feat: Complete BMAD agent creation system with install tooling, references, and field guidance

## 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**Deleted Bloated/Outdated Docs (2,651 lines removed):**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- Outdated workflow guides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>
This commit is contained in:
Brian Madison
2025-11-17 22:25:15 -06:00
parent 7b7f984cd2
commit 054b031c1d
58 changed files with 5845 additions and 2622 deletions

View File

@@ -840,6 +840,15 @@ class Installer {
console.log(chalk.dim('Review the .bak files to see your changes and merge if needed.\n'));
}
// Reinstall custom agents from _cfg/custom/agents/ sources
const customAgentResults = await this.reinstallCustomAgents(projectDir, bmadDir);
if (customAgentResults.count > 0) {
console.log(chalk.green(`\n✓ Reinstalled ${customAgentResults.count} custom agent${customAgentResults.count > 1 ? 's' : ''}`));
for (const agent of customAgentResults.agents) {
console.log(chalk.dim(` - ${agent}`));
}
}
// Display completion message
const { UI } = require('../../../lib/ui');
const ui = new UI();
@@ -2245,6 +2254,116 @@ class Installer {
return nodes;
}
/**
* Reinstall custom agents from _cfg/custom/agents/ sources
* This preserves custom agents across quick updates/reinstalls
* @param {string} projectDir - Project directory
* @param {string} bmadDir - BMAD installation directory
* @returns {Object} Result with count and agent names
*/
async reinstallCustomAgents(projectDir, bmadDir) {
const customAgentsCfgDir = path.join(bmadDir, '_cfg', 'custom', 'agents');
const results = { count: 0, agents: [] };
if (!(await fs.pathExists(customAgentsCfgDir))) {
return results;
}
try {
const {
discoverAgents,
loadAgentConfig,
extractManifestData,
addToManifest,
createIdeSlashCommands,
updateManifestYaml,
} = require('../../../lib/agent/installer');
const { compileAgent } = require('../../../lib/agent/compiler');
// Discover custom agents in _cfg/custom/agents/
const agents = discoverAgents(customAgentsCfgDir);
if (agents.length === 0) {
return results;
}
const customAgentsDir = path.join(bmadDir, 'custom', 'agents');
await fs.ensureDir(customAgentsDir);
const manifestFile = path.join(bmadDir, '_cfg', 'agent-manifest.csv');
const manifestYamlFile = path.join(bmadDir, '_cfg', 'manifest.yaml');
for (const agent of agents) {
try {
const agentConfig = loadAgentConfig(agent.yamlFile);
const finalAgentName = agent.name; // Already named correctly from save
// Determine agent type from the name (e.g., "fred-commit-poet" → "commit-poet")
let agentType = finalAgentName;
const parts = finalAgentName.split('-');
if (parts.length >= 2) {
// Try to extract type (last part or last two parts)
// For "fred-commit-poet", we want "commit-poet"
// This is heuristic - could be improved with metadata storage
agentType = parts.slice(-2).join('-'); // Take last 2 parts as type
}
// Create target directory
const agentTargetDir = path.join(customAgentsDir, finalAgentName);
await fs.ensureDir(agentTargetDir);
// Calculate paths
const compiledFileName = `${finalAgentName}.md`;
const compiledPath = path.join(agentTargetDir, compiledFileName);
const relativePath = path.relative(projectDir, compiledPath);
// Compile with embedded defaults (answers are already in defaults section)
const { xml, metadata } = compileAgent(
await fs.readFile(agent.yamlFile, 'utf8'),
agentConfig.defaults || {},
finalAgentName,
relativePath,
);
// Write compiled agent
await fs.writeFile(compiledPath, xml, 'utf8');
// Copy sidecar files if expert agent
if (agent.hasSidecar && agent.type === 'expert') {
const { copySidecarFiles } = require('../../../lib/agent/installer');
copySidecarFiles(agent.path, agentTargetDir, agent.yamlFile);
}
// Update manifest CSV
if (await fs.pathExists(manifestFile)) {
const manifestData = extractManifestData(xml, { ...metadata, name: finalAgentName }, relativePath, 'custom');
manifestData.name = finalAgentName;
manifestData.displayName = metadata.name || finalAgentName;
manifestData.path = relativePath;
addToManifest(manifestFile, manifestData);
}
// Create IDE slash commands (async function)
await createIdeSlashCommands(projectDir, finalAgentName, relativePath, metadata);
// Update manifest.yaml
if (await fs.pathExists(manifestYamlFile)) {
updateManifestYaml(manifestYamlFile, finalAgentName, agentType);
}
results.count++;
results.agents.push(finalAgentName);
} catch (agentError) {
console.log(chalk.yellow(` ⚠️ Failed to reinstall ${agent.name}: ${agentError.message}`));
}
}
} catch (error) {
console.log(chalk.yellow(` ⚠️ Error reinstalling custom agents: ${error.message}`));
}
return results;
}
/**
* Copy IDE-specific documentation to BMAD docs
* @param {Array} ides - List of selected IDEs

