Brian Madison 054b031c1d 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**Deleted Bloated/Outdated Docs (2,651 lines removed):**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- Outdated workflow guides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>
2025-11-18 21:55:47 -06:00

258 lines
9.2 KiB
JavaScript

const path = require('node:path');
const fs = require('fs-extra');
const os = require('node:os');
const chalk = require('chalk');
const yaml = require('js-yaml');
const { BaseIdeSetup } = require('./_base-ide');
const { WorkflowCommandGenerator } = require('./shared/workflow-command-generator');
const { TaskToolCommandGenerator } = require('./shared/task-tool-command-generator');
const { AgentCommandGenerator } = require('./shared/agent-command-generator');
/**
* OpenCode IDE setup handler
*/
class OpenCodeSetup extends BaseIdeSetup {
constructor() {
super('opencode', 'OpenCode', true); // Mark as preferred/recommended
this.configDir = '.opencode';
this.commandsDir = 'command';
this.agentsDir = 'agent';
}
async setup(projectDir, bmadDir, options = {}) {
console.log(chalk.cyan(`Setting up ${this.name}...`));
const baseDir = path.join(projectDir, this.configDir);
const commandsBaseDir = path.join(baseDir, this.commandsDir);
const agentsBaseDir = path.join(baseDir, this.agentsDir);
await this.ensureDir(commandsBaseDir);
await this.ensureDir(agentsBaseDir);
// Clean up any existing BMAD files before reinstalling
await this.cleanup(projectDir);
// Generate agent launchers
const agentGen = new AgentCommandGenerator(this.bmadFolderName);
const { artifacts: agentArtifacts } = await agentGen.collectAgentArtifacts(bmadDir, options.selectedModules || []);
// Install primary agents with flat naming: bmad-agent-{module}-{name}.md
// OpenCode agents go in the agent folder (not command folder)
let agentCount = 0;
for (const artifact of agentArtifacts) {
const agentContent = artifact.content;
// Flat structure in agent folder: bmad-agent-{module}-{name}.md
const targetPath = path.join(agentsBaseDir, `bmad-agent-${artifact.module}-${artifact.name}.md`);
await this.writeFile(targetPath, agentContent);
agentCount++;
}
// Install workflow commands with flat naming: bmad-workflow-{module}-{name}.md
const workflowGenerator = new WorkflowCommandGenerator(this.bmadFolderName);
const { artifacts: workflowArtifacts, counts: workflowCounts } = await workflowGenerator.collectWorkflowArtifacts(bmadDir);
let workflowCommandCount = 0;
for (const artifact of workflowArtifacts) {
if (artifact.type === 'workflow-command') {
const commandContent = artifact.content;
// Flat structure: bmad-workflow-{module}-{name}.md
// artifact.relativePath is like: bmm/workflows/plan-project.md
const workflowName = path.basename(artifact.relativePath, '.md');
const targetPath = path.join(commandsBaseDir, `bmad-workflow-${artifact.module}-${workflowName}.md`);
await this.writeFile(targetPath, commandContent);
workflowCommandCount++;
}
// Skip workflow launcher READMEs as they're not needed in flat structure
}
// Install task and tool commands with flat naming
const { tasks, tools } = await this.generateFlatTaskToolCommands(bmadDir, commandsBaseDir);
console.log(chalk.green(`${this.name} configured:`));
console.log(chalk.dim(` - ${agentCount} agents installed to .opencode/agent/`));
if (workflowCommandCount > 0) {
console.log(chalk.dim(` - ${workflowCommandCount} workflows installed to .opencode/command/`));
}
if (tasks + tools > 0) {
console.log(chalk.dim(` - ${tasks + tools} tasks/tools installed to .opencode/command/ (${tasks} tasks, ${tools} tools)`));
}
return {
success: true,
agents: agentCount,
workflows: workflowCommandCount,
workflowCounts,
};
}
/**
* Generate flat task and tool commands for OpenCode
* OpenCode doesn't support nested command directories
*/
async generateFlatTaskToolCommands(bmadDir, commandsBaseDir) {
const taskToolGen = new TaskToolCommandGenerator();
const tasks = await taskToolGen.loadTaskManifest(bmadDir);
const tools = await taskToolGen.loadToolManifest(bmadDir);
// Filter to only standalone items
const standaloneTasks = tasks ? tasks.filter((t) => t.standalone === 'true' || t.standalone === true) : [];
const standaloneTools = tools ? tools.filter((t) => t.standalone === 'true' || t.standalone === true) : [];
// Generate command files for tasks with flat naming: bmad-task-{module}-{name}.md
for (const task of standaloneTasks) {
const commandContent = taskToolGen.generateCommandContent(task, 'task');
const targetPath = path.join(commandsBaseDir, `bmad-task-${task.module}-${task.name}.md`);
await this.writeFile(targetPath, commandContent);
}
// Generate command files for tools with flat naming: bmad-tool-{module}-{name}.md
for (const tool of standaloneTools) {
const commandContent = taskToolGen.generateCommandContent(tool, 'tool');
const targetPath = path.join(commandsBaseDir, `bmad-tool-${tool.module}-${tool.name}.md`);
await this.writeFile(targetPath, commandContent);
}
return {
tasks: standaloneTasks.length,
tools: standaloneTools.length,
};
}
async readAndProcess(filePath, metadata) {
const content = await fs.readFile(filePath, 'utf8');
return this.processContent(content, metadata);
}
async createAgentContent(content, metadata) {
const { frontmatter = {}, body } = this.parseFrontmatter(content);
frontmatter.description =
frontmatter.description && String(frontmatter.description).trim().length > 0
? frontmatter.description
: `BMAD ${metadata.module} agent: ${metadata.name}`;
// OpenCode agents use: 'primary' mode for main agents
frontmatter.mode = 'primary';
const frontmatterString = this.stringifyFrontmatter(frontmatter);
// Get the activation header from central template
const activationHeader = await this.getAgentCommandHeader();
return `${frontmatterString}\n\n${activationHeader}\n\n${body}`;
}
parseFrontmatter(content) {
const match = content.match(/^---\s*\n([\s\S]*?)\n---\s*\n?/);
if (!match) {
return { data: {}, body: content };
}
const body = content.slice(match[0].length);
let frontmatter = {};
try {
frontmatter = yaml.load(match[1]) || {};
} catch {
frontmatter = {};
}
return { frontmatter, body };
}
stringifyFrontmatter(frontmatter) {
const yamlText = yaml
.dump(frontmatter, {
indent: 2,
lineWidth: -1,
noRefs: true,
sortKeys: false,
})
.trimEnd();
return `---\n${yamlText}\n---`;
}
/**
* Cleanup OpenCode configuration - surgically remove only BMAD files
*/
async cleanup(projectDir) {
const agentsDir = path.join(projectDir, this.configDir, this.agentsDir);
const commandsDir = path.join(projectDir, this.configDir, this.commandsDir);
let removed = 0;
// Clean up agent folder
if (await fs.pathExists(agentsDir)) {
const files = await fs.readdir(agentsDir);
for (const file of files) {
if (file.startsWith('bmad-') && file.endsWith('.md')) {
await fs.remove(path.join(agentsDir, file));
removed++;
}
}
}
// Clean up command folder
if (await fs.pathExists(commandsDir)) {
const files = await fs.readdir(commandsDir);
for (const file of files) {
if (file.startsWith('bmad-') && file.endsWith('.md')) {
await fs.remove(path.join(commandsDir, file));
removed++;
}
}
}
if (removed > 0) {
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 };