## 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**Deleted Bloated/Outdated Docs (2,651 lines removed):**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- Outdated workflow guides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>
## Summary
- Add ide-only and web-only boolean fields to agent menu schema
- Filter menu items based on build target (web bundle vs local IDE)
- Update BMM agent definitions with platform restrictions and improved descriptions
- Update frame-expert agent icon to 📐 and add webskip flag
## Changes
### Schema & Bundler Updates
- tools/schema/agent.js: Add ide-only and web-only optional boolean fields
- tools/cli/lib/yaml-xml-builder.js: Filter ide-only items from web bundles
- tools/cli/lib/xml-handler.js: Pass forWebBundle flag through build chain
### Agent Updates
- frame-expert: Change icon to 📐, add webskip flag, improve principle formatting
- pm: Mark workflow-init and correct-course as ide-only, advanced-elicitation as web-only
- ux-designer: Rename trigger to create-ux-design, mark advanced-elicitation as web-only
- sm: Rename triggers for consistency (story-context → create-story-context)
- analyst: Add research workflow after brainstorm, mark advanced-elicitation as web-only
- architect: Remove document field from validate-architecture, add web-only flag
- dev: Update persona and critical actions for clarity
- tech-writer: Add party-mode workflow, mark advanced-elicitation as web-only
- tea: Mark advanced-elicitation as web-only
- All agents: Standardize party-mode description
This enables platform-specific functionality where some commands only make sense
in IDE environments (workflow-init) or web interfaces (advanced-elicitation).
- Installation path is now fully configurable, allowing users to specify custom installation directories during setup
- Default installation location changed to .bmad (hidden directory) for cleaner project root organization
Web Bundle Improvements:
- All web bundles (single agent and team) now include party mode support for multi-agent collaboration!
- Advanced elicitation capabilities integrated into standalone agents
- All bundles enhanced with party mode agent manifests
- Added default-party.csv files to bmm, bmgd, and cis module teams
- The default party file is what will be used with single agent bundles. teams can customize for different party configurations before web bundling through a setting in the team yaml file
- New web bundle outputs for all agents (analyst, architect, dev, pm, sm, tea, tech-writer, ux-designer, game-*, creative-squad)
Phase 4 Workflow Updates (In Progress):
- Initiated shift to separate phase 4 implementation artifacts from documentation
- Phase 4 implementation artifacts (stories, code review, sprint plan, context files) will move to dedicated location outside docs folder
- Installer questions and configuration added for artifact path selection
- Updated workflow.yaml files for code-review, sprint-planning, story-context, epic-tech-context, and retrospective workflows to support this, but still might require some udpates
Additional Changes:
- New agent and action command header models for standardization
- Enhanced web-bundle-activation-steps fragment
- Updated web-bundler.js to support new structure
- VS Code settings updated for new .bmad directory
- Party mode instructions and workflow enhanced for better orchestration
IDE Installer Updates:
- Show version number of installer in cli
- improved Installer UX
- Gemini TOML Improved to have clear loading instructions with @ commands
- All tools agent launcher mds improved to use a central file template critical indication isntead of hardcoding in 2 different locations.
This commit represents a major documentation quality improvement, fixing critical inaccuracies and adding forward-looking guidance on the evolving role of PMs/UX in AI-driven development.
## Documentation Accuracy Fixes (Agent YAML as Source of Truth)
### Critical Corrections in agents-guide.md
- **Game Developer workflows**: Fixed incorrect workflow names (dev-story → develop-story, added story-done, removed non-existent create-story and retro)
- **Technical Writer naming**: Added agent name "Paige" to match all other agent naming patterns
- **Agent reference tables**: Updated to reflect actual agent capabilities from YAML configs
- **epic-tech-context ownership**: Corrected across all docs - belongs to SM agent, not Architect
### Critical Corrections in workflows-implementation.md
- **Line 16 + 75**: Fixed epic-tech-context agent from "Architect" → "SM" (matches sm.agent.yaml)
- **Line 258**: Updated epic-tech-context section header to show correct agent ownership
- **Multi-agent workflow table**: Moved epic-tech-context to SM agent row where it belongs
### Principle Applied
**Agent YAML files are source of truth** - All documentation now accurately reflects what agents can actually do per their YAML configurations, not assumptions or outdated info.
## Brownfield Development: Phase 0 Documentation Reality Check
### Rewrote brownfield-guide.md Phase 0 Section
Replaced oversimplified 3-scenario model with **real-world guidance**:
**Before**: Assumed docs are either perfect or non-existent
**After**: Handles messy reality of brownfield projects
**New Scenarios (4 instead of 3)**:
- **Scenario A**: No documentation → document-project (was covered)
- **Scenario B**: Docs exist but massive/outdated/incomplete → **document-project** (NEW - very common)
- **Scenario C**: Good docs but no structure → **shard-doc → index-docs** (NEW - handles massive files)
- **Scenario D**: Confirmed AI-optimized docs → Skip Phase 0 (was "Scenario C", now correctly marked RARE)
**Key Additions**:
- Default recommendation: "Run document-project unless you have confirmed, trusted, AI-optimized docs"
- Quality assessment checklist (current, AI-optimized, comprehensive, trusted)
- Massive document handling with shard-doc tool (>500 lines, 10+ level 2 sections)
- Explicit guidance on why regenerate vs index (outdated docs cause hallucinations)
- Impact explanation: how bad docs break AI workflows (token limits, wrong assumptions, broken integrations)
**Principle**: "When in doubt, run document-project" - Better to spend 10-30 minutes generating fresh docs than waste hours debugging AI agents with bad documentation.
## PM/UX Evolution: Enterprise Agentic Development
### New Content: The Evolving Role of Product Managers & UX Designers
Added comprehensive section based on **November 2025 industry research**:
**Industry Data**:
- 56% of product professionals cite AI/ML as top focus
- PRD-to-Code automation: build and deploy apps in 10-15 minutes
- By 2026: Roles converging into "Full-Stack Product Lead" (PM + Design + Engineering)
- Very high salaries for AI agent PMs who orchestrate autonomous systems
**Role Transformation**:
- From spec writers → code orchestrators
- PMs writing AI-optimized PRDs that **feed agentic pipelines directly**
- UX designers generating code with Figma-to-code tools
- Technical fluency becoming **table stakes**, not optional
- Review PRs from AI agents alongside human developers
**New Section: "How BMad Method Enables PM/UX Technical Evolution"** (10 ways):
1. **AI-Executable PRD Generation** - PRDs become work packages for cloud agents
2. **Automated Epic/Story Breakdown** - No more story refinement sessions
3. **Human-in-the-Loop Architecture** - PMs learn while validating technical decisions
4. **Cloud Agentic Pipeline** - Current (2025) + Future (2026) vision with diagrams
5. **UX Design Integration** - Designs validated through working prototypes
6. **PM Technical Skills Development** - Learn by doing through conversational workflows
7. **Organizational Leverage** - 1 PM → 20-50 AI agents (5-10× multiplier)
8. **Quality Consistency** - What gets built matches what was specified
9. **Rapid Prototyping** - Hours to validate ideas vs months
10. **Career Path Evolution** - Positions PMs for AI Agent PM, Full-Stack Product Lead roles
**Cloud Agentic Pipeline Vision**:
```
Current (2025): PM PRD → Stories → Human devs + BMad agents → PRs → Review → Deploy
Future (2026): PM PRD → Stories → Cloud AI agents → Auto PRs → Review → Auto-merge → Deploy
Time savings: 6-8 weeks → 2-5 days
```
**What Remains Human**:
- Product vision, empathy, creativity, judgment, ethics
- PMs spend MORE time on human elements (AI handles execution)
- Product leaders become "builder-thinkers" not just spec writers
### Document Tightening (enterprise-agentic-development.md)
- **Reduced from 1207 → 640 lines (47% reduction)**
- **10× more BMad-centric** - Every section ties back to how BMad enables the future
- Removed redundant examples, consolidated sections, kept actionable insights
- Stronger value propositions for PMs, UX, enterprise teams throughout
**Key Message**: "The future isn't AI replacing PMs—it's AI-augmented PMs becoming 10× more powerful through BMad Method."
## Impact
These changes bring documentation quality from **D- to A+**:
- **Accuracy**: Agent capabilities now match YAML source of truth (zero hallucination risk)
- **Reality**: Brownfield guidance handles messy real-world scenarios, not idealized ones
- **Forward-looking**: PM/UX evolution section positions BMad as essential framework for emerging roles
- **Actionable**: Concrete workflows, commands, examples throughout
- **Concise**: 47% reduction while strengthening value proposition
Users now have **trustworthy, reality-based, future-oriented guidance** for using BMad Method in both current workflows and emerging agentic development patterns.
Brian Madison