* feat(skills): migrate Roo Code installer to native skills format
Move Roo Code from legacy `.roo/commands/` flat files to native
`.roo/skills/{skill-name}/SKILL.md` directory output. Verified
skill discovery in Roo Code v3.51 with 43 skills installed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test(skills): add native skills tests for Claude Code, Codex, and Cursor
Add dedicated test suites covering config validation, fresh install,
legacy cleanup, and ancestor conflict detection for Claude Code, Codex
CLI, and Cursor. Updates migration checklist to reflect verified status.
84 assertions now pass (up from 50).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test(skills): add Roo Code reinstall/upgrade test
Verify that running Roo setup over existing skills output succeeds
and preserves SKILL.md output. Checks off the last Roo checklist item.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): migrate GitHub Copilot to config-driven native skills
Replace 699-line custom installer with config-driven skill_format.
Output moves from .github/agents/ + .github/prompts/ to
.github/skills/{skill-name}/SKILL.md. Legacy cleanup strips BMAD
markers from copilot-instructions.md and removes old directories.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: update migration checklist with Copilot and Roo verified results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): migrate Cline to config-driven native skills
Move Cline installer from .clinerules/workflows to .cline/skills with
SKILL.md directory output. Add legacy cleanup and 9 test assertions.
* feat(skills): migrate CodeBuddy to config-driven native skills
Move CodeBuddy installer from .codebuddy/commands to .codebuddy/skills
with SKILL.md directory output. Add legacy cleanup and 9 test assertions.
* feat(skills): migrate Crush to config-driven native skills
Move Crush installer from .crush/commands to .crush/skills with
SKILL.md directory output. Add legacy cleanup and 9 test assertions.
* feat(skills): migrate Trae to config-driven native skills
Move Trae installer from .trae/rules to .trae/skills with SKILL.md
directory output. Add legacy cleanup and 9 test assertions.
* feat(skills): migrate KiloCoder to config-driven native skills
Replace 269-line custom kilo.js installer with config-driven entry in
platform-codes.yaml targeting .kilocode/skills/ with skill_format: true.
- Add installer config: target_dir, skill_format, template_type, legacy_targets
- Add cleanupKiloModes() to strip BMAD modes from .kilocodemodes on cleanup
- Remove kilo.js from manager.js customFiles and Kilo-specific result handling
- Delete tools/cli/installers/lib/ide/kilo.js
- Add test Suite 22: 11 assertions (config, install, legacy cleanup, modes, reinstall)
- Update migration checklist with verified results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): migrate Gemini CLI to config-driven native skills
Replace TOML-based .gemini/commands output with native SKILL.md output
in .gemini/skills/. Gemini CLI confirms native skills support per
geminicli.com/docs/cli/skills/.
- Update platform-codes.yaml: target_dir, skill_format, legacy_targets
- Add test Suite 23: 9 assertions (config, install, legacy, reinstall)
- Add Gemini CLI section to migration checklist
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): migrate iFlow, QwenCoder, and Rovo Dev to native skills
Complete the native skills migration for all remaining platforms:
- iFlow: .iflow/commands → .iflow/skills (config change)
- QwenCoder: .qwen/commands → .qwen/skills (config change)
- Rovo Dev: replace 257-line custom rovodev.js with config-driven
.rovodev/skills, add cleanupRovoDevPrompts() for prompts.yml cleanup
All platforms now use config-driven native skills. No custom installer
files remain. Manager.js customFiles array is now empty.
- Add test suites 24-26: 20 new assertions (173 total)
- Update migration checklist: all summary gates passed
- Delete tools/cli/installers/lib/ide/rovodev.js
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(installer): preserve bmad-os-* skills during cleanup
The cleanupTarget method removed all entries starting with "bmad" from
IDE skills directories, which would also wipe version-controlled
bmad-os-* skills from the BMAD-METHOD repo. Add exclusion for the
bmad-os- prefix so those skills survive reinstalls.
* docs: flag all unverified platforms for manual IDE testing
Add NEEDS MANUAL IDE VERIFICATION to KiloCoder, Gemini CLI, iFlow,
QwenCoder, and Rovo Dev checklists. CodeBuddy, Crush, and Trae already
had the flag.
* fix(installer): suspend Kilo Code and add verified Gemini/Crush results
Kilo Code does not support the Agent Skills standard — the migration
from modes+workflows to skills was based on a false fork assumption.
