mirror of
https://github.com/bmadcode/BMAD-METHOD.git
synced 2025-12-18 02:05:30 +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**Deleted Bloated/Outdated Docs (2,651 lines removed):**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- Outdated workflow guides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>
391 lines
12 KiB
JavaScript
391 lines
12 KiB
JavaScript
/**
|
|
* BMAD Agent Compiler
|
|
* Transforms agent YAML to compiled XML (.md) format
|
|
* Uses the existing BMAD builder infrastructure for proper formatting
|
|
*/
|
|
|
|
const yaml = require('yaml');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
const { processAgentYaml, extractInstallConfig, stripInstallConfig, getDefaultValues } = require('./template-engine');
|
|
|
|
// Use existing BMAD builder if available
|
|
let YamlXmlBuilder;
|
|
try {
|
|
YamlXmlBuilder = require('../../lib/yaml-xml-builder').YamlXmlBuilder;
|
|
} catch {
|
|
YamlXmlBuilder = null;
|
|
}
|
|
|
|
/**
|
|
* Escape XML special characters
|
|
*/
|
|
function escapeXml(text) {
|
|
if (!text) return '';
|
|
return text.replaceAll('&', '&').replaceAll('<', '<').replaceAll('>', '>').replaceAll('"', '"').replaceAll("'", ''');
|
|
}
|
|
|
|
/**
|
|
* Build frontmatter for agent
|
|
* @param {Object} metadata - Agent metadata
|
|
* @param {string} agentName - Final agent name
|
|
* @returns {string} YAML frontmatter
|
|
*/
|
|
function buildFrontmatter(metadata, agentName) {
|
|
const nameFromFile = agentName.replaceAll('-', ' ');
|
|
const description = metadata.title || 'BMAD Agent';
|
|
|
|
return `---
|
|
name: "${nameFromFile}"
|
|
description: "${description}"
|
|
---
|
|
|
|
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
|
|
|
|
`;
|
|
}
|
|
|
|
/**
|
|
* Build simple activation block for custom agents
|
|
* @param {Array} criticalActions - Agent-specific critical actions
|
|
* @param {Array} menuItems - Menu items to determine which handlers to include
|
|
* @returns {string} Activation XML
|
|
*/
|
|
function buildSimpleActivation(criticalActions = [], menuItems = []) {
|
|
let activation = '<activation critical="MANDATORY">\n';
|
|
|
|
let stepNum = 1;
|
|
|
|
// Standard steps
|
|
activation += ` <step n="${stepNum++}">Load persona from this current agent file (already in context)</step>\n`;
|
|
activation += ` <step n="${stepNum++}">Load and read {project-root}/{bmad_folder}/core/config.yaml to get {user_name}, {communication_language}, {output_folder}</step>\n`;
|
|
activation += ` <step n="${stepNum++}">Remember: user's name is {user_name}</step>\n`;
|
|
|
|
// Agent-specific steps from critical_actions
|
|
for (const action of criticalActions) {
|
|
activation += ` <step n="${stepNum++}">${action}</step>\n`;
|
|
}
|
|
|
|
// Menu and interaction steps
|
|
activation += ` <step n="${stepNum++}">ALWAYS communicate in {communication_language}</step>\n`;
|
|
activation += ` <step n="${stepNum++}">Show greeting using {user_name} from config, communicate in {communication_language}, then display numbered list of
|
|
ALL menu items from menu section</step>\n`;
|
|
activation += ` <step n="${stepNum++}">STOP and WAIT for user input - do NOT execute menu items automatically - accept number or cmd trigger or fuzzy command
|
|
match</step>\n`;
|
|
activation += ` <step n="${stepNum++}">On user input: Number → execute menu item[n] | Text → case-insensitive substring match | Multiple matches → ask user
