- Remember previously configured IDEs before deleting bmad directory
- During full reinstall, treat all selected IDEs as newly selected
- Properly prompt for IDE configuration questions during reinstall
- Remove debug logging
- Fix manifest reading to use manifest.yaml instead of manifest.csv
- Show previously configured IDEs as selected by default in UI
- Skip configuration prompts for already configured IDEs during updates
- Properly collect IDE configurations during full reinstall
- Handle installation cancellation without throwing errors
- Created agent-activation-web.xml with bundled file access instructions
- Updated web-bundler to inject web activation into all agent bundles
- Agents now understand how to access <file> elements instead of filesystem
- Includes workflow execution instructions for bundled environments
- Generated new web bundles with activation blocks
* feat: add OpenCode integration implementation plan for BMAD-METHOD
* installer(opencode): add OpenCode target metadata in install.config.yaml
* chore(deps): add comment-json for JSONC parsing in OpenCode integration
* feat(installer/opencode): implement setupOpenCode with minimal instructions merge and BMAD-managed agents/commands
* feat(installer): add OpenCode (SST) to IDE selector and CLI --ide help
* fix(opencode): align generated opencode.json(c) with schema (instructions as strings; agent.prompt; command.template; remove unsupported fields)
* feat(installer): enhance OpenCode setup with agent selection and prefix options
* fix: update configuration file references from `bmad-core/core-config.yaml` to `.bmad-core/core-config.yaml` across multiple agent and task files for consistency and clarity.
* refactor: streamline OpenCode configuration prompts and normalize instruction paths for agents and tasks
* feat: add tools property to agent definitions for enhanced functionality. Otherwise opencode consders the subagents as readonly
* feat: add extraction of 'whenToUse' from agents markdown files for improved agent configuration in opencode
* feat: enhance task purpose extraction from markdown files with improved parsing and cleanup logic
* feat: add collision warnings for non-BMAD-managed agent and command keys during setup
* feat: generate and update AGENTS.md for OpenCode integration with agent and task details
* feat: add compact AGENTS.md generator and JSON-only integration for OpenCode
* chore(docs): remove completed OpenCode integration implementation plans
* feat: enable default prefixes for agent and command keys to avoid collisions
* fix: remove unnecessary line breaks in 'whenToUse' descriptions for QA agents to mathc the rest of the agents definitions and improve programatic parsing of whenToUse prop
* fix: update OpenCode references to remove 'SST' for consistency across documentation and configuration
* fix: update agent mode from 'subagent' to 'all' for consistency in agent definitions
* fix: consolidate 'whenToUse' description format for clarity and consistent parsing
* feat: add iflow cli support
* chore: update project dependencies and development tooling (#508)
- Update various direct and transitive project dependencies.
- Remove the circular `bmad-method` self-dependency.
- Upgrade ESLint, Prettier, Jest, and other dev tools.
- Update semantic-release and related GitHub packages.
Co-authored-by: Kayvan Sylvan <kayvan@meanwhile.bm>
* refactor: refactor by format
---------
Co-authored-by: Kayvan Sylvan <kayvan@sylvan.com>
Co-authored-by: Kayvan Sylvan <kayvan@meanwhile.bm>
Co-authored-by: PinkyD <paulbeanjr@gmail.com>
Co-authored-by: Brian <bmadcode@gmail.com>
- Added support for a new optional `.bmad-flattenignore` file to allow users to specify additional files to exclude from the flattened XML output.
- Updated README and documentation to reflect the new feature and provide examples for usage.
- Modified ignore rules to incorporate patterns from the `.bmad-flattenignore` file after applying `.gitignore` rules.
Benefits:
- Greater flexibility in managing file exclusions for AI model consumption.
* feat: add Augment Code IDE support with multi-location installation options
- Add Augment Code to supported IDE list in installer CLI and interactive prompts
- Configure multi-location setup for Augment Code commands:
- User Commands: ~/.augment/commands/bmad/ (global, user-wide)
- Workspace Commands: ./.augment/commands/bmad/ (project-specific, team-shared)
- Update IDE configuration with proper location handling and tilde expansion
- Add interactive prompt for users to select installation locations
- Update documentation in bmad-kb.md to include Augment Code in supported IDEs
- Implement setupAugmentCode method with location selection and file installation
This enables BMAD Method integration with Augment Code's custom command system,
allowing users to access BMad agents via /agent-name slash commands in both
global and project-specific contexts.
