Initialize a project for BMad workflows. Creates _bmad/ directory, config, and status tracking.
From bmad-coworknpx claudepluginhub bspann/bmad-cowork --plugin bmad-coworkThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Use when setting up a new project for BMad workflows. Creates the directory structure, config, and status tracking files.
Trigger with: "init bmad", "initialize project", "set up bmad", "start new project"
Create the following directories and files in the project root:
_bmad/
├── config.yaml # Project configuration
├── bmm-workflow-status.yaml # Workflow tracking (Phase 1-3)
└── context.md # Accumulated project context
_bmad-output/
├── planning-artifacts/ # Briefs, PRDs, architecture, UX, epics
└── implementation-artifacts/
├── stories/ # Individual story files
├── quick-specs/ # Quick Flow tech specs
└── tests/ # Test artifacts (TEA)
docs/ # Project documentation
Create _bmad/config.yaml with this template (ask the user to fill in):
project:
name: "[PROJECT NAME]"
description: "[Brief description]"
type: "greenfield" # greenfield | brownfield
stack:
frontend: "" # e.g., "Next.js, Tailwind, ShadCN"
backend: "" # e.g., "Supabase, Node.js"
language: "" # e.g., "TypeScript"
database: "" # e.g., "PostgreSQL"
hosting: "" # e.g., "Vercel, AWS"
planning:
track: "bmad-method" # quick-flow | bmad-method | enterprise
modules:
bmm: true # Core development lifecycle
tea: false # Test Engineering Architect
bmb: false # BMad Builder
Create _bmad/bmm-workflow-status.yaml:
version: "1.0"
project_key: "default"
current_phase: 1
planning_track: "bmad-method"
phases:
phase_1_analysis:
status: "not_started"
project_brief: "not_started"
phase_2_planning:
status: "not_started"
prd: "not_started"
phase_3_solutioning:
status: "not_started"
architecture: "not_started"
ux_design: "not_started"
epics_and_stories: "not_started"
readiness_check: "not_started"
phase_4_implementation:
status: "not_started"
sprint_planning: "not_started"
completed_workflows: []
active_workflow: null
blockers: []
Create _bmad/context.md:
# Project Context
This file accumulates key decisions and context as you progress through BMad workflows.
Agents read this file to stay informed about project-wide decisions.
## Key Decisions
(Updated automatically as workflows complete)
## Open Questions
(Track unresolved questions here)
Ask the user which modules they want to enable:
Tell the user:
bmad-help to see what to do next/bmad-cowork:brief to start with a project brief