Breakthrough Method for Agile Ai Driven Development
Go to file
Brian Madison 7ad054f0e9 fix(installer): address fourth-round PR #2353 review comments
(1) Use process.exitCode instead of process.exit() after --list-options
write (CodeRabbit major). process.exit() forces immediate termination
even with pending I/O, which can truncate buffered writes when stdout
is piped or captured by CI. Await the write callback, set exitCode,
and return so the event loop drains naturally.

(2) Thread setOverrides through Config → OfficialModules.build for
headless callers (CodeRabbit major). Non-UI entry points (direct
installer.install({...}) without going through ui.collectModuleConfigs)
previously got an empty override map. Config now carries setOverrides
and the headless branch of OfficialModules.build also runs
loadExistingConfig + applyOverridesAfterSeeding('core') to mirror the
UI path's semantics. The UI path is unaffected because it takes the
moduleConfigs early-return.

(3) Evaluate function defaults under skipPrompts and accept-defaults
paths (CodeRabbit major). Both branches were dropping function defaults
silently, so any same-module dynamic default (`{other_key}` placeholder
in default:) disappeared under --yes. Two-pass: write non-function
defaults first so the answer bag is populated, then call function
defaults with that bag. Try/catch around the call surfaces resolution
failures as warnings instead of crashing the install.

(4) Track result-only schema keys as declared (Augment medium). A
schema entry with `result:` and no `prompt:` was being classified as
"unknown" when targeted by --set, producing a wrong warning and
overwriting the computed template output with the raw value. Added
declaredResultKeys parallel to declaredPromptKeys; an override on
either is now seeded as the answer so the result template still
renders ({value} substitution preserved). Carry-forward block
refactored to consume the same set.

(5) Diagnose non-object module.yaml under --list-options (Augment low).
The non-object branch silently flipped moduleScopedFailure with no
output. Now emits "module.yaml is not a valid object (got <type>)"
mirroring the catch branch, and the type guard also catches arrays
which typeof reports as 'object'.

(6) Reword --list-options doc cache scope (CodeRabbit minor).
"Installed at least once on this machine" → "currently cached official
modules" with a note that cache can be cleared or absent on ephemeral
CI workers — accurately reflects what the command can discover.

Tests: +4 cases — Config.build setOverrides threading and default,
formatOptionsList non-object yaml diagnostic and ok:false. Total 347
passing.
2026-04-28 18:59:17 -05:00
.augment chore(tools): align Augment config with skill-validator as single source of truth 2026-03-15 17:41:54 -06:00
.claude-plugin chore: remove SM agent (Bob) and migrate to Developer agent (#2186) 2026-04-02 12:25:24 -07:00
.github fix(publish): advance @next dist-tag after stable release (#2320) 2026-04-26 10:30:41 -05:00
.husky docs: fix docs build (#1336) 2026-01-15 16:44:14 -06:00
.vscode excorcise the deamons part 1 - remove dead uneeed artifacts and items no longer being supported beyond beta of the BMM or core - but could return later as a module 2026-02-04 15:44:25 -06:00
docs fix(installer): address fourth-round PR #2353 review comments 2026-04-28 18:59:17 -05:00
src fix: align bmad-help.csv with documented schema and clean up source rows (#2278) (#2349) 2026-04-27 23:54:21 -05:00
test fix(installer): address fourth-round PR #2353 review comments 2026-04-28 18:59:17 -05:00
tools fix(installer): address fourth-round PR #2353 review comments 2026-04-28 18:59:17 -05:00
website docs: remove Bob from workflow map diagrams 2026-04-12 23:12:32 -05:00
.coderabbit.yaml feat(coderabbit): add docs-staleness check for all src/ changes 2026-03-17 15:30:32 -06:00
.gitignore feat(skills): TOML-based agent and workflow customization (#2284) 2026-04-19 19:30:29 -05:00
.markdownlint-cli2.yaml refactor: replace 'execute' with 'Read fully and follow:' in workflow prompts (#1387) 2026-01-23 22:25:19 -06:00
.npmignore chore: remove dead agent schema validation infrastructure 2026-03-17 20:20:12 -06:00
.npmrc fix: resolve npm install peer dependency issues 2026-01-30 15:37:42 +00:00
.nvmrc feat: v6.0.0-alpha.0 - the future is now 2025-09-28 23:17:07 -05:00
.prettierignore chore: ignore .junie/ IDE integration folder (#1719) 2026-02-20 20:33:23 -06:00
AGENTS.md feat(tools): add deterministic skill validator for CI 2026-03-17 23:49:01 -06:00
CHANGELOG.md docs: add v6.5.0 changelog entry (#2314) 2026-04-25 21:24:43 -05:00
CNAME Add CNAME file 2026-01-07 18:18:12 +08:00
CONTRIBUTING.md docs: add contribution guardrails for unsolicited PRs (#2207) 2026-04-04 12:13:06 -05:00
CONTRIBUTORS.md project licence, contribution and discord noise updates, along with improved simplified issue templates 2026-01-18 17:03:47 -06:00
LICENSE project licence, contribution and discord noise updates, along with improved simplified issue templates 2026-01-18 17:03:47 -06:00
README.md fix(installer): address third-round PR #2353 review comments 2026-04-28 11:42:07 -05:00
README_CN.md chore: remove SM agent (Bob) and migrate to Developer agent (#2186) 2026-04-02 12:25:24 -07:00
README_VN.md docs(vi-vn): sync translations and add missing checkpoint-preview page (#2222) 2026-04-09 20:49:18 -07:00
SECURITY.md Enhance security policy documentation (#1312) 2026-01-14 16:27:52 -06:00
TRADEMARK.md project licence, contribution and discord noise updates, along with improved simplified issue templates 2026-01-18 17:03:47 -06:00
Wordmark.png feat: update website header with new BMAD Method branding (#1352) 2026-01-18 00:25:12 -06:00
banner-bmad-method.png feat: update website header with new BMAD Method branding (#1352) 2026-01-18 00:25:12 -06:00
eslint.config.mjs feat(skills): TOML-based agent and workflow customization (#2284) 2026-04-19 19:30:29 -05:00
package-lock.json chore(release): v6.5.0 [skip ci] 2026-04-26 02:25:31 +00:00
package.json chore(release): v6.5.0 [skip ci] 2026-04-26 02:25:31 +00:00
prettier.config.mjs feat: v6.0.0-alpha.0 - the future is now 2025-09-28 23:17:07 -05:00
removals.txt fix(installer): remove pre-v6.2.0 wrapper skills on update (closes #2309) (#2315) 2026-04-25 22:08:44 -05:00