View File

@@ -73,6 +73,19 @@ class BaseIdeSetup {
}
}
/**
* Install a custom agent launcher - subclasses should override
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command, or null if not supported
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
// Default implementation - subclasses can override
return null;
}
/**
* Detect whether this IDE already has configuration in the project
* Subclasses can override for custom logic

View File

@@ -466,6 +466,49 @@ class ClaudeCodeSetup extends BaseIdeSetup {
console.log(chalk.dim(` Total subagents installed: ${copiedCount}`));
}
}
/**
* Install a custom agent launcher for Claude Code
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const customAgentsDir = path.join(projectDir, this.configDir, this.commandsDir, 'bmad', 'custom', 'agents');
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
return null; // IDE not configured for this project
}
await this.ensureDir(customAgentsDir);
const launcherContent = `---
name: '${agentName}'
description: '${agentName} agent'
---
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
const launcherPath = path.join(customAgentsDir, `${agentName}.md`);
await this.writeFile(launcherPath, launcherContent);
return {
path: launcherPath,
command: `/bmad:custom:agents:${agentName}`,
};
}
}
module.exports = { ClaudeCodeSetup };

View File

@@ -344,6 +344,45 @@ class CodexSetup extends BaseIdeSetup {
await this.clearOldBmadFiles(projectSpecificDir);
}
}
/**
* Install a custom agent launcher for Codex
* @param {string} projectDir - Project directory (not used, Codex installs to home)
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const destDir = this.getCodexPromptDir();
await fs.ensureDir(destDir);
const launcherContent = `---
name: '${agentName}'
description: '${agentName} agent'
---
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
const fileName = `bmad-custom-agents-${agentName}.md`;
const launcherPath = path.join(destDir, fileName);
await fs.writeFile(launcherPath, launcherContent, 'utf8');
return {
path: launcherPath,
command: `/${fileName.replace('.md', '')}`,
};
}
}
module.exports = { CodexSetup };

View File

@@ -347,6 +347,54 @@ alwaysApply: false
// Return MDC header + launcher content (without its original frontmatter)
return mdcHeader + contentWithoutFrontmatter;
}
/**
* Install a custom agent launcher for Cursor
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const customAgentsDir = path.join(projectDir, this.configDir, this.rulesDir, 'bmad', 'custom', 'agents');
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
return null; // IDE not configured for this project
}
await this.ensureDir(customAgentsDir);
const launcherContent = `You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
// Cursor uses MDC format with metadata header
const mdcContent = `---
description: "${agentName} agent"
globs:
alwaysApply: false
---
${launcherContent}
`;
const launcherPath = path.join(customAgentsDir, `${agentName}.mdc`);
await this.writeFile(launcherPath, mdcContent);
return {
path: launcherPath,
command: `@${agentName}`,
};
}
}
module.exports = { CursorSetup };

