mirror of
https://github.com/bmadcode/BMAD-METHOD.git
synced 2025-12-18 10:15:31 +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**Deleted Bloated/Outdated Docs (2,651 lines removed):**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- Outdated workflow guides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>
401 lines
13 KiB
JavaScript
401 lines
13 KiB
JavaScript
const path = require('node:path');
|
|
const { BaseIdeSetup } = require('./_base-ide');
|
|
const chalk = require('chalk');
|
|
const { AgentCommandGenerator } = require('./shared/agent-command-generator');
|
|
|
|
/**
|
|
* Cursor IDE setup handler
|
|
*/
|
|
class CursorSetup extends BaseIdeSetup {
|
|
constructor() {
|
|
super('cursor', 'Cursor', true); // preferred IDE
|
|
this.configDir = '.cursor';
|
|
this.rulesDir = 'rules';
|
|
}
|
|
|
|
/**
|
|
* Cleanup old BMAD installation before reinstalling
|
|
* @param {string} projectDir - Project directory
|
|
*/
|
|
async cleanup(projectDir) {
|
|
const fs = require('fs-extra');
|
|
const bmadRulesDir = path.join(projectDir, this.configDir, this.rulesDir, 'bmad');
|
|
|
|
if (await fs.pathExists(bmadRulesDir)) {
|
|
await fs.remove(bmadRulesDir);
|
|
console.log(chalk.dim(` Removed old BMAD rules from ${this.name}`));
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Setup Cursor IDE configuration
|
|
* @param {string} projectDir - Project directory
|
|
* @param {string} bmadDir - BMAD installation directory
|
|
* @param {Object} options - Setup options
|
|
*/
|
|
async setup(projectDir, bmadDir, options = {}) {
|
|
console.log(chalk.cyan(`Setting up ${this.name}...`));
|
|
|
|
// Clean up old BMAD installation first
|
|
await this.cleanup(projectDir);
|
|
|
|
// Create .cursor/rules directory structure
|
|
const cursorDir = path.join(projectDir, this.configDir);
|
|
const rulesDir = path.join(cursorDir, this.rulesDir);
|
|
const bmadRulesDir = path.join(rulesDir, 'bmad');
|
|
|
|
await this.ensureDir(bmadRulesDir);
|
|
|
|
// Generate agent launchers first
|
|
const agentGen = new AgentCommandGenerator(this.bmadFolderName);
|
|
const { artifacts: agentArtifacts } = await agentGen.collectAgentArtifacts(bmadDir, options.selectedModules || []);
|
|
|
|
// Convert artifacts to agent format for index creation
|
|
const agents = agentArtifacts.map((a) => ({ module: a.module, name: a.name }));
|
|
|
|
// Get tasks, tools, and workflows (standalone only)
|
|
const tasks = await this.getTasks(bmadDir, true);
|
|
const tools = await this.getTools(bmadDir, true);
|
|
const workflows = await this.getWorkflows(bmadDir, true);
|
|
|
|
// Create directories for each module
|
|
const modules = new Set();
|
|
for (const item of [...agents, ...tasks, ...tools, ...workflows]) modules.add(item.module);
|
|
|
|
for (const module of modules) {
|
|
await this.ensureDir(path.join(bmadRulesDir, module));
|
|
await this.ensureDir(path.join(bmadRulesDir, module, 'agents'));
|
|
await this.ensureDir(path.join(bmadRulesDir, module, 'tasks'));
|
|