|
|
to clarify | No match → show "Not recognized"</step>\n`;
|
|
|
|
// Detect which handlers are actually used
|
|
const usedHandlers = new Set();
|
|
for (const item of menuItems) {
|
|
if (item.action) usedHandlers.add('action');
|
|
if (item.workflow) usedHandlers.add('workflow');
|
|
if (item.exec) usedHandlers.add('exec');
|
|
if (item.tmpl) usedHandlers.add('tmpl');
|
|
}
|
|
|
|
// Only include menu-handlers section if handlers are used
|
|
if (usedHandlers.size > 0) {
|
|
activation += ` <step n="${stepNum++}">When executing a menu item: Check menu-handlers section below - extract any attributes from the selected menu item and follow the corresponding handler instructions</step>\n`;
|
|
|
|
// Menu handlers - only include what's used
|
|
activation += `
|
|
<menu-handlers>
|
|
<handlers>\n`;
|
|
|
|
if (usedHandlers.has('action')) {
|
|
activation += ` <handler type="action">
|
|
When menu item has: action="#id" → Find prompt with id="id" in current agent XML, execute its content
|
|
When menu item has: action="text" → Execute the text directly as an inline instruction
|
|
</handler>\n`;
|
|
}
|
|
|
|
if (usedHandlers.has('workflow')) {
|
|
activation += ` <handler type="workflow">
|
|
When menu item has: workflow="path/to/workflow.yaml"
|
|
1. CRITICAL: Always LOAD {project-root}/{bmad_folder}/core/tasks/workflow.xml
|
|
2. Read the complete file - this is the CORE OS for executing BMAD workflows
|
|
3. Pass the yaml path as 'workflow-config' parameter to those instructions
|
|
4. Execute workflow.xml instructions precisely following all steps
|
|
5. Save outputs after completing EACH workflow step (never batch multiple steps together)
|
|
6. If workflow.yaml path is "todo", inform user the workflow hasn't been implemented yet
|
|
</handler>\n`;
|
|
}
|
|
|
|
if (usedHandlers.has('exec')) {
|
|
activation += ` <handler type="exec">
|
|
When menu item has: exec="command" → Execute the command directly
|
|
</handler>\n`;
|
|
}
|
|
|
|
if (usedHandlers.has('tmpl')) {
|
|
activation += ` <handler type="tmpl">
|
|
When menu item has: tmpl="template-path" → Load and apply the template
|
|
</handler>\n`;
|
|
}
|
|
|
|
activation += ` </handlers>
|
|
</menu-handlers>\n`;
|
|
}
|
|
|
|
activation += `
|
|
<rules>
|
|
- ALWAYS communicate in {communication_language} UNLESS contradicted by communication_style
|
|
- Stay in character until exit selected
|
|
- Menu triggers use asterisk (*) - NOT markdown, display exactly as shown
|
|
- Number all lists, use letters for sub-options
|
|
- Load files ONLY when executing menu items or a workflow or command requires it. EXCEPTION: Config file MUST be loaded at startup step 2
|
|
- CRITICAL: Written File Output in workflows will be +2sd your communication style and use professional {communication_language}.
|
|
</rules>
|
|
</activation>\n`;
|
|
|
|
return activation;
|
|
}
|
|
|
|
/**
|
|
* Build persona XML section
|
|
* @param {Object} persona - Persona object
|
|
* @returns {string} Persona XML
|
|
*/
|
|
function buildPersonaXml(persona) {
|
|
if (!persona) return '';
|
|
|
|
let xml = ' <persona>\n';
|
|
|
|
if (persona.role) {
|
|
const roleText = persona.role.trim().replaceAll(/\n+/g, ' ').replaceAll(/\s+/g, ' ');
|
|
xml += ` <role>${escapeXml(roleText)}</role>\n`;
|
|
}
|
|
|
|
if (persona.identity) {
|
|
const identityText = persona.identity.trim().replaceAll(/\n+/g, ' ').replaceAll(/\s+/g, ' ');