* Added options to choose the rule locations
* Update instruction to match with namespace for commands
* Update instruction to match with namespace for commands
* Renamed Augment Code to Auggie CLI (Augment Code)
---------
Co-authored-by: Hau Vo <hauvo@Haus-Mac-mini.local>
Co-authored-by: Brian <bmadcode@gmail.com>
This fixes a regression bug where the flatten command would fail with an
error message even when valid arguments were provided.
The bug was:
- First introduced in commit 0fdbca7
- Fixed in commit fab9d5e (v5.0.0-beta.2)
- Accidentally reintroduced in commit ed53943
The else branch at lines 130-134 was incorrectly handling the case when
users provided arguments, showing a misleading error about
'no arguments provided' when arguments were actually present.
Fixes all flatten command variations:
- npx bmad-method flatten
- npx bmad-method flatten --input /path
- npx bmad-method flatten --output file.xml
- npx bmad-method flatten --input /path --output file.xml
Co-authored-by: Brian <bmadcode@gmail.com>
Previously users had to manually type the full path or run pwd to get
the current directory when installing BMad. Now the installer prefills
the current working directory as the default, improving UX.
Co-authored-by: its-brianwithai <brian@ultrawideturbodev.com>
- Fix version-bump.js to actually update package.json version
- Add tag existence check to prevent duplicate tag errors
- Remove semantic-release dependency from version bumping
- Add automatic release notes generation from commit history
- Categorize commits into Features, Bug Fixes, and Maintenance
- Include installation instructions and changelog links
- Add preview-release-notes script for testing
- Update GitHub release creation to use generated notes
- Remove automatic versioning and dual publishing strategy
- Delete release.yaml and promote-to-stable.yaml workflows
- Add manual-release.yaml for controlled releases
- Remove semantic-release dependencies and config
- Update all documentation to use npx bmad-method install
- Configure NPM to publish to @stable tag by default
- Users can now use simple npx bmad-method install command
* feat: add support for Crush IDE configuration and commands
* fix: update Crush IDE instructions for clarity on persona/task switching
---------
Co-authored-by: Brian <bmadcode@gmail.com>
- Add missing semver dependency to installer package.json
- Configure semantic-release to use correct channels (beta/latest)
- This ensures beta releases publish to @beta tag correctly
* Add update-check command
* Adding additional information to update-check command and aligning with cli theme
* Correct update-check message to exclude global
* feat: install Cursor rules to subdirectory
Implement feature request #376 to avoid filename collisions and confusion
between repo-specific and BMAD-specific rules.
Changes:
- Move Cursor rules from .cursor/rules/ to .cursor/rules/bmad/
- Update installer configuration to use new subdirectory structure
- Update upgrader to reflect new rule directory path
This keeps BMAD Method files separate from existing project rules,
reducing chance of conflicts and improving organization.
Fixes#376
* chore: correct formatting in cursor rules directory path
---------
Co-authored-by: Stefan Klümpers <stefan.kluempers@materna.group>
Downgrade chalk, inquirer, and ora in tools/installer to CommonJS-compatible versions:
- chalk: ^5.4.1 -> ^4.1.2
- inquirer: ^12.6.3 -> ^8.2.6
- ora: ^8.2.0 -> ^5.4.1
Resolves 'is not a function' errors caused by ESM/CommonJS incompatibility.
* feat(cli): move flatten command to installer and update docs
Refactor the flatten command from tools/cli.js to tools/installer/bin/bmad.js for better integration. Add support for custom input directory and improve error handling. Update documentation in README.md and working-in-the-brownfield.md to reflect new command usage. Also clean up package-lock.json and add it to .gitignore.
* chore: update gitignore and add package-lock.json for installer tool
Remove package-lock.json from root gitignore since it's now needed for the installer tool
Add package-lock.json with dependencies for the bmad-method installer
---------
Co-authored-by: Devin Stagner <devin@blackstag.family>
* This PR introduces a powerful new Codebase Flattener Tool that aggregates entire codebases into AI-optimized XML format, making it easy to share project context with AI assistants for analysis, debugging, and development assistance.
