CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/npm-bmad-method

Universal AI agent framework for agentic agile-driven development with progressive disclosure documentation optimized for AI agents

Pending
Quality

Pending

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Pending

The risk profile of this skill

Overview
Eval results
Files

index.mddocs/

BMad Method

Universal AI agent framework for agentic agile-driven development. Transforms traditional software projects through specialized AI agent teams with a two-phase approach: Agentic Planning (web platforms) and Context-Engineered Development (IDEs).

Package Information

interface PackageInfo {
  name: 'bmad-method';
  type: 'npm';
  language: 'JavaScript';
  install: 'npx bmad-method install';
  version: '4.44.3';
  nodeVersion: '>=20.10.0';
}

Quick Start

# Install BMad Method
npx bmad-method install                    # Interactive mode with prompts
npx bmad-method install --full             # Full installation
npx bmad-method install --ide cursor       # Configure specific IDE

# Check status
npx bmad-method status                     # Show installation status

# List available resources
npx bmad-method list:expansions            # List expansion packs
npx bmad-method list:agents                # List all agents

After installation, agents are available in .bmad-core/ directory. Load agents in your IDE or web platform, activate with *help command.

Core Concepts

Two-Phase Approach

BMad Method eliminates planning inconsistency and context loss through two distinct phases:

Phase 1: Agentic Planning (Web UI)

  • Platform: ChatGPT, Claude, Gemini
  • Team: Analyst → PM → UX Expert → Architect → PO
  • Output: Comprehensive specifications (PRD, Architecture, Frontend Spec)
  • Purpose: Create complete, validated specifications before development

Phase 2: Context-Engineered Development (IDE)

  • Platform: Cursor, Claude Code, Windsurf, etc.
  • Team: SM → Dev → QA
  • Process: Story files contain complete context - no re-reading of PRD/architecture
  • Purpose: Implement with complete context embedded in each story

Key Components

Agent System: 10 specialized AI agent personas (Orchestrator, Analyst, PM, Architect, UX Expert, PO, SM, Dev, QA)

Task System: 23 tasks (21 core tasks + 2 common shared tasks) for reusable executable procedures

Workflow System: 6 structured workflows (greenfield/brownfield variants for fullstack, service, UI)

Template System: 13 YAML-based document templates with sophisticated markup language

Agent Teams: Pre-configured bundles for different project types (fullstack, ide-minimal, no-ui, all)

Expansion Packs: Domain-specific extensions (game development, creative writing, DevOps)

Agent Quick Reference

Agent IDNamePhaseKey CommandsUse Case
bmad-orchestratorBMad OrchestratorAll*agent, *workflow, *planMaster coordinator, workflow guidance
analystMaryPlanning*brainstorm, *create-project-briefMarket research, requirements
pm-Planning*create-prd, *update-prdProduct requirements, PRD
architect-Planning*create-architectureSystem design, architecture
ux-expert-Planning*create-frontend-spec, *generate-ui-promptUI/UX specifications
poSarahPlanning/Dev*shard-doc, *validate-story-draftDocument sharding, validation
smBobDevelopment*draftStory creation with full context
devJamesDevelopment*develop-story, *run-testsCode implementation
qaQuinnDevelopment*review, *gateQuality review, gates

Detailed Documentation: Agent Reference

Workflow Quick Reference

Workflow IDTypeAgentsUse Case
greenfield-fullstackNew8 agentsFull-stack app from scratch
greenfield-serviceNew7 agents (no UX)Backend/API only
greenfield-uiNewFrontend-focusedFrontend apps only
brownfield-fullstackExistingSkip AnalystExtend full-stack apps
brownfield-serviceExistingSkip Analyst, no UXExtend backend services
brownfield-uiExistingSkip AnalystExtend frontend apps

Detailed Documentation: Workflow Reference

Task Categories

CategoryKey TasksPrimary Users
Document Managementshard-doc, create-doc, index-docsPO, PM, Architect
Story/Epiccreate-next-story, create-brownfield-story, review-storySM, PM, PO
Developmentapply-qa-fixes, correct-courseDev, SM, PO
Quality Assuranceqa-gate, test-design, trace-requirementsQA
Researchcreate-deep-research-prompt, advanced-elicitationAnalyst
Integrationgenerate-ai-frontend-prompt, kb-mode-interactionUX, Orchestrator