|
|
xml += ` <identity>${escapeXml(identityText)}</identity>\n`;
|
|
}
|
|
|
|
if (persona.communication_style) {
|
|
const styleText = persona.communication_style.trim().replaceAll(/\n+/g, ' ').replaceAll(/\s+/g, ' ');
|
|
xml += ` <communication_style>${escapeXml(styleText)}</communication_style>\n`;
|
|
}
|
|
|
|
if (persona.principles) {
|
|
let principlesText;
|
|
if (Array.isArray(persona.principles)) {
|
|
principlesText = persona.principles.join(' ');
|
|
} else {
|
|
principlesText = persona.principles.trim().replaceAll(/\n+/g, ' ');
|
|
}
|
|
xml += ` <principles>${escapeXml(principlesText)}</principles>\n`;
|
|
}
|
|
|
|
xml += ' </persona>\n';
|
|
|
|
return xml;
|
|
}
|
|
|
|
/**
|
|
* Build prompts XML section
|
|
* @param {Array} prompts - Prompts array
|
|
* @returns {string} Prompts XML
|
|
*/
|
|
function buildPromptsXml(prompts) {
|
|
if (!prompts || prompts.length === 0) return '';
|
|
|
|
let xml = ' <prompts>\n';
|
|
|
|
for (const prompt of prompts) {
|
|
xml += ` <prompt id="${prompt.id || ''}">\n`;
|
|
xml += ` <content>\n`;
|
|
// Don't escape prompt content - it's meant to be read as-is
|
|
xml += `${prompt.content || ''}\n`;
|
|
xml += ` </content>\n`;
|
|
xml += ` </prompt>\n`;
|
|
}
|
|
|
|
xml += ' </prompts>\n';
|
|
|
|
return xml;
|
|
}
|
|
|
|
/**
|
|
* Build menu XML section
|
|
* @param {Array} menuItems - Menu items
|
|
* @returns {string} Menu XML
|
|
*/
|
|
function buildMenuXml(menuItems) {
|
|
let xml = ' <menu>\n';
|
|
|
|
// Always inject *help first
|
|
xml += ` <item cmd="*help">Show numbered menu</item>\n`;
|
|
|
|
// Add user-defined menu items
|
|
if (menuItems && menuItems.length > 0) {
|
|
for (const item of menuItems) {
|
|
let trigger = item.trigger || '';
|
|
if (!trigger.startsWith('*')) {
|
|
trigger = '*' + trigger;
|
|
}
|
|
|
|
const attrs = [`cmd="${trigger}"`];
|
|
|
|
// Add handler attributes
|
|
if (item.workflow) attrs.push(`workflow="${item.workflow}"`);
|
|
if (item.exec) attrs.push(`exec="${item.exec}"`);
|
|
if (item.tmpl) attrs.push(`tmpl="${item.tmpl}"`);
|
|
if (item.data) attrs.push(`data="${item.data}"`);
|
|
if (item.action) attrs.push(`action="${item.action}"`);
|
|
|
|
xml += ` <item ${attrs.join(' ')}>${escapeXml(item.description || '')}</item>\n`;
|
|
}
|
|
}
|
|
|
|
// Always inject *exit last
|
|
xml += ` <item cmd="*exit">Exit with confirmation</item>\n`;
|
|
|
|
xml += ' </menu>\n';
|
|
|
|
return xml;
|
|
}
|
|
|
|
/**
|
|
* Compile agent YAML to proper XML format
|
|
* @param {Object} agentYaml - Parsed and processed agent YAML
|
|
* @param {string} agentName - Final agent name (for ID and frontmatter)
|
|
* @param {string} targetPath - Target path for agent ID
|
|
* @returns {string} Compiled XML string with frontmatter
|
|
*/
|
|
function compileToXml(agentYaml, agentName = '', targetPath = '') {
|
|
const agent = agentYaml.agent;
|
|
const meta = agent.metadata;
|
|
|
|
let xml = '';
|
|
|
|
// Build frontmatter
|
|
xml += buildFrontmatter(meta, agentName || meta.name || 'agent');
|
|
|
|
// Start code fence
|
|
xml += '```xml\n';
|
|
|
|
// Agent opening tag
|
|
const agentAttrs = [
|
|
`id="${targetPath || meta.id || ''}"`,
|
|
`name="${meta.name || ''}"`,
|
|
`title="${meta.title || ''}"`,
|
|
`icon="${meta.icon || '🤖'}"`,
|
|
];
|
|
|
|
xml += `<agent ${agentAttrs.join(' ')}>\n`;
|
|
|
|
// Activation block - pass menu items to determine which handlers to include