- AI-Optimized XML Output : Generates clean, structured XML specifically designed for AI model consumption
- Smart File Discovery : Recursive file scanning with intelligent filtering using glob patterns
- Binary File Detection : Automatically identifies and excludes binary files, focusing on source code
- Progress Tracking : Real-time progress indicators with comprehensive completion statistics
- Flexible Output : Customizable output file location and naming via CLI arguments
- Gitignore Integration : Automatically respects .gitignore patterns to exclude unnecessary files
- CDATA Handling : Proper XML CDATA sections with escape sequence handling for ]]> patterns
- Content Indentation : Beautiful XML formatting with properly indented file content (4-space indentation)
- Error Handling : Robust error handling with detailed logging for problematic files
- Hierarchical Formatting : Clean XML structure with proper indentation and formatting
- File Content Preservation : Maintains original file formatting within indented CDATA sections
- Exclusion Logic : Prevents self-inclusion of output files ( flattened-codebase.xml , repomix-output.xml )
- tools/flattener/main.js - Complete flattener implementation with CLI interface
- package.json - Added new dependencies (glob, minimatch, fs-extra, commander, ora, chalk)
- package-lock.json - Updated dependency tree
- .gitignore - Added exclusions for flattener outputs
- README.md - Comprehensive documentation with usage examples
- docs/bmad-workflow-guide.md - Integration guidance
- tools/cli.js - CLI integration
- .vscode/settings.json - SonarLint configuration
```
current directory
npm run flatten
npm run flatten -- --output my-project.xml
npm run flatten -- -o /path/to/output/codebase.xml
```
The tool provides comprehensive completion summaries including:
- File count and breakdown (text/binary/errors)
- Source code size and generated XML size
- Total lines of code and estimated token count
- Processing progress and performance metrics
- Bug Fix : Corrected typo in exclusion patterns ( repromix-output.xml → repomix-output.xml )
- Performance : Efficient file processing with streaming and progress indicators
- Reliability : Comprehensive error handling and validation
- Maintainability : Clean, well-documented code with modular functions
- AI Integration : Perfect for sharing codebase context with AI assistants
- Code Reviews : Streamlined code review process with complete project context
- Documentation : Enhanced project documentation and analysis capabilities
- Development Workflow : Improved development assistance and debugging support
This tool significantly enhances the BMad-Method framework's AI integration capabilities, providing developers with a seamless way to share complete project context for enhanced AI-assisted development workflows.
* docs(bmad-core): update documentation for enhanced workflow and user guide
- Fix typos and improve clarity in user guide
- Add new enhanced development workflow documentation
- Update brownfield workflow with flattened codebase instructions
- Improve consistency in documentation formatting
* chore: remove unused files and configurations
- Delete deprecated bmad workflow guide and roomodes file
- Remove sonarlint project configuration
- Downgrade ora dependency version
- Remove jest test script
* Update package.json
Removed jest as it is not needed.
* Update working-in-the-brownfield.md
added documentation for sharding docs
* perf(flattener): improve memory efficiency by streaming xml output
- Replace in-memory XML generation with streaming approach
- Add comprehensive common ignore patterns list
- Update statistics calculation to use file size instead of content length
* fix/chore: Update console.log for user-guide.md install path. Cleaned up config files/folders and updated .gitignore (#347)
* fix: Update console.log for user-guide.md install path
Changed
IMPORTANT: Please read the user guide installed at docs/user-guilde.md
to
IMPORTANT: Please read the user guide installed at .bmad-core/user-guide.md
WHY: the actual install location of the user-guide.md is in the .bmad-core directory.
* chore: remove formatting configs and clean up gitignore
- Delete husky pre-commit hook and prettier config files
- Remove VS Code chat/copilot settings
- Reorganize and clean up gitignore entries
* feat: Overhaul and Enhance 2D Unity Game Dev Expansion Pack (#350)
* Updated game-sm agent to match the new core framework patterns
* feat:Created more comprehensive game story matching new format system as well
* feat:Added Game specific course correct task
* feat:Updated dod-checklist to match new DoD format
* feat:Added new Architect agent for appropriate architecture doc creation and design
* feat:Overhaul of game-architecture-tmpl template
* feat:Updated rest of templates besides level which doesnt really need it
* feat: Finished extended architecture documentation needed for new game story tasks
* feat: Updated game Developer to new format
* feat: Updated last agent to new format and updated bmad-kb. bmad-kb I did my best with but im not sure of it's valid usage in the expansion pack, the AI generated more of the file then myself. I made sure to include it due to the new core-config file
* feat: Finished updating designer agent to new format and cleaned up template linting errors
* Built dist for web bundle
* Increased expansion pack minor verison number
* Updated architecht and design for sharding built-in
* chore: bump bmad-2d-unity-game-dev version (minor)
* updated config.yaml for game-specific pieces to supplement core-config.yaml
* Updated game-core-config and epic processing for game story and game design. Initial implementation was far too generic
* chore: bump bmad-2d-unity-game-dev version (patch)
* feat: Fixed issue with multi-configs being needed. chore: bump bmad-2d-unity-game-dev version (patch)
* Chore: Built web-bundle
* feat: Added the ability to specify the unity editor install location.\nchore: bump bmad-2d-unity-game-dev version (patch)
* feat: core-config must be in two places to support inherited tasks at this time so added instructions to copy and create one in expansion pack folder as well. chore: bump bmad-2d-unity-game-dev version (patch)
* This PR introduces a powerful new Codebase Flattener Tool that aggregates entire codebases into AI-optimized XML format, making it easy to share project context with AI assistants for analysis, debugging, and development assistance.