Detailed Documentation: Task Reference

Template Quick Reference

Template IDOutputUsed ByPurpose
project-brief-tmpldocs/project-brief.mdAnalystInitial overview
prd-tmpldocs/prd.mdPMGreenfield requirements
brownfield-prd-tmpldocs/brownfield-prd.mdPMEnhancement requirements
architecture-tmpldocs/architecture.mdArchitectGeneric architecture
fullstack-architecture-tmpldocs/fullstack-architecture.mdArchitectFull-stack architecture
front-end-spec-tmpldocs/front-end-spec.mdUX ExpertUI/UX specifications
story-tmpldocs/stories/{epic}.{story}.mdSMStory with complete context
qa-gate-tmpldocs/qa/{story}-qa-gate.mdQAQuality gate decision

Detailed Documentation: Template Reference

Agent Teams

TeamAgentsPlatformUse Case
team-fullstack6 planning agentsWeb platformsFull lifecycle planning
team-ide-minimalPO, SM, Dev, QADesktop IDEsDevelopment only
team-no-ui5 planning agentsWeb platformsBackend/service planning
team-allAll 10 agentsAnyMaximum flexibility

Detailed Documentation: Agent Teams Reference

Expansion Packs

Pack IDVersionDescription
bmad-godot-game-dev1.0.0Godot game development (GDScript & C#)
bmad-2d-unity-game-dev1.0.0Unity 2D game development
bmad-2d-phaser-game-dev1.0.0Phaser 2D game development
bmad-creative-writing1.0.0Creative writing & storytelling
bmad-infrastructure-devops1.0.0DevOps & infrastructure

Detailed Documentation: Expansion Packs Reference

Installation Output Structure

your-project/
├── .bmad-core/              # Core framework
│   ├── agents/              # 10 agent personas
│   ├── tasks/               # 21 core tasks
│   ├── templates/           # 13 document templates
│   ├── workflows/           # 6 workflow definitions
│   ├── checklists/          # 6 quality checklists
│   ├── agent-teams/         # 4 team configurations
│   ├── data/                # Knowledge base files
│   └── core-config.yaml     # Project configuration
├── common/                  # Shared resources
│   ├── tasks/               # 2 common shared tasks (create-doc, execute-checklist)
│   └── utils/               # Common utilities
├── .{expansion-pack}/       # Optional expansion packs
├── docs/                    # Generated documentation
│   ├── prd.md              # Product Requirements
│   ├── architecture.md      # Architecture document
│   └── stories/            # Story files for development
└── web-bundles/            # Optional web bundles for ChatGPT/Claude/Gemini

Configuration

Core configuration is in .bmad-core/core-config.yaml:

markdownExploder: true              # Use markdown-tree-parser for sharding
qa:
  qaLocation: docs/qa               # QA artifacts directory
prd:
  prdFile: docs/prd.md             # PRD file path
  prdVersion: v4                    # Format version
  prdSharded: true                  # Enable sharding
  prdShardedLocation: docs/prd      # Sharded directory
  epicFilePattern: epic-{n}*.md     # Epic file naming pattern
architecture:
  architectureFile: docs/architecture.md
  architectureVersion: v4
  architectureSharded: true
  architectureShardedLocation: docs/architecture
devLoadAlwaysFiles:                 # Files dev always loads
  - docs/architecture/coding-standards.md
  - docs/architecture/tech-stack.md
devStoryLocation: docs/stories      # Story directory
slashPrefix: "*"                    # Command prefix

Detailed Documentation: Configuration Reference

CLI Commands

CommandPurposeExample
installInstall/upgrade BMadnpx bmad-method install
updateUpdate installationnpx bmad-method update
statusShow installation statusnpx bmad-method status
flattenFlatten codebase to XMLnpx bmad-method flatten -i ./src -o out.xml
list:expansionsList available packsnpx bmad-method list:expansions
list:agentsList all agentsnpx bmad-method list:agents

Detailed Documentation: CLI Reference

Programmatic API

bmad-method can be used programmatically in Node.js applications:

const installer = require('bmad-method/tools/installer/lib/installer');
const WebBuilder = require('bmad-method/tools/builders/web-builder');
const DependencyResolver = require('bmad-method/tools/lib/dependency-resolver');