- Add suspended field to platform-codes.yaml, hiding Kilo from the IDE
picker and blocking setup with a clear message
- Fail the installer early (before writing _bmad/) if all selected IDEs
are suspended, protecting existing installations from being corrupted
- Still clean up legacy Kilo artifacts (.kilocodemodes, .kilocode/workflows)
when users switch to a different IDE
- Mark Crush and Gemini CLI as manually verified (both work end-to-end)
- Replace Suite 22 install tests with suspended-behavior tests (7 assertions)
* docs: update KiloCoder checklist to reflect suspended status
* fix(skills): add canonicalIds for BMM research and PRD workflows
Drop the bmm module prefix from 6 workflow skill names so they
install as bmad-create-prd, bmad-domain-research, etc. instead of
bmad-bmm-create-prd, bmad-bmm-domain-research, etc.
* fix(installer): address PR review findings from automated reviewers
Triage of 18 findings from Augment and CodeRabbit reviews on PR #1841:
Source code fixes:
- Exclude bmad-os-* from findAncestorConflict to match cleanupTarget
- Wrap cleanupCopilotInstructions in try/catch (best-effort, not fatal)
- Wrap suspended-platform cleanup in try/catch (failure boundary)
- Clean up temp backup dirs in catch block when install aborts
- Normalize IDE keys to lowercase before suspended lookup
- Delete dead loadCustomInstallerFiles method and stale references
- Rename "Roo Cline" to "Roo Code" in both platform-codes.yaml files
- Fix Gemini CLI package name (@google/gemini-cli, not @anthropic-ai)
Test improvements:
- Add name/frontmatter invariant check to 6 missing platform suites
- Assert stale bmad-architect skill is removed after cleanup
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): add canonical bmad- naming via skill manifests
Add bmad-skill-manifest.yaml sidecars to all 38 capabilities (tasks,
agents, workflows) declaring canonicalId as the single source of truth
for skill names. Update Claude Code and Codex installers to prefer
canonicalId over path-derived names, with graceful fallback.
- 24 manifest files covering 38 capabilities
- New shared skill-manifest.js utility for manifest loading
- resolveSkillName() in path-utils.js bridges manifest → installer
- All command generators propagate canonicalId through CSV manifests
- Drops bmm module prefix from all user-facing skill names
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): claude-code installer outputs .claude/skills/<name>/SKILL.md
Refactor the config-driven installer to emit Agent Skills Open Standard
format for Claude Code: directory-per-skill with SKILL.md entrypoint,
unquoted YAML frontmatter, and full canonical names.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(installer): migrate codex to config-driven pipeline
Delete the custom codex.js installer (441 lines) and route Codex
through the config-driven pipeline via platform-codes.yaml. This
fixes 7 task/tool descriptions that were generic due to bypassing
manifests, and eliminates duplicate transformToSkillFormat code.
Key changes:
- Add codex entry to platform-codes.yaml with skill_format + legacy_targets
- Remove codex from custom installer list in manager.js
- Add installCustomAgentLauncher() to config-driven for custom agent support
- Add detect() override for skill_format platforms (bmad-prefix check)
- Set configDir from target_dir for base-class detect() compatibility
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(installer): guard codex skill installs in nested directories
* fix(installer): warn on stale global legacy skill dirs
* feat(installer): migrate cursor to native skills
* Migrate Windsurf installer to native skills
* Clarify Windsurf skill invocation in checklist
* feat(installer): migrate kiro to native skills
* docs: record kiro skill visibility verification
* Migrate Antigravity installer to native skills
* Document Antigravity ancestor skill verification
* Synchronize native skills migration checklist
* Migrate Auggie installer to native skills
* Migrate OpenCode installer to native skills
* Document live skill verification for Auggie and OpenCode
* fix(test): replace _bmad filesystem dependency with self-contained fixture
The installation component tests walked up the filesystem looking for a
pre-installed _bmad directory, which exists locally but not in CI. Replace
findInstalledBmadDir() with createTestBmadFixture() that creates a minimal
temp directory with fake compiled agents, making tests fully self-contained.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* fix(installer): refuse install when ancestor dir has BMAD commands
Claude Code inherits slash commands from parent directories, so
installing into a nested project when a parent already has .claude/commands
with bmad-* files causes duplicate entries in the autocomplete.