- AI-Optimized XML Output : Generates clean, structured XML specifically designed for AI model consumption
- Smart File Discovery : Recursive file scanning with intelligent filtering using glob patterns
- Binary File Detection : Automatically identifies and excludes binary files, focusing on source code
- Progress Tracking : Real-time progress indicators with comprehensive completion statistics
- Flexible Output : Customizable output file location and naming via CLI arguments
- Gitignore Integration : Automatically respects .gitignore patterns to exclude unnecessary files
- CDATA Handling : Proper XML CDATA sections with escape sequence handling for ]]> patterns
- Content Indentation : Beautiful XML formatting with properly indented file content (4-space indentation)
- Error Handling : Robust error handling with detailed logging for problematic files
- Hierarchical Formatting : Clean XML structure with proper indentation and formatting
- File Content Preservation : Maintains original file formatting within indented CDATA sections
- Exclusion Logic : Prevents self-inclusion of output files ( flattened-codebase.xml , repomix-output.xml )
- tools/flattener/main.js - Complete flattener implementation with CLI interface
- package.json - Added new dependencies (glob, minimatch, fs-extra, commander, ora, chalk)
- package-lock.json - Updated dependency tree
- .gitignore - Added exclusions for flattener outputs
- README.md - Comprehensive documentation with usage examples
- docs/bmad-workflow-guide.md - Integration guidance
- tools/cli.js - CLI integration
- .vscode/settings.json - SonarLint configuration
```
current directory
npm run flatten
npm run flatten -- --output my-project.xml
npm run flatten -- -o /path/to/output/codebase.xml
```
The tool provides comprehensive completion summaries including:
- File count and breakdown (text/binary/errors)
- Source code size and generated XML size
- Total lines of code and estimated token count
- Processing progress and performance metrics
- Bug Fix : Corrected typo in exclusion patterns ( repromix-output.xml → repomix-output.xml )
- Performance : Efficient file processing with streaming and progress indicators
- Reliability : Comprehensive error handling and validation
- Maintainability : Clean, well-documented code with modular functions
- AI Integration : Perfect for sharing codebase context with AI assistants
- Code Reviews : Streamlined code review process with complete project context
- Documentation : Enhanced project documentation and analysis capabilities
- Development Workflow : Improved development assistance and debugging support
This tool significantly enhances the BMad-Method framework's AI integration capabilities, providing developers with a seamless way to share complete project context for enhanced AI-assisted development workflows.
* chore: remove unused files and configurations
- Delete deprecated bmad workflow guide and roomodes file
- Remove sonarlint project configuration
- Downgrade ora dependency version
- Remove jest test script
* docs: update command names and agent references in documentation
- Change `*create` to `*draft` in workflow guide
- Update PM agent commands to use consistent naming
- Replace `analyst` references with `architect`
- Fix command examples to match new naming conventions
---------
Co-authored-by: PinkyD <paulbeanjr@gmail.com>
* fix: Update console.log for user-guide.md install path
Changed
IMPORTANT: Please read the user guide installed at docs/user-guilde.md
to
IMPORTANT: Please read the user guide installed at .bmad-core/user-guide.md
WHY: the actual install location of the user-guide.md is in the .bmad-core directory.
* chore: remove formatting configs and clean up gitignore
- Delete husky pre-commit hook and prettier config files
- Remove VS Code chat/copilot settings
- Reorganize and clean up gitignore entries
* refactor: simplify installer package version sync script and add comments
* chore: bump core version based on provided semver type
* chore(expansion): bump bmad-creator-tools version (patch)
- Update installer config to use .claude/commands/BMad/ path
- Modify setupClaudeCode function to create nested directory structure
- Update documentation and upgrader to reflect new command location
- Improves organization by grouping all BMad commands together
* refactor(gemini-cli): change agent storage from multiple files to single concatenated file
- Update configuration to use .gemini/bmad-method/ directory instead of .gemini/agents/
- Implement new logic to concatenate all agent files into single GEMINI.md
- Add backward compatibility for existing settings.json
- Remove old agents directory and update related documentation
- Ensure all agent settings are properly loaded
* fix(ide-setup): change agent trigger symbol from @ to *
The change was made to standardize the agent trigger symbol across the system and avoid confusion with other special characters.
