External/BMAD-METHOD
1
0
Fork 0
mirror of https://github.com/bmadcode/BMAD-METHOD.git synced 2025-12-29 16:14:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

BMad Agent (V3) Final Beta Testing Release (#59)

Browse Source
This commit is contained in:
Brian
2025-05-17 23:21:14 -05:00
committed by GitHub
parent 6e771a10ca
commit b2ad4b7e85
215 changed files with 7213 additions and 3562 deletions
Download Patch File Download Diff File Expand all files Collapse all files

162
README.md
View File

@@ -1,122 +1,65 @@
# The BMAD-Method (Breakthrough Method of Agile (ai-driven) Development)
**BETA-V3 is the current focus of development and represents the latest iteration of the BMAD Method.** Find all V3 resources in the `BETA-V3/` directory.
Current Version: V3 Release Preview "Bmad Agent"
#### A demo of full beta run one all of its output artifacts along with an explanation of what each file represents is avilable [here](BETA-V3/v3-demos/full-stack-app-demo/readme.md)
Demos of the BMad Agent and the entire workflow can be found soon in [Demos](./demos/).
If you want to jump right in, here are the [Setup Instructions for V3](./BETA-V3/instruction.md) For IDE, WEB and Task setup.
## Quickstart Project Setup
## BETA-V3: Advancing AI-Driven Development
Orchestrator Uber BMad Agent that does it all - already [pre-built](./web-build-sample/agent-prompt.txt)! Just copy to a Gemini Gem or custom GPT as instructions, and attach the remaining files in the folder to the agent as shown in the following image.
Welcome to **BETA-V3**! This version represents a significant evolution, building upon the foundations of V2 and introducing a more refined and comprehensive suite of agents, templates, checklists, and processes.
![image info](./docs/images/gem-setup.png)
Feel free to try it out - its beta, so please know its still undergoing testing and updates and there are some significant (amazing improvements) changes.
If you are not sure what to do in the Web Agent - try /help to get a list of commands, and /agents to see what personas BMad can become.
_Previous versions (`LEGACY-V1` and `CURRENT-V2`) are available for historical reference but are no longer actively maintained._
If you are going to use the IDE Agents in your project, after cloning the repo, you can copy the bmad-agent folder to your project as is if you like - this is the easiest. You can also from this cloned repo root folder execute the command with nodeJS to build and bundle your assets to easily program an ultra powerful Web Agent to handle all agile process from ideation to ready to develop (Recommended).
## What's New in BETA-V3?
So if you want to jump right in, here are the [Setup and Usage Instructions](./docs/instruction.md) for IDE, WEB and Task setup.
BETA-V3 introduces several key enhancements to streamline your AI-driven development lifecycle:
## Advancing AI-Driven Development
- **Enhanced Agent Roles & Phases:** The core agents (Analyst, PM, Architect) have more clearly defined operational phases, inputs, and outputs, leading to smoother transitions.
- **New Specialized Agents:**
- **Design Architect (`4-design-architect.md`):** A dedicated agent for projects with User Interfaces, handling UI/UX Specification and Frontend Technical Architecture in distinct modes.
- **Technical POSM (`5-posm.md`) (Product Owner & Scrum Master):** A unified agent with critical new capabilities:
- **Master Checklist Phase:** Validates all project documentation against a comprehensive checklist (`po-master-checklist.txt`).
- **Librarian Phase:** Decomposes large documents into a granular, indexed (`docs/index.md`) documentation ecosystem within your project's `docs/` folder, optimizing for AI agent consumption and human navigability (IDE recommended).
- **Story Creator Phase:** Autonomously generates detailed, developer-ready story files using the granular documentation.
- **Release Train Engineer (RTE-Agent) (`6-rte.md`):** A crucial agent for navigating significant mid-project changes (pivots, tech issues, missed requirements), analyzing impacts, and drafting necessary artifact updates.
- **Improved Agent Interaction (Easier Multi-Question Answering):** Agents now number their questions when asking multiple at once (e.g., "1., 2a., 2b."). This makes it significantly easier for users to respond to each point specifically, which is especially helpful when interacting via voice.
- **Enhanced PM Agent Flexibility (Tailored Story Granularity):** The Product Manager (PM) agent, when in PRD Generation Mode, can now operate in two distinct workflow contexts:
- **Full Agile Team Workflow:** The PM focuses on outcome-based User Stories, leaving detailed technical elaboration to downstream Architect and Scrum Master roles.
