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 Documentation Overhaul **Deleted Bloated/Outdated Docs (2,651 lines removed):** - Old verbose architecture docs - Redundant pattern files - Outdated workflow guides **Created Focused, Type-Specific Docs:** - `src/modules/bmb/docs/understanding-agent-types.md` - Architecture vs capability distinction -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>
2025-12-29 16:14:59 +00:00 · 2025-11-17 22:25:15 -06:00
parent 7b7f984cd2
commit 054b031c1d
58 changed files with 5845 additions and 2622 deletions
--- a/src/modules/bmb/docs/agent-compilation.md
+++ b/src/modules/bmb/docs/agent-compilation.md
@@ -0,0 +1,301 @@
+# Agent Compilation: YAML to XML
+
+What the compiler auto-injects. **DO NOT duplicate these in your YAML.**
+
+## Compilation Pipeline
+
+```
+agent.yaml → Handlebars processing → XML generation → frontmatter.md
+```
+
+Source: `tools/cli/lib/agent/compiler.js`
+
+## Auto-Injected Components
+
+### 1. Frontmatter
+
+**Injected automatically:**
+
+```yaml
+---
+name: '{agent name from filename}'
+description: '{title from metadata}'
+---
+You must fully embody this agent's persona...
+```
+
+**DO NOT add** frontmatter to your YAML source.
+
+### 2. Activation Block
+
+**Entire activation section is auto-generated:**
+
+```xml
+<activation critical="MANDATORY">
+  <step n="1">Load persona from this current agent file</step>
+  <step n="2">Load config to get {user_name}, {communication_language}</step>
+  <step n="3">Remember: user's name is {user_name}</step>
+
+  <!-- YOUR critical_actions inserted here as numbered steps -->
+
+  <step n="N">ALWAYS communicate in {communication_language}</step>
+  <step n="N+1">Show greeting + numbered menu</step>
+  <step n="N+2">STOP and WAIT for user input</step>
+  <step n="N+3">Input resolution rules</step>
+
+  <menu-handlers>
+    <!-- Only handlers used in YOUR menu are included -->
+  </menu-handlers>
+
+  <rules>
+    <!-- Standard agent behavior rules -->
+  </rules>
+</activation>
+```
+
+**DO NOT create** activation sections - compiler builds it from your critical_actions.
+
+### 3. Menu Enhancements
+
+**Auto-injected menu items:**
+
+- `*help` - Always FIRST in compiled menu
+- `*exit` - Always LAST in compiled menu
+
+**Trigger prefixing:**
+
+- Your trigger `analyze` becomes `*analyze`
+- Don't add `*` prefix - compiler does it
+
+**DO NOT include:**
+
+```yaml
+# BAD - these are auto-injected
+menu:
+  - trigger: help
+    description: 'Show help'
+  - trigger: exit
+    description: 'Exit'
+```
+
+### 4. Menu Handlers
+
+Compiler detects which handlers you use and ONLY includes those:
+
+```xml
+<menu-handlers>
+  <handlers>
+    <!-- Only if you use action="#id" or action="text" -->
+    <handler type="action">...</handler>
+
+    <!-- Only if you use workflow="path" -->
+    <handler type="workflow">...</handler>
+
+    <!-- Only if you use exec="path" -->
+    <handler type="exec">...</handler>
+
+    <!-- Only if you use tmpl="path" -->
+    <handler type="tmpl">...</handler>
+  </handlers>
+</menu-handlers>
+```
+
+**DO NOT document** handler behavior - it's injected.
+
+### 5. Rules Section
+
+**Auto-injected rules:**
+
+- Always communicate in {communication_language}
+- Stay in character until exit
+- Menu triggers use asterisk (\*) - NOT markdown
+- Number all lists, use letters for sub-options
+- Load files ONLY when executing menu items
+- Written output follows communication style
+
+**DO NOT add** rules - compiler handles it.
+
+## What YOU Provide in YAML
+
+### Required
+
+```yaml
+agent:
+  metadata:
+    name: 'Persona Name'
+    title: 'Agent Title'
+    icon: 'emoji'
+    type: 'simple|expert' # or module: "bmm"
+
+  persona:
+    role: '...'