* docs: update gemini cli syntax and file structure
- Change agent mention syntax from @ to * in docs and config
- Update file structure documentation from .gemini/agents/ to .gemini/bmad-method/
- Add gemini cli syntax to workflow guide
* fix(ide-setup): remove redundant contextFileNames handling
* refactor: Standardize on 'GitHub Copilot' branding
- Update all references from 'Github Copilot' to 'GitHub Copilot' (official branding)
- Simplify GitHub Copilot guide reference in README
- Rebuild distribution files to reflect changes
- Ensure consistent branding across documentation and configuration
* fix: add Trae IDE support while maintaining GitHub Copilot branding
* fix: correct typos in documentation and agent files
Fix multiple instances of "assest" typo to "assets" in documentation
Correct "quetsions" typo to "questions" in repository structure sections
Add new words to cSpell dictionary in VS Code settings
* feat(trae): add support for trae ide integration
- Add trae guide documentation
- Update installer to support trae configuration
- Include trae in ide options and documentation references
- Fix typo in architect agent documentation
---------
Co-authored-by: Devin Stagner <devin@blackstag.family>
When cloning a project in a Windows environment, Git may automatically convert line endings from `\n` to `\r\n`. This can cause a mismatch in the `yaml` configuration, leading to a build failure. To resolve this, a step has been added to enforce the replacement of `\r` characters, ensuring the build can proceed normally.
# [4.20.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.19.2...v4.20.0) (2025-06-29)
### Features
* Massive documentation refactor, added explanation of the new expanded role of the QA agent that will make your code quality MUCH better. 2 new diagram clearly explain the role of the pre dev ideation cycle (prd and architecture) and the details of how the dev cycle works. ([c881dcc](c881dcc48f))
When users enter "." as the installation directory, the web bundles directory
path was not being resolved correctly, causing the bundles to not be copied.
This fix ensures the web bundles directory is resolved using the same logic
as the main installation directory, resolving relative paths from the original
working directory where npx was executed.
# [4.8.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.7.0...v4.8.0) (2025-06-19)
### Bug Fixes
* installer has fast v4 update option now to keep the bmad method up to date with changes easily without breaking any customizations from the user. The SM and DEV are much more configurable to find epics stories and architectureal information when the prd and architecture are deviant from v4 templates and/or have not been sharded. so a config will give the user the option to configure the SM to use the full large documents or the sharded versions! ([aea7f3c](aea7f3cc86))
* prevent double installation when updating v4 ([af0e767](af0e767ecf))
* resolve undefined config properties in performUpdate ([0185e01](0185e012bb))
* update file-manager to properly handle YAML manifest files ([724cdd0](724cdd07a1))
### Features
* add early v4 detection for improved update flow ([29e7bbf](29e7bbf4c5))
* add file resolution context for IDE agents ([74d9bb4](74d9bb4b2b))
* update web builder to remove IDE-specific properties from agent bundles ([2f2a1e7](2f2a1e72d6))
- 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 flag to prevent installer.install() being called twice
- Fixed undefined 'directory' error by using answers.directory
- Update flow now completes without errors
- Prevents 'Cannot read properties of undefined' error after successful update
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added optional chaining for newConfig.ide access
- Added ides array to config object in performUpdate
- Fixes 'Cannot read properties of undefined' error after update
- Ensures all required config properties are present for showSuccessMessage
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Now detects existing v4 installations immediately after directory prompt
- Offers update option upfront for existing v4 installations
- If user declines update, continues with normal installation flow
- Added 'update' install type handling in installer
- Improves user experience by streamlining the update process
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Alex Verkhovsky
Brian Madison
Javier Gomez
liyuyun-lyy
VansonLeung
Yoav Gal
Yuewen Ma
Daniel Dabrowski
Hau Vo
Mikhail Romanov
Jonathan Borgwing
circus
Brian, with AI
manjaroblack
github-actions[bot]
Thiago Freitas
cecil-the-coder
Aaron
Stefan Klümpers
semantic-release-bot
Lior Assouline
Houston Zhang
Mbosinwa Awunor
Jorge Castillo
MIPAN
Hossam Ghanam
Gabriel Lemire
Davor Racic
David Elisma
木炭
David Elisma
hieu.sats
Reider Olivér
titocr