View File

@@ -297,6 +297,80 @@ ${cleanContent}
}
}
}
/**
* Install a custom agent launcher for GitHub Copilot
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const chatmodesDir = path.join(projectDir, this.configDir, this.chatmodesDir);
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
return null; // IDE not configured for this project
}
await this.ensureDir(chatmodesDir);
const launcherContent = `You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
// GitHub Copilot needs specific tools in frontmatter
const copilotTools = [
'changes',
'codebase',
'createDirectory',
'createFile',
'editFiles',
'fetch',
'fileSearch',
'githubRepo',
'listDirectory',
'problems',
'readFile',
'runInTerminal',
'runTask',
'runTests',
'runVscodeCommand',
'search',
'searchResults',
'terminalLastCommand',
'terminalSelection',
'testFailure',
'textSearch',
'usages',
];
const chatmodeContent = `---
description: "Activates the ${metadata.title || agentName} agent persona."
tools: ${JSON.stringify(copilotTools)}
---
# ${metadata.title || agentName} Agent
${launcherContent}
`;
const chatmodePath = path.join(chatmodesDir, `bmad-agent-custom-${agentName}.chatmode.md`);
await this.writeFile(chatmodePath, chatmodeContent);
return {
path: chatmodePath,
command: `bmad-agent-custom-${agentName}`,
};
}
}
module.exports = { GitHubCopilotSetup };

View File

@@ -204,6 +204,41 @@ class IdeManager {
return detected;
}
/**
* Install custom agent launchers for specified IDEs
* @param {Array} ides - List of IDE names to install for
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object} Results for each IDE
*/
async installCustomAgentLaunchers(ides, projectDir, agentName, agentPath, metadata) {
const results = {};
for (const ideName of ides) {
const handler = this.handlers.get(ideName.toLowerCase());
if (!handler) {
console.warn(chalk.yellow(`⚠️ IDE '${ideName}' is not yet supported for custom agent installation`));
continue;
}
try {
if (typeof handler.installCustomAgentLauncher === 'function') {
const result = await handler.installCustomAgentLauncher(projectDir, agentName, agentPath, metadata);
if (result) {
results[ideName] = result;
}
}
} catch (error) {
console.warn(chalk.yellow(`⚠️ Failed to install ${ideName} launcher: ${error.message}`));
}
}
return results;
}
}
module.exports = { IdeManager };

View File

@@ -207,6 +207,51 @@ class OpenCodeSetup extends BaseIdeSetup {
console.log(chalk.dim(` Cleaned up ${removed} existing BMAD files`));
}
}
/**
* Install a custom agent launcher for OpenCode
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const agentsDir = path.join(projectDir, this.configDir, this.agentsDir);
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
return null; // IDE not configured for this project
}
await this.ensureDir(agentsDir);
const launcherContent = `---
name: '${agentName}'
description: '${metadata.title || agentName} agent'
mode: 'primary'
---
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
// OpenCode uses flat naming: bmad-agent-custom-{name}.md
const launcherPath = path.join(agentsDir, `bmad-agent-custom-${agentName}.md`);
await this.writeFile(launcherPath, launcherContent);
return {
path: launcherPath,
command: `bmad-agent-custom-${agentName}`,
};
}
}
module.exports = { OpenCodeSetup };

View File

@@ -206,6 +206,53 @@ ${content}`;
console.log(chalk.dim(` Cleaned up existing BMAD workflows`));
}
}
/**
* Install a custom agent launcher for Windsurf
* @param {string} projectDir - Project directory
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
* @param {string} agentPath - Path to compiled agent (relative to project root)
* @param {Object} metadata - Agent metadata
* @returns {Object|null} Info about created command
*/
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
const fs = require('fs-extra');
const customAgentsDir = path.join(projectDir, this.configDir, this.workflowsDir, 'bmad', 'custom', 'agents');
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
return null; // IDE not configured for this project
}
await this.ensureDir(customAgentsDir);
const launcherContent = `You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent-activation CRITICAL="TRUE">
1. LOAD the FULL agent file from @${agentPath}
2. READ its entire contents - this contains the complete agent persona, menu, and instructions
3. FOLLOW every step in the <activation> section precisely
4. DISPLAY the welcome/greeting as instructed
5. PRESENT the numbered menu
6. WAIT for user input before proceeding
</agent-activation>
`;
// Windsurf uses workflow format with frontmatter
const workflowContent = `---
description: ${metadata.title || agentName}
auto_execution_mode: 3
---
${launcherContent}`;
const launcherPath = path.join(customAgentsDir, `${agentName}.md`);
await fs.writeFile(launcherPath, workflowContent);
return {
path: launcherPath,
command: `bmad/custom/agents/${agentName}`,
};
}
}
module.exports = { WindsurfSetup };