+    identity: '...'
+    communication_style: '...'
+    principles: [...]
+
+  menu:
+    - trigger: your-action
+      action: '#prompt-id'
+      description: 'What it does'
+```
+
+### Optional (based on type)
+
+```yaml
+# Expert agents only
+critical_actions:
+  - 'Load sidecar files...'
+  - 'Restrict access...'
+
+# Simple/Expert with embedded logic
+prompts:
+  - id: prompt-id
+    content: '...'
+
+# Simple/Expert with customization
+install_config:
+  questions: [...]
+```
+
+## Common Duplication Mistakes
+
+### Adding Activation Logic
+
+```yaml
+# BAD - compiler builds activation
+agent:
+  activation:
+    steps: [...]
+```
+
+### Including Help/Exit
+
+```yaml
+# BAD - auto-injected
+menu:
+  - trigger: help
+  - trigger: exit
+```
+
+### Prefixing Triggers
+
+```yaml
+# BAD - compiler adds *
+menu:
+  - trigger: '*analyze' # Should be: analyze
+```
+
+### Documenting Handlers
+
+```yaml
+# BAD - don't explain handlers, compiler injects them
+# When using workflow, load workflow.xml...
+```
+
+### Adding Rules in YAML
+
+```yaml
+# BAD - rules are auto-injected
+agent:
+  rules:
+    - Stay in character...
+```
+
+## Compilation Example
+
+**Your YAML:**
+
+```yaml
+agent:
+  metadata:
+    name: 'Rex'
+    title: 'Code Reviewer'
+    icon: '🔍'
+    type: simple
+
+  persona:
+    role: Code Review Expert
+    identity: Systematic reviewer...
+    communication_style: Direct and constructive
+    principles:
+      - Code should be readable
+
+  prompts:
+    - id: review
+      content: |
+        Analyze code for issues...
+
+  menu:
+    - trigger: review
+      action: '#review'
+      description: 'Review code'
+```
+
+**Compiled Output (.md):**
+
+```markdown
+---
+name: 'rex'
+description: 'Code Reviewer'
+---
+
+You must fully embody...
+
+\`\`\`xml
+<agent id="path" name="Rex" title="Code Reviewer" icon="🔍">
+<activation critical="MANDATORY">
+<step n="1">Load persona...</step>
+<step n="2">Load config...</step>
+<step n="3">Remember user...</step>
+<step n="4">Communicate in language...</step>
+<step n="5">Show greeting + menu...</step>
+<step n="6">STOP and WAIT...</step>
+<step n="7">Input resolution...</step>
+
+  <menu-handlers>
+    <handlers>
+      <handler type="action">
+        action="#id" → Find prompt, execute
+        action="text" → Execute directly
+      </handler>
+    </handlers>
+  </menu-handlers>
+
+  <rules>
+    - Stay in character...
+    - Number lists...
+    - Load files when executing...
+  </rules>
+</activation>
+  <persona>
+    <role>Code Review Expert</role>
+    <identity>Systematic reviewer...</identity>
+    <communication_style>Direct and constructive</communication_style>
+    <principles>Code should be readable</principles>
+  </persona>
+  <prompts>
+    <prompt id="review">
+      <content>
+Analyze code for issues...
+      </content>
+    </prompt>
+  </prompts>
+  <menu>
+    <item cmd="*help">Show numbered menu</item>
+    <item cmd="*review" action="#review">Review code</item>
+    <item cmd="*exit">Exit with confirmation</item>
+  </menu>
+</agent>
+\`\`\`
+```
+
+## Key Takeaways
+
+1. **Compiler handles boilerplate** - Focus on persona and logic
+2. **Critical_actions become activation steps** - Just list your agent-specific needs
+3. **Menu items are enhanced** - Help/exit added, triggers prefixed
+4. **Handlers auto-detected** - Only what you use is included
+5. **Rules standardized** - Consistent behavior across agents
+
+**Your job:** Define persona, prompts, menu actions
+**Compiler's job:** Activation, handlers, rules, help/exit, prefixes