await this.ensureDir(path.join(bmadRulesDir, module, 'tools'));
|
|
await this.ensureDir(path.join(bmadRulesDir, module, 'workflows'));
|
|
}
|
|
|
|
// Process and write agent launchers with MDC format
|
|
let agentCount = 0;
|
|
for (const artifact of agentArtifacts) {
|
|
// Add MDC metadata header to launcher (but don't call processContent which adds activation headers)
|
|
const content = this.wrapLauncherWithMDC(artifact.content, {
|
|
module: artifact.module,
|
|
name: artifact.name,
|
|
});
|
|
|
|
const targetPath = path.join(bmadRulesDir, artifact.module, 'agents', `${artifact.name}.mdc`);
|
|
|
|
await this.writeFile(targetPath, content);
|
|
agentCount++;
|
|
}
|
|
|
|
// Process and copy tasks
|
|
let taskCount = 0;
|
|
for (const task of tasks) {
|
|
const content = await this.readAndProcess(task.path, {
|
|
module: task.module,
|
|
name: task.name,
|
|
});
|
|
|
|
const targetPath = path.join(bmadRulesDir, task.module, 'tasks', `${task.name}.mdc`);
|
|
|
|
await this.writeFile(targetPath, content);
|
|
taskCount++;
|
|
}
|
|
|
|
// Process and copy tools
|
|
let toolCount = 0;
|
|
for (const tool of tools) {
|
|
const content = await this.readAndProcess(tool.path, {
|
|
module: tool.module,
|
|
name: tool.name,
|
|
});
|
|
|
|
const targetPath = path.join(bmadRulesDir, tool.module, 'tools', `${tool.name}.mdc`);
|
|
|
|
await this.writeFile(targetPath, content);
|
|
toolCount++;
|
|
}
|
|
|
|
// Process and copy workflows
|
|
let workflowCount = 0;
|
|
for (const workflow of workflows) {
|
|
const content = await this.readAndProcess(workflow.path, {
|
|
module: workflow.module,
|
|
name: workflow.name,
|
|
});
|
|
|
|
const targetPath = path.join(bmadRulesDir, workflow.module, 'workflows', `${workflow.name}.mdc`);
|
|
|
|
await this.writeFile(targetPath, content);
|
|
workflowCount++;
|
|
}
|
|
|
|
// Create BMAD index file (but NOT .cursorrules - user manages that)
|
|
await this.createBMADIndex(bmadRulesDir, agents, tasks, tools, workflows, modules);
|
|
|
|
console.log(chalk.green(`✓ ${this.name} configured:`));
|
|
console.log(chalk.dim(` - ${agentCount} agents installed`));
|
|
console.log(chalk.dim(` - ${taskCount} tasks installed`));
|
|
console.log(chalk.dim(` - ${toolCount} tools installed`));
|
|
console.log(chalk.dim(` - ${workflowCount} workflows installed`));
|
|
console.log(chalk.dim(` - Rules directory: ${path.relative(projectDir, bmadRulesDir)}`));
|
|
|
|
return {
|
|
success: true,
|
|
agents: agentCount,
|
|
tasks: taskCount,
|
|
tools: toolCount,
|
|
workflows: workflowCount,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Create BMAD index file for easy navigation
|
|
*/
|
|
async createBMADIndex(bmadRulesDir, agents, tasks, tools, workflows, modules) {
|
|
const indexPath = path.join(bmadRulesDir, 'index.mdc');
|
|
|
|
let content = `---
|
|
description: BMAD Method - Master Index
|
|
globs:
|
|
alwaysApply: true
|
|
---
|
|
|
|
# BMAD Method - Cursor Rules Index
|
|
|
|
This is the master index for all BMAD agents, tasks, tools, and workflows available in your project.
