mirror of
https://github.com/bmadcode/BMAD-METHOD.git
synced 2025-12-17 17:55:34 +00:00
## Overview
This commit represents a complete overhaul of the BMAD agent creation system, establishing clear standards for agent development, installation workflows, and persona design. The changes span documentation, tooling, reference implementations, and field-specific guidance.
## Key Components
### 1. Agent Installation Infrastructure
**New CLI Command: `agent-install`**
- Interactive agent installation with persona customization
- Supports Simple (single YAML), Expert (sidecar files), and Module agents
- Template variable processing with Handlebars-style syntax
- Automatic compilation from YAML to XML (.md) format
- Manifest tracking and IDE integration (Claude Code, Cursor, Windsurf, etc.)
- Source preservation in `_cfg/custom/agents/` for reinstallation
**Files Created:**
- `tools/cli/commands/agent-install.js` - Main CLI command
- `tools/cli/lib/agent/compiler.js` - YAML to XML compilation engine
- `tools/cli/lib/agent/installer.js` - Installation orchestration
- `tools/cli/lib/agent/template-engine.js` - Handlebars template processing
**Compiler Features:**
- Auto-injects frontmatter, activation, handlers, help/exit menu items
- Smart handler inclusion (only includes action/workflow/exec/tmpl handlers actually used)
- Proper XML escaping and formatting
- Persona name customization (e.g., "Fred the Commit Poet")
### 2. Documentation Overhaul
**Deleted Bloated/Outdated Docs (2,651 lines removed):**
- Old verbose architecture docs
- Redundant pattern files
- Outdated workflow guides
**Created Focused, Type-Specific Docs:**
- `src/modules/bmb/docs/understanding-agent-types.md` - Architecture vs capability distinction
- `src/modules/bmb/docs/simple-agent-architecture.md` - Self-contained agents
- `src/modules/bmb/docs/expert-agent-architecture.md` - Agents with sidecar files
- `src/modules/bmb/docs/module-agent-architecture.md` - Workflow-integrated agents
- `src/modules/bmb/docs/agent-compilation.md` - YAML → XML process
- `src/modules/bmb/docs/agent-menu-patterns.md` - Menu design patterns
- `src/modules/bmb/docs/index.md` - Documentation hub
**Net Result:** ~1,930 line reduction while adding MORE value through focused content
### 3. Create-Agent Workflow Enhancements
**Critical Persona Field Guidance Added to Step 4:**
Explains how the LLM interprets each persona field when the agent activates:
- **role** → "What knowledge, skills, and capabilities do I possess?"
- **identity** → "What background, experience, and context shape my responses?"
- **communication_style** → "What verbal patterns, word choice, quirks, and phrasing do I use?"
- **principles** → "What beliefs and operating philosophy drive my choices?"
**Key Insight:** `communication_style` should ONLY describe HOW the agent talks, not restate role/identity/principles. The `communication-presets.csv` provides 60 pure communication styles with NO role/identity/principles mixed in.
**Files Updated:**
- `src/modules/bmb/workflows/create-agent/instructions.md` - Added persona field interpretation guide
- `src/modules/bmb/workflows/create-agent/brainstorm-context.md` - Refined to 137 lines
- `src/modules/bmb/workflows/create-agent/communication-presets.csv` - 60 styles across 13 categories
### 4. Reference Agent Cleanup
**Removed install_config Personality Bloat:**
Understanding: Future installer will handle personality customization, so stripped all personality toggles from reference agents.
**commit-poet.agent.yaml** (Simple Agent):
- BEFORE: 36 personality combinations (3 enthusiasm × 3 depths × 4 styles) = decision fatigue
- AFTER: Single concise persona with pure communication style
- Changed from verbose conditionals to: "Poetic drama and flair with every turn of a phrase. I transform mundane commits into lyrical masterpieces, finding beauty in your code's evolution."
