.
Comprehensive Spec-Driven Development toolkit with multi-language support, specialized agents, and integrated security/observability tools
Spec-driven development for big features. When features get too big, plan mode gets too vague—leading to hallucinations during implementation. ShipSpec replaces vague plans with structured PRDs, technical designs, and ordered tasks that keep Claude grounded.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer