bmad-method 4.21.0 → 4.21.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,3 +1,17 @@
1
+ ## [4.21.2](https://github.com/bmadcode/BMAD-METHOD/compare/v4.21.1...v4.21.2) (2025-06-30)
2
+
3
+
4
+ ### Bug Fixes
5
+
6
+ * improve create-doc task clarity for template execution ([86d5139](https://github.com/bmadcode/BMAD-METHOD/commit/86d5139aea7097cc5d4ee9da0f7d3e395ce0835e))
7
+
8
+ ## [4.21.1](https://github.com/bmadcode/BMAD-METHOD/compare/v4.21.0...v4.21.1) (2025-06-30)
9
+
10
+
11
+ ### Bug Fixes
12
+
13
+ * readme clarifies that the installer handles installs upgrades and expansion installation ([9371a57](https://github.com/bmadcode/BMAD-METHOD/commit/9371a5784f6a6f2ad358a72ea0cde9c980357167))
14
+
1
15
  # [4.21.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.20.0...v4.21.0) (2025-06-30)
2
16
 
3
17
 
package/README.md CHANGED
@@ -71,30 +71,42 @@ This makes it easy to benefit from the latest improvements, bug fixes, and new a
71
71
 
72
72
  ## 🚀 Quick Start
73
73
 
74
- ### Fastest Start: Web UI (2 minutes) 🏃‍♂️
74
+ ### One Command for Everything (IDE Installation)
75
+
76
+ **Just run one of these commands:**
77
+
78
+ ```bash
79
+ npx bmad-method install
80
+ # OR if you already have BMad installed:
81
+ npm run install:bmad
82
+ ```
83
+
84
+ This single command handles:
85
+
86
+ - **New installations** - Sets up BMad in your project
87
+ - **Upgrades** - Updates existing installations automatically
88
+ - **Expansion packs** - Installs any expansion packs you've added to package.json
89
+
90
+ > **That's it!** Whether you're installing for the first time, upgrading, or adding expansion packs - these commands do everything.
91
+
92
+ **Prerequisites**: [Node.js](https://nodejs.org) v20+ required
93
+
94
+ ### Fastest Start: Web UI (2 minutes)
75
95
 
76
96
  1. **Get the bundle**: Copy `dist/teams/team-fullstack.txt` (from this repository)
77
97
  2. **Create AI agent**: Create a new Gemini Gem or CustomGPT
78
98
  3. **Upload & configure**: Upload the file and set instructions: "Your critical operating instructions are attached, do not break character as directed"
79
99
  4. **Start Ideating and Planning**: Start chatting! Type `*help` to see available commands or pick an agent like `*analyst` to start right in on creating a brief.
80
100
 
81
- > 💡 **All pre-built bundles are in the `dist/` folder** - ready to copy and use immediately!
82
-
83
- ### IDE Quick Start (5 minutes) 💻
101
+ > **All pre-built bundles are in the `dist/` folder** - ready to copy and use immediately!
84
102
 
85
- **Prerequisites**: Install [Node.js](https://nodejs.org) (v20 or higher)
86
-
87
- Run `npx bmad-method install`
88
-
89
- OR
103
+ ### Alternative: Clone and Build
90
104
 
91
105
  ```bash
92
106
  git clone https://github.com/bmadcode/bmad-method.git
93
107
  npm run install:bmad # build and install all to a destination folder
94
108
  ```
95
109
 
96
- This installs all agents and configures them for your IDE. If you have an existing v3 installation, it will offer to upgrade it automatically.
97
-
98
110
  ## Overview
99
111
 
100
112
  The BMad Method (Breakthrough Method of Agile Agentic-Driven Development) elevates 'Vibe Coding' by providing specialized AI agents for every role in an Agile team. Each agent has deep expertise in their domain helping you really plan and execute on your vision while keeping the agents on the rails even through complex application plans.
@@ -103,7 +115,25 @@ Unlike systems like Task Master, or inbuilt Task tool, the BMad Methods agile fl
103
115
 
104
116
  ## Installation
105
117
 
106
- ### Method 1: Pre-Built Web Bundles (Fastest) 📦
118
+ ### Method 1: CLI Installer (For IDEs)
119
+
120
+ **Just run one command:**
121
+
122
+ ```bash
123
+ npx bmad-method install
124
+ # OR if you already have BMad installed:
125
+ npm run install:bmad
126
+ ```
127
+
128
+ **This single command does everything:**
129
+
130
+ - Installs BMad for the first time
131
+ - Updates existing installations
132
+ - Adds any expansion packs from your package.json
133
+
134
+ **Prerequisites**: Install [Node.js](https://nodejs.org) v20+ first
135
+
136
+ ### Method 2: Pre-Built Web Bundles (For Web UI)
107
137
 
108
138
  For ChatGPT, Claude, or Gemini web interfaces:
109
139
 
@@ -114,12 +144,6 @@ For ChatGPT, Claude, or Gemini web interfaces:
114
144
  3. Set instructions: "Your critical operating instructions are attached, do not break character as directed"
115
145
  4. Type `/help` to see available commands
116
146
 
117
- ### Method 2: CLI Installer (For IDEs) 🎯
118
-
119
- **Prerequisites**: Install [Node.js](https://nodejs.org) v20+ first
120
-
121
- Install directly into your project: `npx bmad-method install`
122
-
123
147
  **Supported IDEs:**
124
148
 
125
149
  The BMad Method works with any IDE, but has built-in integration for:
@@ -2,73 +2,70 @@
2
2
 
3
3
  ## Purpose
4
4
 
5
- - Generate documents from any specified template following embedded instructions from the perspective of the selected agent persona
5
+ Generate documents from templates by EXECUTING (not just reading) embedded instructions from the perspective of the selected agent persona.
6
6
 