|
|
xml += buildSimpleActivation(agent.critical_actions || [], agent.menu || []);
|
|
|
|
// Persona section
|
|
xml += buildPersonaXml(agent.persona);
|
|
|
|
// Prompts section (if present)
|
|
if (agent.prompts && agent.prompts.length > 0) {
|
|
xml += buildPromptsXml(agent.prompts);
|
|
}
|
|
|
|
// Menu section
|
|
xml += buildMenuXml(agent.menu || []);
|
|
|
|
// Closing agent tag
|
|
xml += '</agent>\n';
|
|
|
|
// Close code fence
|
|
xml += '```\n';
|
|
|
|
return xml;
|
|
}
|
|
|
|
/**
|
|
* Full compilation pipeline
|
|
* @param {string} yamlContent - Raw YAML string
|
|
* @param {Object} answers - Answers from install_config questions (or defaults)
|
|
* @param {string} agentName - Optional final agent name (user's custom persona name)
|
|
* @param {string} targetPath - Optional target path for agent ID
|
|
* @returns {Object} { xml: string, metadata: Object }
|
|
*/
|
|
function compileAgent(yamlContent, answers = {}, agentName = '', targetPath = '') {
|
|
// Parse YAML
|
|
const agentYaml = yaml.parse(yamlContent);
|
|
|
|
// Inject custom agent name into metadata.name if provided
|
|
// This is the user's chosen persona name (e.g., "Fred" instead of "Inkwell Von Comitizen")
|
|
if (agentName && agentYaml.agent && agentYaml.agent.metadata) {
|
|
// Convert kebab-case to title case for the name field
|
|
// e.g., "fred-commit-poet" → "Fred Commit Poet"
|
|
const titleCaseName = agentName
|
|
.split('-')
|
|
.map((word) => word.charAt(0).toUpperCase() + word.slice(1))
|
|
.join(' ');
|
|
agentYaml.agent.metadata.name = titleCaseName;
|
|
}
|
|
|
|
// Extract install_config
|
|
const installConfig = extractInstallConfig(agentYaml);
|
|
|
|
// Merge defaults with provided answers
|
|
let finalAnswers = answers;
|
|
if (installConfig) {
|
|
const defaults = getDefaultValues(installConfig);
|
|
finalAnswers = { ...defaults, ...answers };
|
|
}
|
|
|
|
// Process templates with answers
|
|
const processedYaml = processAgentYaml(agentYaml, finalAnswers);
|
|
|
|
// Strip install_config from output
|
|
const cleanYaml = stripInstallConfig(processedYaml);
|
|
|
|
// Compile to XML
|
|
const xml = compileToXml(cleanYaml, agentName, targetPath);
|
|
|
|
return {
|
|
xml,
|
|
metadata: cleanYaml.agent.metadata,
|
|
processedYaml: cleanYaml,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Compile agent file to .md
|
|
* @param {string} yamlPath - Path to agent YAML file
|
|
* @param {Object} options - { answers: {}, outputPath: string }
|
|
* @returns {Object} Compilation result
|
|
*/
|
|
function compileAgentFile(yamlPath, options = {}) {
|
|
const yamlContent = fs.readFileSync(yamlPath, 'utf8');
|
|
const result = compileAgent(yamlContent, options.answers || {});
|
|
|
|
// Determine output path
|
|
let outputPath = options.outputPath;
|
|
if (!outputPath) {
|
|
// Default: same directory, same name, .md extension
|
|
const dir = path.dirname(yamlPath);
|
|
const basename = path.basename(yamlPath, '.agent.yaml');
|
|
outputPath = path.join(dir, `${basename}.md`);
|
|
}
|
|
|
|
// Write compiled XML
|
|
fs.writeFileSync(outputPath, result.xml, 'utf8');
|
|
|
|
return {
|
|
...result,
|
|
outputPath,
|
|
sourcePath: yamlPath,
|
|
};
|
|
}
|
|
|
|
module.exports = {
|
|
compileToXml,
|
|
compileAgent,
|
|
compileAgentFile,
|
|
escapeXml,
|
|
buildFrontmatter,
|
|
buildSimpleActivation,
|
|
buildPersonaXml,
|
|
buildPromptsXml,
|
|
buildMenuXml,
|
|
};
|