README.md

BMad Method

Version License: MIT Node.js Version Python Version uv Discord

Build More Architect Dreams — An AI-driven agile development module for the BMad Method Module Ecosystem, the best and most comprehensive Agile AI Driven Development framework that has true scale-adaptive intelligence that adjusts from bug fixes to enterprise systems.

100% free and open source. No paywalls. No gated content. No gated Discord. We believe in empowering everyone, not just those who can pay for a gated community or courses.

Why the BMad Method?

Traditional AI tools do the thinking for you, producing average results. BMad agents and facilitated workflows act as expert collaborators who guide you through a structured process to bring out your best thinking in partnership with the AI.

  • AI Intelligent Help — Invoke the bmad-help skill anytime for guidance on what's next
  • Scale-Domain-Adaptive — Automatically adjusts planning depth based on project complexity
  • Structured Workflows — Grounded in agile best practices across analysis, planning, architecture, and implementation
  • Specialized Agents — 12+ domain experts (PM, Architect, Developer, UX, and more)
  • Party Mode — Bring multiple agent personas into one session to collaborate and discuss
  • Complete Lifecycle — From brainstorming to deployment

Learn more at docs.bmad-method.org


🚀 What's Next for BMad?

V6 is here and we're just getting started! The BMad Method is evolving rapidly with optimizations including Cross Platform Agent Team and Sub Agent inclusion, Skills Architecture, BMad Builder v1, Dev Loop Automation, and so much more in the works.

📍 Check out the complete Roadmap →


Quick Start

Prerequisites: Node.js v20+ · Python 3.10+ · uv

npx bmad-method install

Want the newest prerelease build? Use npx bmad-method@next install. Expect higher churn than the default install.

Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, etc.) in your project folder.

Non-Interactive Installation (for CI/CD):

npx bmad-method install --directory /path/to/project --modules bmm --tools claude-code --yes

Override any module config option with --set <module>.<key>=<value> (repeatable). Run --list-options [module] to see locally-known official keys (built-in modules plus any external officials cached on this machine):

npx bmad-method install --yes \
  --modules bmm --tools claude-code \
  --set bmm.project_knowledge=research \
  --set bmm.user_skill_level=expert

See all installation options

Not sure what to do? Ask bmad-help — it tells you exactly what's next and what's optional. You can also ask questions like bmad-help I just finished the architecture, what do I do next?

Modules

BMad Method extends with official modules for specialized domains. Available during installation or anytime after.

Module Purpose
BMad Method (BMM) Core framework with 34+ workflows
BMad Builder (BMB) Create custom BMad agents and workflows
Test Architect (TEA) Risk-based test strategy and automation
Game Dev Studio (BMGD) Game development workflows (Unity, Unreal, Godot)
Creative Intelligence Suite (CIS) Innovation, brainstorming, design thinking

Documentation

BMad Method Docs Site — Tutorials, guides, concepts, and reference

Quick links:

Community

Support BMad

BMad is free for everyone and always will be. Star this repo, buy me a coffee, or email contact@bmadcode.com for corporate sponsorship.

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

License

MIT License — see LICENSE for details.


BMad and BMAD-METHOD are trademarks of BMad Code, LLC. See TRADEMARK.md for details.

Contributors

See CONTRIBUTORS.md for contributor information.