7
- ## Instructions
7
+ ## CRITICAL RULES
8
8
 
9
- ### 1. Identify Template and Context
9
+ 1. **Templates are PROGRAMS** - Execute every [[LLM:]] instruction exactly as written
10
+ 2. **NEVER show markup** - Hide all [[LLM:]], {{placeholders}}, @{examples}, and template syntax
11
+ 3. **STOP and EXECUTE** - When you see "apply tasks#" or "execute tasks#", STOP and run that task immediately
12
+ 4. **WAIT for user input** - At review points and after elicitation tasks
10
13
 
11
- - Determine which template to use (user-provided or list available for selection to user)
14
+ ## Execution Flow
12
15
 
13
- - Agent-specific templates are listed in the agent's dependencies under `templates`. For each template listed, consider it a document the agent can create. So if an agent has:
16
+ ### 1. Identify Template
14
17
 
15
- @{example}
16
- dependencies:
17
- templates: - prd-tmpl - architecture-tmpl
18
- @{/example}
18
+ - Load from `templates#*` or `{root}/templates directory`
19
+ - Agent-specific templates are listed in agent's dependencies
20
+ - If agent has `templates: [prd-tmpl, architecture-tmpl]`, offer to create "PRD" and "Architecture" documents
19
21
 
20
- You would offer to create "PRD" and "Architecture" documents when the user asks what you can help with.
22
+ ### 2. Ask Interaction Mode
21
23
 
22
- - Gather all relevant inputs, or ask for them, or else rely on user providing necessary details to complete the document
23
- - Understand the document purpose and target audience
24
-
25
- ### 2. Determine Interaction Mode
26
-
27
- Confirm with the user their preferred interaction style:
28
-
29
- - **Incremental:** Work through chunks of the document.
30
- - **YOLO Mode:** Draft complete document making reasonable assumptions in one shot. (Can be entered also after starting incremental by just typing /yolo)
24
+ > 1. **Incremental** - Section by section with reviews
25
+ > 2. **YOLO Mode** - Complete draft then review (user can type `/yolo` anytime to switch)
31
26
 
32
27
  ### 3. Execute Template
33
28
 
34
- - Load specified template from `templates#*` or the `{root}/templates directory`
35
- - Follow ALL embedded LLM instructions within the template
36
- - Process template markup according to `utils#template-format` or `{root}/utils/template-format` conventions
29
+ - Replace {{placeholders}} with real content
30
+ - Execute [[LLM:]] instructions as you encounter them
31
+ - Process <<REPEAT>> loops and ^^CONDITIONS^^
32
+ - Use @{examples} for guidance but never output them
37
33
 
38
- ### 4. Template Processing Rules
34
+ ### 4. Key Execution Patterns
39
35
 
40
- #### CRITICAL: Never display template markup, LLM instructions, or examples to users
36
+ **When you see:** `[[LLM: Draft X and immediately execute tasks#advanced-elicitation]]`
41
37
 
42
- - Replace all {{placeholders}} with actual content
43
- - Execute all [[LLM: instructions]] internally
44
- - Process `<<REPEAT>>` sections as needed
45
- - Evaluate ^^CONDITION^^ blocks and include only if applicable
46
- - Use @{examples} for guidance but never output them
38
+ - Draft the content
39
+ - Present it to user
40
+ - IMMEDIATELY execute the task
41
+ - Wait for completion before continuing
47
42
 
48
- ### 5. Content Generation
43
+ **When you see:** `[[LLM: After section completion, apply tasks#Y]]`
49
44
 
50
- - **Incremental Mode**: Present each major section for review before proceeding
51
- - **YOLO Mode**: Generate all sections, then review complete document with user
52
- - Apply any elicitation protocols specified in template
53
- - Incorporate user feedback and iterate as needed
45
+ - Finish the section
46
+ - STOP and execute the task
47
+ - Wait for user input
54
48
 
55
- ### 6. Validation
49
+ ### 5. Validation & Final Presentation
56
50
 
57
- If template specifies a checklist:
51
+ - Run any specified checklists
52
+ - Present clean, formatted content only
53
+ - No truncation or summarization
54
+ - Begin directly with content (no preamble)
55
+ - Include any handoff prompts from template
58
56
 
59
- - Run the appropriate checklist against completed document
60
- - Document completion status for each item
61
- - Address any deficiencies found
62
- - Present validation summary to user
57
+ ## Common Mistakes to Avoid
63
58
 
64
- ### 7. Final Presentation
59
+ Skipping elicitation tasks
60
+ ❌ Showing template markup to users
61
+ ❌ Continuing past STOP signals
62
+ ❌ Combining multiple review points
65
63
 
66
- - Present clean, formatted content only
67
- - Ensure all sections are complete
68
- - DO NOT truncate or summarize content
69
- - Begin directly with document content (no preamble)
70
- - Include any handoff prompts specified in template
64
+ Execute ALL instructions in sequence
65
+ Present only clean, formatted content
66
+ Stop at every elicitation point
67
+ Wait for user confirmation when instructed
71
68
 
72
- ## Important Notes
69
+ ## Remember
73
70
 
74
- - Template markup is for AI processing only - never expose to users
71
+ Templates contain precise instructions for a reason. Follow them exactly to ensure document quality and completeness.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bmad-method",
3
- "version": "4.21.0",
3
+ "version": "4.21.2",
4
4
  "description": "Breakthrough Method of Agile AI-driven Development",
5
5
  "main": "tools/cli.js",
6
6
  "bin": {
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bmad-method",
3
- "version": "4.21.0",
3
+ "version": "4.21.2",
4
4
  "description": "BMAD Method installer - AI-powered Agile development framework",
5
5
  "main": "lib/installer.js",
6
6
  "bin": {