Implemented Cline-inspired Memory Bank pattern for AI context persistence across sessions.
This ensures continuity and deep understanding of projects even when AI memory resets.
Core Memory Bank Components:
- Created 6 core memory bank templates following hierarchical structure
- projectbrief.md: Foundation document with project scope and goals
- productContext.md: The 'why' behind the project
- systemPatterns.md: Technical architecture and decisions
- techContext.md: Technology stack and environment
- activeContext.md: Current work focus and priorities
- progress.md: Project state tracking and evolution
Tasks and Workflows:
- initialize-memory-bank.md: Creates initial Memory Bank structure
- update-memory-bank.md: Updates based on dev journals, ADRs, and changes
- memory-bank-triggers.md: Reference guide for when to update
Agent Integrations:
- Enhanced architect agent with Memory Bank awareness and commands
- Enhanced dev agent to update activeContext and progress
- Enhanced po agent for requirements alignment with Memory Bank
- All agents now read Memory Bank at session start
Pervasive Integration Strategy:
- ADR creation triggers systemPatterns updates
- Dev journal entries trigger activeContext updates
- Story completion triggers progress updates
- Comprehensive commits/PRs trigger relevant updates
- Document-project task integrates with Memory Bank initialization
This provides AI agents with persistent context across sessions, preventing
loss of project knowledge and ensuring consistent understanding.
- Created create-comprehensive-commit.md task with anti-tunnel vision mechanisms
- Multi-stream aware commit message generation
- Systematic evidence gathering from multiple sources
- Comprehensive context analysis and rationale documentation
- Quality checklist to prevent tunnel vision
- Created create-comprehensive-pr.md task for detailed PR descriptions
- Work stream identification and documentation
- Per-stream testing instructions
- Visual evidence requirements
- Review focus areas and deployment notes
- Integrated workflows into dev and architect agents
- Added *comprehensive-commit command
- Added *comprehensive-pr command
- Made workflows available to agents who create commits/PRs
These workflows ensure high-quality git documentation with comprehensive
coverage of all changes, preventing the tunnel vision that often results
in incomplete commit messages or PR descriptions.
- Removed unnecessary folders from BMAD-METHOD repo (docs/adr, docs/devJournal)
- Updated tasks to create folders in destination projects when needed
- Removed standalone adr-specialist agent (functionality integrated into architect)
- Added create-adr task with folder setup instructions
- Both ADR and Dev Journal features now properly create their structures in target projects
The agents will now create and maintain docs/adr and docs/devJournal folders
in the projects where BMAD is installed, not in the BMAD-METHOD repo itself.
- Created comprehensive ADR template following Michael Nygard's format
- Enhanced architect agent with ADR management capabilities
- Added ADR triggers reference guide for decision documentation
- Updated architect checklist with ADR validation section
- Imported user's comprehensive development methodology in tmp/
- Memory Bank system for AI context persistence
- Detailed rules covering coding principles and architecture patterns
- Workflows for common development tasks with anti-tunnel vision checks
- Created foundation for integrating user methodology with BMAD
- Fixed pre-commit hook by removing non-existent test script
This enhancement brings structured architectural decision documentation
to BMAD while preparing for deeper integration with advanced AI-assisted
development patterns.
This release introduces significant enhancements across multiple areas:
QA Agent Transformation:
- Transform QA agent into senior developer role with active code refactoring abilities
- Add review-story task enabling QA to review, refactor, and improve code directly
- Integrate QA review step into standard development workflow (SM → Dev → QA)
- QA can fix small issues directly and leave checklist for remaining items
- Updated dev agent to maintain File List for QA review focus
Knowledge Base Improvements:
- Add extensive brownfield development documentation and best practices
- Clarify Web UI vs IDE usage with cost optimization strategies
- Document PRD-first approach for large codebases/monorepos
- Add comprehensive expansion packs explanation
- Update IDE workflow to include QA review step
- Clarify agent usage (bmad-master vs specialized agents)
Brownfield Enhancements:
- Create comprehensive Working in the Brownfield guide
- Add document-project task to analyst agent capabilities
- Implement PRD-first workflow option for focused documentation
- Transform document-project to create practical brownfield architecture docs
- Document technical debt, workarounds, and real-world constraints
- Reference actual files instead of duplicating content
- Add impact analysis when PRD is provided
Documentation Task Improvements:
- Simplify to always create ONE unified architecture document
- Add deep codebase analysis phase with targeted questions
- Focus on documenting reality including technical debt
- Include Quick Reference section with key file paths
- Add practical sections: useful commands, debugging tips, known issues
Workflow Updates:
- Update all 6 workflow files with detailed IDE transition instructions
- Add clear SM → Dev → QA → Dev cycle explanation
- Emphasize Gemini Web for brownfield analysis (1M+ context advantage)
- Support both PRD-first and document-first approaches
This release significantly improves the brownfield development experience and introduces a powerful shift-left QA approach with senior developer mentoring.
Issue Being Solved:
Dev agent was marking tasks as complete even when tests/lint/typecheck failed,
causing broken code to reach merge and creating technical debt.
Gap in System:
Missing explicit quality gates in dev agent configuration to block task completion
until all automated validations pass.
Solution:
- Add "Quality Gate Discipline" core principle
- Update task execution flow: Execute validations→Only if ALL pass→Update [x]
- Add "Failing validations" to blocking conditions
- Simplify completion criteria to focus on validation success
Alignment with BMAD Core Principles:
- Quality-First: Prevents defective code progression through workflow
- Agent Excellence: Ensures dev agent maintains high standards
- Technology Agnostic: Uses generic "validations" concept vs specific tools
Small, focused change that strengthens existing dev agent without architectural changes.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Remove 'root' property from YAML when building web bundles
- Remove 'IDE-FILE-RESOLUTION' and 'REQUEST-RESOLUTION' properties
- Filter out IDE-specific activation instructions
- Keep agent header minimal for web bundles
- Ensures web bundles are clean of IDE-specific configuration
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added two concise activation instructions to SM agent
- IDE-FILE-RESOLUTION: One-line explanation of file path mapping
- REQUEST-RESOLUTION: One-line instruction for flexible request matching
- Simplified file-resolution-context.md to be a quick reference
- Removed verbose documentation in favor of clear, actionable instructions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added file resolution section to SM agent explaining path patterns
- Created reusable file-resolution-context.md utility
- Documents how agents resolve tasks/templates/checklists to file paths
- Provides natural language to command mapping examples
- Helps IDE agents understand file system structure
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add expansion pack installation system with game dev and infrastructure expansion packs
- Added expansion pack discovery and installation to BMAD installer
- Supports interactive and CLI installation of expansion packs
- Expansion pack files install to destination root (.bmad-core)
- Added game development expansion pack (.bmad-2d-phaser-game-dev)
- Game designer, developer, and scrum master agents
- Game-specific templates, tasks, workflows, and guidelines
- Specialized for Phaser 3 + TypeScript development
- Added infrastructure devops expansion pack (.bmad-infrastructure-devops)
- Platform engineering agent and infrastructure templates
- Expansion pack agents automatically integrate with IDE rules
- Added list:expansions command and --expansion-packs CLI option
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
* alpha expansion packs and installer update to support installing expansion packs optionally
* node20
---------
Co-authored-by: Brian Madison <brianmadison@Brians-MacBook-Pro.local>
Co-authored-by: Claude <noreply@anthropic.com>
Lucas C
Brian Madison
gabadi
Brian