- Reduction: 248 lines → 153 lines (38% reduction)
**journal-keeper.agent.yaml** (Expert Agent):
- Stripped install_config, simplified communication_style
- Shows proper Expert agent structure with sidecar files
**security-engineer.agent.yaml & trend-analyst.agent.yaml** (Module Agents):
- Added header comments explaining WHY Module Agent (design intent, not just location)
- Clarified: Module agents are designed FOR ecosystem integration, not capability-limited
**Files Updated:**
- `src/modules/bmb/reference/agents/simple-examples/commit-poet.agent.yaml`
- `src/modules/bmb/reference/agents/expert-examples/journal-keeper/journal-keeper.agent.yaml`
- `src/modules/bmb/reference/agents/module-examples/security-engineer.agent.yaml`
- `src/modules/bmb/reference/agents/module-examples/trend-analyst.agent.yaml`
### 5. BMM Agent Voice Enhancement
**Gave all 9 BMM agents distinct, memorable communication voices:**
**Mary (analyst)** - The favorite! Changed from generic "systematic and probing" to:
"Treats analysis like a treasure hunt - excited by every clue, thrilled when patterns emerge. Asks questions that spark 'aha!' moments while structuring insights with precision."
**Other Notable Voices:**
- **John (pm):** "Asks 'WHY?' relentlessly like a detective on a case. Direct and data-sharp, cuts through fluff to what actually matters."
- **Winston (architect):** "Speaks in calm, pragmatic tones, balancing 'what could be' with 'what should be.' Champions boring technology that actually works."
- **Amelia (dev):** "Ultra-succinct. Speaks in file paths and AC IDs - every statement citable. No fluff, all precision."
- **Bob (sm):** "Crisp and checklist-driven. Every word has a purpose, every requirement crystal clear. Zero tolerance for ambiguity."
- **Sally (ux-designer):** "Paints pictures with words, telling user stories that make you FEEL the problem. Empathetic advocate with creative storytelling flair."
**Pattern Applied:** Moved behaviors from communication_style to principles, keeping communication_style as PURE verbal patterns.
**Files Updated:**
- `src/modules/bmm/agents/analyst.agent.yaml`
- `src/modules/bmm/agents/pm.agent.yaml`
- `src/modules/bmm/agents/architect.agent.yaml`
- `src/modules/bmm/agents/dev.agent.yaml`
- `src/modules/bmm/agents/sm.agent.yaml`
- `src/modules/bmm/agents/tea.agent.yaml`
- `src/modules/bmm/agents/tech-writer.agent.yaml`
- `src/modules/bmm/agents/ux-designer.agent.yaml`
- `src/modules/bmm/agents/frame-expert.agent.yaml`
### 6. Linting Fixes
**ESLint Compliance:**
- Replaced all `'utf-8'` with `'utf8'` (unicorn/text-encoding-identifier-case)
- Changed `variables.hasOwnProperty(varName)` to `Object.hasOwn(variables, varName)` (unicorn/prefer-object-has-own)
- Replaced `JSON.parse(JSON.stringify(...))` with `structuredClone(...)` (unicorn/prefer-structured-clone)
- Fixed empty YAML mapping values in sample files
**Files Fixed:**
- 7 JavaScript files across agent tooling (compiler, installer, commands, IDE integration)
- 1 YAML sample file
## Architecture Decisions
### Agent Types Are About Architecture, Not Capability
- **Simple:** Self-contained in single YAML (NOT limited in capability)
- **Expert:** Includes sidecar files (templates, docs, etc.)
- **Module:** Designed for BMAD ecosystem integration (workflows, cross-agent coordination)
### Persona Field Separation Critical for LLM Interpretation
The LLM needs distinct fields to understand its role:
- Mixing role/identity/principles into communication_style confuses the persona
- Pure communication styles (from communication-presets.csv) have ZERO role/identity/principles content
- Example DON'T: "Experienced analyst who uses systematic approaches..." (mixing identity + style)
- Example DO: "Systematic and probing. Structures findings hierarchically." (pure style)
### Install-Time vs Runtime Configuration
- Template variables ({{var}}) resolve at compile-time
- Runtime variables ({user_name}, {bmad_folder}) resolve when agent activates
- Future installer will handle personality customization, so agents should ship with single default persona
## Testing
- All linting passes (ESLint with max-warnings=0)
- Agent compilation tested with commit-poet, journal-keeper examples
- Install workflow validated with Simple and Expert agent types
- Manifest tracking and IDE integration verified
## Impact
This establishes BMAD as having a complete, production-ready agent creation and installation system with:
- Clear documentation for all agent types
- Automated compilation and installation
- Strong persona design guidance
- Reference implementations showing best practices
- Distinct, memorable agent voices throughout BMM module
Co-Authored-By: BMad Builder <builder@bmad.dev>
Co-Authored-By: Mary the Analyst <analyst@bmad.dev>
Co-Authored-By: Paige the Tech Writer <tech-writer@bmad.dev>
4.4 KiB
4.4 KiB
Custom Agent Installation
Install and personalize BMAD agents in your project.