|
|
|
|
## Installation Complete!
|
|
|
|
BMAD rules have been installed to: \`.cursor/rules/bmad/\`
|
|
|
|
**Note:** BMAD does not modify your \`.cursorrules\` file. You manage that separately.
|
|
|
|
## How to Use
|
|
|
|
- Reference specific agents: @bmad/{module}/agents/{agent-name}
|
|
- Reference specific tasks: @bmad/{module}/tasks/{task-name}
|
|
- Reference specific tools: @bmad/{module}/tools/{tool-name}
|
|
- Reference specific workflows: @bmad/{module}/workflows/{workflow-name}
|
|
- Reference entire modules: @bmad/{module}
|
|
- Reference this index: @bmad/index
|
|
|
|
## Available Modules
|
|
|
|
`;
|
|
|
|
for (const module of modules) {
|
|
content += `### ${module.toUpperCase()}\n\n`;
|
|
|
|
// List agents for this module
|
|
const moduleAgents = agents.filter((a) => a.module === module);
|
|
if (moduleAgents.length > 0) {
|
|
content += `**Agents:**\n`;
|
|
for (const agent of moduleAgents) {
|
|
content += `- @bmad/${module}/agents/${agent.name} - ${agent.name}\n`;
|
|
}
|
|
content += '\n';
|
|
}
|
|
|
|
// List tasks for this module
|
|
const moduleTasks = tasks.filter((t) => t.module === module);
|
|
if (moduleTasks.length > 0) {
|
|
content += `**Tasks:**\n`;
|
|
for (const task of moduleTasks) {
|
|
content += `- @bmad/${module}/tasks/${task.name} - ${task.name}\n`;
|
|
}
|
|
content += '\n';
|
|
}
|
|
|
|
// List tools for this module
|
|
const moduleTools = tools.filter((t) => t.module === module);
|
|
if (moduleTools.length > 0) {
|
|
content += `**Tools:**\n`;
|
|
for (const tool of moduleTools) {
|
|
content += `- @bmad/${module}/tools/${tool.name} - ${tool.name}\n`;
|
|
}
|
|
content += '\n';
|
|
}
|
|
|
|
// List workflows for this module
|
|
const moduleWorkflows = workflows.filter((w) => w.module === module);
|
|
if (moduleWorkflows.length > 0) {
|
|
content += `**Workflows:**\n`;
|
|
for (const workflow of moduleWorkflows) {
|
|
content += `- @bmad/${module}/workflows/${workflow.name} - ${workflow.name}\n`;
|
|
}
|
|
content += '\n';
|
|
}
|
|
}
|
|
|
|
content += `
|
|
## Quick Reference
|
|
|
|
- All BMAD rules are Manual type - reference them explicitly when needed
|
|
- Agents provide persona-based assistance with specific expertise
|
|
- Tasks are reusable workflows for common operations
|
|
- Tools provide specialized functionality
|
|
- Workflows orchestrate multi-step processes
|
|
- Each agent includes an activation block for proper initialization
|
|
|
|
## Configuration
|
|
|
|
BMAD rules are configured as Manual rules (alwaysApply: false) to give you control
|
|
over when they're included in your context. Reference them explicitly when you need
|
|
specific agent expertise, task workflows, tools, or guided workflows.
|
|
`;
|
|
|
|
await this.writeFile(indexPath, content);
|
|
}
|
|
|
|
/**
|
|
* Read and process file content
|
|
*/
|
|
async readAndProcess(filePath, metadata) {
|
|
const fs = require('fs-extra');
|
|
const content = await fs.readFile(filePath, 'utf8');
|
|
return this.processContent(content, metadata);
|
|
}
|
|
|
|
/**
|
|
* Override processContent to add MDC metadata header for Cursor
|
|
* @param {string} content - File content
|
|
* @param {Object} metadata - File metadata
|
|
* @returns {string} Processed content with MDC header
|
|
*/
|
|
processContent(content, metadata = {}) {
|
|
// First apply base processing (includes activation injection for agents)
|
|
let processed = super.processContent(content, metadata);
|
|
|
|
// Strip any existing frontmatter from the processed content
|
|
// This prevents duplicate frontmatter blocks
|
|
const frontmatterRegex = /^---\s*\n[\s\S]*?\n---\s*\n/;
|
|
if (frontmatterRegex.test(processed)) {
|
|