- **Simplified PM-to-Development Workflow:** The PM adopts a more "solution-aware" stance, producing more granularly detailed User Stories and Acceptance Criteria. This is ideal for scenarios requiring a more direct handoff to a Scrum Master and then to development, or when the Architect's role is more consultative.
- **IDE Tasks (`BETA-V3/tasks/`):** Self-contained instruction sets for IDE agents to perform specific one-off jobs (e.g., run checklist, create next story, shard docs) without bloating main agent definitions. [Read more below](#ide-tasks-v3-exclusive).
- **Comprehensive & Updated Templates:** New and revised templates support the expanded agent capabilities, located in `BETA-V3/templates/`.
- **Detailed Checklists:** New and updated checklists ensure quality and completeness at each stage, located in `BETA-V3/checklists/`.
- **Streamlined Workflow & Documentation Focus:** A more explicit, iterative workflow incorporating all agents, with a strong emphasis on creating and maintaining a robust, granular, and indexed documentation structure (`docs/`) to support development.
- **Clear Agent Handoffs:** Improved clarity on what each agent produces and what the subsequent agent expects as input.
- **Optimized IDE Agents:** IDE agent modes (`BETA-V3/ide-agent-modes/`) are optimized for size (<6k tokens) for broader IDE compatibility.
- **Web UI Parity:** Agent instructions and templates are designed for use in both web-based UIs (instructions and files in `BETA-V3/web-agent-modes/`) and IDE custom modes.
Welcome to the latest and most advanced yet easy to use version of the Web and IDE Agent Agile Workflow! This new version, called BMad Agent, represents a significant evolution that builds but vastly improves upon the foundations of [legacy V2](./legacy-archive/V2/), introducing a more refined and comprehensive suite of agents, templates, checklists, tasks - and the amazing BMad Orchestrator and Knowledge Base agent is now available - a master of every aspect of the method that can become any agent and even handle multiple tasks all within a single massive web context if so desired.
## Guiding Principles (V3)
## What's New?
- **Environment Recommendations & Workflow:**
- **Web UI Preferred for Initial Planning (Agents 0-5):** For initial ideation, research, PRD creation, architecture design, UI/UX specification, and initial documentation validation (Analyst, PM, Architect, Design Architect, and POSM Master Checklist phase), Web UIs (Gems/Custom GPTs) are highly effective and often more cost-efficient for the iterative, conversational nature of these tasks.
- **POSM - Librarian & Story Creator:** While the POSM's Librarian phase (document sharding and indexing) is strongly recommended for an IDE due to file system operations, the Story Creator phase _can_ be done in a Web UI. However, an IDE is often preferred for easier cross-referencing with existing `docs/` content and the eventual codebase.
- **IDE Recommended for Execution & Specialized Tasks:** For development (Dev Agent), detailed story generation (SM Agent or POSM Story Creator in IDE), and managing significant mid-project changes (RTE-Agent), an IDE environment with custom agent modes is generally more powerful and efficient. The core recommended IDE agents, especially after initial web-based planning, are the **Dev Agent, SM/Story Creator, and RTE-Agent**.
- **Quality & Information Flow (V3 Enhancements):**
- The **PM Agent** is tuned to produce higher quality, more detailed Epics and User Stories.
- There's improved consistency between what the **SM Agent (or POSM in Story Creator mode)** includes in story files and what the **Dev Agent** expects. The SM focuses on embedding necessary contextual details directly into the story.
- The **Dev Agent** is programmed to always consult standard project documents like `docs/coding-standards.md` and `docs/project-structure.md` upon starting a new story. This reduces the need to repeat this boilerplate information in every story file, keeping stories leaner and focused on the specific requirements.
- **No Rules Required (Flexibility):** Agents primarily reference project documents (PRDs, architecture docs, coding standards, etc.) rather than relying heavily on proprietary AI platform rule systems. This promotes flexibility and reduces platform lock-in.
- **Iterative & Collaborative:** The method emphasizes a step-by-step, interactive process where agents collaborate with the user, pausing for input and validation at key decision points.
All IDE Agents are now optimized to be under 6K characters, so they will work with windsurf's file limit restrictions.
The method now has an uber Orchestrator called BMAD - this agent will take your web or ide usage to the next level - this agent can morph and become the specific agent you want to work with! This makes Web usage super easy to use and set up. And in the IDE - you do not have to set up so many different agents if you do not want to!