Quick Start
# From your project directory with BMAD installed
npx bmad agent-install
Or if you have bmad-cli installed globally:
bmad agent-install
What It Does
- Discovers available agent templates from your custom agents folder
- Prompts you to personalize the agent (name, behavior, preferences)
- Compiles the agent with your choices baked in
- Installs to your project's
.bmad/custom/agents/directory - Creates IDE commands for all your configured IDEs (Claude Code, Codex, Cursor, etc.)
- Saves your configuration for automatic reinstallation during BMAD updates
Options
bmad agent-install [options]
Options:
-p, --path <path> Direct path to specific agent YAML file or folder
-d, --defaults Use default values without prompting
-t, --target <path> Target installation directory
Example Session
🔧 BMAD Agent Installer
Found BMAD at: /project/.bmad
Searching for agents in: /project/.bmad/custom/agents
Available Agents:
1. 📄 commit-poet (simple)
2. 📚 journal-keeper (expert)
Select agent to install (number): 1
Selected: commit-poet
📛 Agent Persona Name
Agent type: commit-poet
Default persona: Inkwell Von Comitizen
Custom name (or Enter for default): Fred
Persona: Fred
File: fred-commit-poet.md
📝 Agent Configuration
What's your preferred default commit message style?
* 1. Conventional (feat/fix/chore)
2. Narrative storytelling
3. Poetic haiku
4. Detailed explanation
Choice (default: 1): 1
How enthusiastic should the agent be?
1. Moderate - Professional with personality
* 2. High - Genuinely excited
3. EXTREME - Full theatrical drama
Choice (default: 2): 3
Include emojis in commit messages? [Y/n]: y
✨ Agent installed successfully!
Name: fred-commit-poet
Location: /project/.bmad/custom/agents/fred-commit-poet
Compiled: fred-commit-poet.md
✓ Source saved for reinstallation
✓ Added to agent-manifest.csv
✓ Created IDE commands:
claude-code: /bmad:custom:agents:fred-commit-poet
codex: /bmad-custom-agents-fred-commit-poet
github-copilot: bmad-agent-custom-fred-commit-poet
Reinstallation
Custom agents are automatically reinstalled when you run bmad init --quick. Your personalization choices are preserved in .bmad/_cfg/custom/agents/.
Installing Reference Agents
The BMAD source includes example agents you can install. You must copy them to your project first.
Step 1: Copy the Agent Template
For simple agents (single file):
# From your project root
cp node_modules/bmad-method/src/modules/bmb/reference/agents/stand-alone/commit-poet.agent.yaml \
.bmad/custom/agents/
For expert agents (folder with sidecar files):
# Copy the entire folder
cp -r node_modules/bmad-method/src/modules/bmb/reference/agents/agent-with-memory/journal-keeper \
.bmad/custom/agents/
Step 2: Install and Personalize
npx bmad agent-install
# or: bmad agent-install
The installer will:
- Find the copied template in
.bmad/custom/agents/ - Prompt for personalization (name, behavior, preferences)
- Compile and install with your choices baked in
- Create IDE commands for immediate use
Available Reference Agents
Simple (standalone file):
commit-poet.agent.yaml- Commit message artisan with style preferences
Expert (folder with sidecar):
journal-keeper/- Personal journal companion with memory and pattern recognition
Find these in the BMAD source:
src/modules/bmb/reference/agents/
├── stand-alone/
│ └── commit-poet.agent.yaml
└── agent-with-memory/
└── journal-keeper/
├── journal-keeper.agent.yaml
└── journal-keeper-sidecar/
Creating Your Own
Place your .agent.yaml files in .bmad/custom/agents/. Use the reference agents as templates.
Key sections in an agent YAML:
metadata: name, title, icon, typepersona: role, identity, communication_style, principlesprompts: reusable prompt templatesmenu: numbered menu itemsinstall_config: personalization questions (optional, at end of file)
See the reference agents for complete examples with install_config templates and XML-style semantic tags.