// Install BMad programmatically
await installer.install({
  installType: 'full',
  directory: './my-project',
  ides: ['claude-code', 'cursor']
});

// Build web bundles
const builder = new WebBuilder({ rootDir: process.cwd() });
await builder.buildAgents();

// Resolve dependencies
const resolver = new DependencyResolver('./my-project');
const agents = await resolver.listAgents();

Detailed Documentation: Programmatic API Reference

Platform Support

Desktop IDEs: Cursor, Claude Code, Windsurf, Trae, Roo Code, Kilo Code, Cline, VS Code (GitHub Copilot), Crush, Qwen Code

CLI Tools: iFlow CLI, Auggie CLI (Augment Code), Gemini CLI, Codex CLI

Web Platforms: ChatGPT, Claude, Gemini, Codex Web, OpenCode

Agent Activation Pattern

All agents follow consistent activation:

  1. Agent reads complete definition file
  2. Adopts persona from configuration
  3. Loads .bmad-core/core-config.yaml
  4. Greets user with name/role and runs *help
  5. Stays in character throughout interaction

All commands use * prefix (e.g., *help, *create-prd, *develop-story).

Common Workflows

For detailed examples: See Real-World Scenarios and Edge Cases for comprehensive usage examples.

Greenfield Full-Stack Workflow

Phase 1: Planning (Web Platform)

*agent analyst          # Create project brief
*agent pm               # Create PRD with epics and stories
*agent ux-expert        # Create frontend specification
*agent architect        # Create full-stack architecture
*agent po               # Validate and shard documents

Phase 2: Development (IDE)

*agent sm               # Create story files with complete context
*agent dev              # Implement stories sequentially
*agent qa               # Review and gate implementation

Brownfield Enhancement Workflow

Phase 1: Document & Plan

npx bmad-method flatten -i . -o project.xml    # Document existing codebase
*agent pm                                       # Create brownfield PRD
*agent architect                                # Document architecture changes
*agent po                                       # Shard documents

Phase 2: Development

*agent sm               # Create brownfield stories
*agent dev              # Implement with safety checks
*agent qa               # Validate changes

Critical Patterns

Document Sharding

Large documents (PRD, Architecture) are split into manageable chunks:

*agent po
*shard-doc

# Output:
# docs/prd/ with epic-1.md, epic-2.md, etc.
# docs/architecture/ with tech-stack.md, coding-standards.md, etc.

Story Creation with Context

SM agent creates stories with complete implementation context:

interface StoryContext {
  requirements: 'From sharded PRD epic';
  architecture: 'Selective sections (tech-stack, backend-architecture, etc.)';
  previousStories: 'Learnings from completed stories';
  sourceReferences: '[Source: docs/architecture/tech-stack.md#frameworks]';
  tasks: 'Checkbox list with subtasks';
}

Quality Gates

QA agent makes gate decisions with detailed rationale:

interface QualityGateDecision {
  PASS: 'All criteria met, ready for production';
  CONCERNS: 'Issues found but not blocking';
  FAIL: 'Critical issues, must address';
  WAIVED: 'Issues waived by stakeholder';
}

Template Markup Language

Templates use sophisticated markup for AI-driven generation:

interface TemplateMarkup {
  placeholders: {
    syntax: '{{variable_name}}';
    example: '{{project_name}}, {{epic_num}}';
  };
  llmInstructions: {
    syntax: '[[LLM: instructions]]';
    visibility: 'Invisible to users, processed by AI';
  };
  elicitation: {
    property: 'elicit: true';
    format: 'Mandatory 1-9 options with methods';
  };
}

Dependency Resolution

Agents load dependencies on-demand:

interface DependencyResolution {
  pattern: '{root}/{type}/{name}';
  types: ['tasks', 'templates', 'checklists', 'data'];
  example: 'create-doc.md → .bmad-core/tasks/create-doc.md';
}

Version Information

  • Current Version: 4.44.3 (stable v4 branch)
  • PRD Version: v4 (current), v3 (legacy support)
  • Architecture Version: v4 (current), v3 (legacy support)
  • Node.js: >= 20.10.0

Documentation Structure

Guides (Step-by-Step)

Examples (Real-World Scenarios)

Reference (Detailed Specs)

Related Resources

  • BMad Method GitHub
  • npm Package
  • Documentation Site

docs

index.md

tile.json