bmad

A structured method for building software with AI, using different roles and workflows for small changes and larger products.

In plain words
What is it for?
Use it to create technical specifications, plan product work, implement individual stories, organize sprints, and review code.
Why use it?
It breaks development into clear steps, so planning, implementation, and review are easier to follow and check.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/re-cinq/wave/bmad
Any agent
npx skills add re-cinq/wave --skill bmad
Clone the repo
git clone --depth 1 https://github.com/re-cinq/wave

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 867 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00867
Opus 5 $0.00017 $0.00434
Sonnet 5 $0.00007 $0.00173
Haiku 4.5 $0.00003 $0.00087

Measured 2d ago against content hash 5cf2d7c4dcdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bmad scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/bmad/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD - Breakthrough Method for Agile AI-Driven Development

BMAD provides a comprehensive methodology for AI-enhanced development workflows with role-based agent specialization and structured collaborative development processes.

Overview

BMAD implements two distinct development paths:

Quick Path (Bug fixes & small features)

Streamlined workflow for small work items (< 1 week):

  • Quick Specification - Analyze codebase and create tech spec with stories
  • Development - Implement individual stories
  • Code Review - Validate quality and compliance

Full Path (Products & complex features)

Comprehensive planning workflow for major initiatives (> 1 week):

  • Product BriefPRDArchitectureEpic BreakdownSprint PlanningStory DevelopmentCode Review

Available Commands

Quick Path

Command Purpose Usage
bmad.quick-spec Analyze codebase and create tech spec with stories /bmad.quick-spec "description"
bmad.dev-story Implement a single story from spec /bmad.dev-story [story-id]
bmad.gh-pr-review Validate code quality and compliance /bmad.gh-pr-review

Full Path

Command Purpose Usage
bmad.product-brief Define problem, users, and MVP scope /bmad.product-brief "product name"
bmad.prd Create detailed Product Requirements Document /bmad.prd
bmad.architecture Create technical architecture document /bmad.architecture
bmad.epics Create prioritized epic and story breakdown /bmad.epics
bmad.sprint Initialize sprint tracking /bmad.sprint
bmad.story Create detailed story specification /bmad.story [epic-id]

Utility

Command Purpose Usage
bmad.help Get contextual guidance and command suggestions /bmad.help [question]
bmad.party Multi-agent collaborative session /bmad.party [topic]

Read the full file on GitHub · 89 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 89 lines · 35 tokens per session scan A 5cf2d7c4dcdc

Subscribe to this mod's changes

bmad is a skill published in the GitHub repository re-cinq/wave (20 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 867 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.