There have been drastic improvements to the generation of documents and artifacts and the agents are now programmed to really help you build the best possible plans. Advanced LLM prompting techniques have been incorporated and programmed to help you help the agents produce amazing accurate artifacts, unlike anything seen before. Additionally agents are now configurable in what they can and cannot do - so you can accept the defaults, or set which personas are able to do what tasks. If you think the PO should be the one generating PRDs and the Scrum Master should be your course corrector - its all possible now! **Define agile the BMad way - or your way!**
While this is very powerful - you can get started with the default recommended set up as is in this repo, and basically use the agents as they are envisioned and will be explained. Detailed configuration and usage is outlined in the [Instructions](./docs/instruction.md)
## What is the BMad Method?
The BMad Method is a revolutionary approach that elevates "vibe coding" to "Vibe CEOing." It provides a structured yet flexible framework to plan, execute, and manage software projects using a team of specialized AI agents. BETA-V3 represents the latest advancement, enabling users to build faster, cheaper, and more effectively by leveraging AI from ideation through to implementation-ready developer stories.
The BMad Method is a revolutionary approach that elevates "vibe coding" to advanced project planning to ensure your developer agents can start and completed advanced projects with very explicit guidance. It provides a structured yet flexible framework to plan, execute, and manage software projects using a team of specialized AI agents.
This method and tooling is so much more than just a task runner - this is a refined tool that will help you bring out your best ideas, define what you really are to build, and execute on it! From ideation, to PRD creation, to the technical decision making - this will help you do it all with the power of advanced LLM guidance.
The method is designed to be tool-agnostic in principle, with agent instructions and workflows adaptable to various AI platforms and IDEs.
Join the [Community Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/discussions) to contribute and evolve these ideas.
## Agile Agents
## Custom Modes and Welcome Contributions
Agents are programmed either directly self contained to drop right into an agent config in the ide - or they can be configured as programmable entities the orchestrating agent can become.
The BMAD community's input is invaluable! We encourage you to contribute by submitting Pull Requests for V3 custom agent modes, new templates, or checklist enhancements tailored for the `BETA-V3` system.
### Web Agents
The Custom Agents in `BETA-V3` follow best practices for LLM prompting (e.g., clear roles, instructions, and context) ensuring they work effectively across various AI platforms.
Gemini 2.5 or Open AI customGPTs are created by running the node build script to generate output to a build folder. This output is the full package to create the orchestrator web agent.
## BETA-V3 Agent Overview
See the detailed [Web Orchestration Setup and Usage Instructions](./docs/instruction.md#setting-up-web-agent-orchestrator)
The `BETA-V3` system features a refined team of specialized AI agents (refer to `BETA-V3/web-agent-modes/` or `BETA-V3/ide-agent-modes/` for full details):
### IDE Agents
### 0. BMAD Method Advisor (`0-bmad.md`)
There are dedicated self contained agents that are stand alone, and also an IDE version of an orchestrator. For there standalone, there are:
The primary guide to understanding and navigating the BMAD Method V3, explaining agent roles, workflows, tasks, and best practices.
- [Dev IDE Agent](./bmad-agent/personas/dev.ide.md)
- [Story Generating SM Agent](./bmad-agent/personas/sm.ide.md)
### 1. Analyst (`1-analyst.md`)
If you want to use the other agents, you can use the other agents from that folder - but some will be larger than Windsurf allows - and there are many agents. So its recommended to either use 1 off tasks - OR even better - use the IDE Orchestrator Agent. See these [set up and Usage instructions for IDE Orchestrator](./docs/instruction.md#ide-agent-setup-and-usage).
Starting point for new/unclear ideas.
**Phases:** Brainstorming, Deep Research (broad market/feasibility), Project Briefing.
**Key Output:** **Project Brief**.
## Tasks
### 2. Product Manager (PM) (`2-pm.md`)
Transforms ideas/briefs into detailed product plans.
**Phases:** Deep Research (focused strategy validation), PRD Generation (Epics, Stories, tech assumptions using `prd-tmpl.txt` & `pm-checklist.txt`), Product Advisor.
**Key Output:** **Product Requirements Document (PRD)**.
### 3. Architect (`3-architect.md`)
Defines the overall technical blueprint.
**Phases:** Deep Research Prompt Generation, Architecture Creation (using `architecture-tmpl.txt` & `architect-checklist.txt`), Master Architect Advisory.
**Key Output:** **Technical Architecture Document**.
### 4. Design Architect (`4-design-architect.md`)
Specializes in UI/UX and frontend technical strategy.