processed = processed.replace(frontmatterRegex, '');
|
|
}
|
|
|
|
// Determine the type and description based on content
|
|
const isAgent = content.includes('<agent');
|
|
const isTask = content.includes('<task');
|
|
const isTool = content.includes('<tool');
|
|
const isWorkflow = content.includes('workflow:') || content.includes('name:');
|
|
|
|
let description = '';
|
|
let globs = '';
|
|
|
|
if (isAgent) {
|
|
// Extract agent title if available
|
|
const titleMatch = content.match(/title="([^"]+)"/);
|
|
const title = titleMatch ? titleMatch[1] : metadata.name;
|
|
description = `BMAD ${metadata.module.toUpperCase()} Agent: ${title}`;
|
|
globs = '';
|
|
} else if (isTask) {
|
|
// Extract task name if available
|
|
const nameMatch = content.match(/name="([^"]+)"/);
|
|
const taskName = nameMatch ? nameMatch[1] : metadata.name;
|
|
description = `BMAD ${metadata.module.toUpperCase()} Task: ${taskName}`;
|
|
globs = '';
|
|
} else if (isTool) {
|
|
// Extract tool name if available
|
|
const nameMatch = content.match(/name="([^"]+)"/);
|
|
const toolName = nameMatch ? nameMatch[1] : metadata.name;
|
|
description = `BMAD ${metadata.module.toUpperCase()} Tool: ${toolName}`;
|
|
globs = '';
|
|
} else if (isWorkflow) {
|
|
// Workflow
|
|
description = `BMAD ${metadata.module.toUpperCase()} Workflow: ${metadata.name}`;
|
|
globs = '';
|
|
} else {
|
|
description = `BMAD ${metadata.module.toUpperCase()}: ${metadata.name}`;
|
|
globs = '';
|
|
}
|
|
|
|
// Create MDC metadata header
|
|
const mdcHeader = `---
|
|
description: ${description}
|
|
globs: ${globs}
|
|
alwaysApply: false
|
|
---
|
|
|
|
`;
|
|
|
|
// Add the MDC header to the processed content
|
|
return mdcHeader + processed;
|
|
}
|
|
|
|
/**
|
|
* Wrap launcher content with MDC metadata (without base processing)
|
|
* Launchers are already complete and should not have activation headers injected
|
|
*/
|
|
wrapLauncherWithMDC(launcherContent, metadata = {}) {
|
|
// Strip the launcher's frontmatter - we'll replace it with MDC frontmatter
|
|
const frontmatterRegex = /^---\s*\n[\s\S]*?\n---\s*\n/;
|
|
const contentWithoutFrontmatter = launcherContent.replace(frontmatterRegex, '');
|
|
|
|
// Extract metadata from launcher frontmatter for MDC description
|
|
const nameMatch = launcherContent.match(/name:\s*"([^"]+)"/);
|
|
const name = nameMatch ? nameMatch[1] : metadata.name;
|
|
|
|
const description = `BMAD ${metadata.module.toUpperCase()} Agent: ${name}`;
|
|
|
|
// Create MDC metadata header
|
|
const mdcHeader = `---
|
|
description: ${description}
|
|
globs:
|
|
alwaysApply: false
|
|
---
|
|
|
|
`;
|
|
|
|
// Return MDC header + launcher content (without its original frontmatter)
|
|
return mdcHeader + contentWithoutFrontmatter;
|
|
}
|
|
|
|
/**
|
|
* Install a custom agent launcher for Cursor
|
|
* @param {string} projectDir - Project directory
|
|
* @param {string} agentName - Agent name (e.g., "fred-commit-poet")
|
|
* @param {string} agentPath - Path to compiled agent (relative to project root)
|
|
* @param {Object} metadata - Agent metadata
|
|
* @returns {Object|null} Info about created command
|
|
*/
|
|
async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
|
|
const customAgentsDir = path.join(projectDir, this.configDir, this.rulesDir, 'bmad', 'custom', 'agents');
|
|
|
|
if (!(await this.exists(path.join(projectDir, this.configDir)))) {
|
|
return null; // IDE not configured for this project
|
|
}
|
|
|
|
await this.ensureDir(customAgentsDir);
|
|
|
|
const launcherContent = `You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
|
|
|
|
<agent-activation CRITICAL="TRUE">
|
|
1. LOAD the FULL agent file from @${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 };
|