**Modes:** UI/UX Specification (using `front-end-spec-tmpl.txt`), Frontend Architecture (using `front-end-architecture-tmpl.txt` & `frontend-architecture-checklist.txt`), AI Frontend Generation Prompt.
**Key Outputs:** **UI/UX Spec**, **Frontend Architecture Doc**.
### 5. Technical POSM (`5-posm.md`)
Ensures documentation quality and prepares for development.
**Phases:** Master Checklist (using `po-master-checklist.txt`), Librarian (creates `docs/` structure & `index.md`), Story Creator (using `story-tmpl.txt`).
**Key Outputs:** **Checklist Report**, Organized granular documentation, **Story Files**.
### 6. Release Train Engineer (RTE-Agent) (`6-rte.md`)
Manages significant mid-project changes and pivots.
**Process:** Uses `rte-checklist.md` for impact analysis, evaluates paths, drafts artifact updates.
**Key Output:** **Sprint Change Proposal** (with analysis and proposed edits).
### 7. Developer Agents (e.g., `dev-agent.md`)
(Specific prompts in `BETA-V3/ide-agent-modes/`)
Implement features based on stories, adhering to architecture and standards (`coding-standards.md`, `project-structure.md`, etc.).
## IDE Tasks (V3 Exclusive!)
Located in `BETA-V3/tasks/`, these self-contained instruction sets allow IDE agents to perform specific one-off jobs on demand, reducing the need for overly complex agent modes.
Located in `bmad-agent/tasks/`, these self-contained instruction sets allow IDE agents or the orchestrators configured agents to perform specific jobs. These also can be used as one off commands with a vanilla agent in the ide by just referencing the task and asking the agent to perform it.
**Purpose:**
@@ -126,40 +69,9 @@ Located in `BETA-V3/tasks/`, these self-contained instruction sets allow IDE age
Think of tasks as specialized mini-agents callable by your main IDE agents.
## BETA-V3 Step-by-Step Process (Typical Flow)
## End Matter
1. **Analyst (`1-analyst.md`):** (Optional) -> **Project Brief**.
2. **PM (`2-pm.md`):** Project Brief/idea -> **PRD** (Epics, Stories).
3. **Architect (`3-architect.md`):** PRD -> **System Architecture Document**.
4. **Design Architect (`4-design-architect.md`):** (If UI) PRD, System Arch -> **UI/UX Spec**, **Frontend Architecture Doc**.
5. **POSM (`5-posm.md`) - Master Checklist Phase:** Validates docs -> **Master Checklist Report**.
6. _(User/Agents apply changes based on POSM report)_.
7. **POSM (`5-posm.md`) - Librarian Phase:** Processes updated docs -> Granular `docs/` files & `index.md`.
8. **POSM (`5-posm.md`) - Story Creator Phase:** -> **Developer Story Files**.
9. **Developer Agents:** Implement stories.
10. **(If major issue arises): RTE-Agent (`6-rte.md`):** -> **Sprint Change Proposal** (with proposed edits). Apply edits or handoff if replan needed.
11. **Ongoing Advisory:** Architect & PM provide continuous support.
Interested in improving the BMAD Method? See the [contributing guidelines](docs/CONTRIBUTING.md).
_This is a guideline; the method is iterative._
## Tooling & Setup (BETA-V3)
- **Templates:** `BETA-V3/templates/`
- **Checklists:** `BETA-V3/checklists/`
- **Web UI Agents:** `BETA-V3/web-agent-modes/` (Use with Gemini Gems/Custom GPTs. Attach relevant templates/checklists).
- **IDE Agents:** `BETA-V3/ide-agent-modes/` (Optimized for IDE custom modes).
- **Tasks:** `BETA-V3/tasks/` (For IDE usage).
- **Instructions:** See [Setup Instructions](./BETA-V3/instruction.md) for details.
## Historical Versions (V1 & V2)
_Brief summary of V1/V2 can remain here or be moved to a separate historical doc if desired._
_(Original V2 sections like "What's New in V2?", "Full Demonstration Walkthrough" (referencing V2 demo), "No Rules Required!", "IDE Agent Integration" (referencing V2 paths), etc. would be reviewed, summarized, or removed to avoid confusion with V3)._
## License
[License](./LICENSE)
## Contributing
Interested in improving the BMAD Method BETA-V3? See our [contributing guidelines](CONTRIBUTING.md).
Thank you and enjoy - BMad!
[License](./docs/LICENSE)