Add ancestor_conflict_check flag (enabled for claude-code) that walks
up the directory tree before install. If BMAD files are found in an
ancestor target_dir, the installer refuses with an actionable error.
Also fix IdeManager.setup() to propagate handler success status instead
of unconditionally returning success: true.
* Address code review feedback from CodeRabbit and Augment
- Move "Setting up..." log after conflict check so it only shows when
install will proceed
- Fix rm command: add -rf flags and correct quoting for glob outside quotes
- Improve error wording: "ancestor installation" instead of misleading
"ancestor directory"
- Use case-insensitive startsWith for bmad file detection (macOS/Windows)
- Document ancestor_conflict_check in the installer config schema
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(installer): resolve symlinks before ancestor conflict walk
Use fs.realpath() instead of path.resolve() so the ancestor directory
walk follows the physical filesystem path, not the logical symlink path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(installer): add custom Rovo Dev installer with prompts.yml generation
Rovo Dev CLI requires a .rovodev/prompts.yml manifest to register prompts
for /prompts access. The config-driven installer was writing .md files but
never generating this manifest, so /prompts showed nothing.
- Create custom rovodev.js installer extending BaseIdeSetup
- Generate prompts.yml indexing all written workflow files
- Merge with existing user entries (only touch bmad- prefixed entries)
- Remove stale rovo entry from tools/platform-codes.yaml
Closes#1466
* fix(installer): prefix prompts.yml descriptions with entry name
The /prompts list in Rovo Dev only shows descriptions, making it hard
to identify entries. Prefix each description with the bmad entry name
so users see e.g. "bmad-bmm-create-prd - PRD workflow..." instead of
just the description text.
* refactor(installer): address review findings in Rovo Dev installer
- Hoist toDashPath import to module top level
- Extract _collectPromptEntries helper replacing 3 duplicated loops
- Remove unused detectionPaths (detect() is overridden)
- Guard generatePromptsYml when writtenFiles is empty
- Align cleanup() with detect() predicate (remove any bmad-*, not just .md)
- Use BaseIdeSetup abstractions (this.pathExists/readFile/writeFile) in cleanup()
- Update loadHandlers() JSDoc to include rovodev.js
---------
Co-authored-by: Brian <bmadcode@gmail.com>
* feat(cli): add uninstall command with selective component removal
Add `bmad uninstall` CLI command for clean removal of BMAD installations.
Interactive mode with directory router and component multiselect; non-interactive
`--yes` flag preserves user artifacts by default. Three-phase spinner UX,
manifest-scoped IDE cleanup, GitHub Copilot marker stripping, recursive empty
directory cleanup, and chalk-to-clack migration in copilot handler.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(cli): address code review findings for uninstall command
- Add path traversal guard in uninstallOutputFolder (resolve + startsWith)
- Thread silent flag through to cleanupCopilotInstructions
- Trim text input before path.resolve in directory prompt
- DRY uninstall() by delegating to extracted helper methods
- Validate projectDir existence before probing for BMAD
- Use fs.rmdir instead of fs.remove in removeEmptyParents (race safety)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(cli): add destructive action warning and confirm before uninstall
Move warning box after component selection and add a confirmation prompt
defaulting to No, so users see the irreversibility warning right before
the point of no return. Non-interactive --yes mode skips both.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* feat: add custom GitHub Copilot installer handler
Adds a dedicated GitHub Copilot handler that generates:
- Agent files with .agent.md extension and enriched descriptions
- Prompt files (.prompt.md) for workflows, tasks, and agent activators
- copilot-instructions.md with project config and agent reference table
Replaces the generic config-driven handler with a custom one that
properly supports Copilot's agent/prompt file conventions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: escape YAML descriptions and preserve user copilot-instructions
- Escape single quotes in YAML frontmatter descriptions across all prompt
generators (createWorkflowPromptContent, createTechWriterPromptContent,
createAgentActivatorPromptContent) to match createAgentContent behavior
- Make copilot-instructions.md non-destructive using BMAD markers
(<!-- BMAD:START --> / <!-- BMAD:END -->) to preserve user content
- On cleanup, only remove content between markers; skip files without markers
- Back up existing unmarked files before overwriting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add error handling for CSV read/parse in loadAgentManifest and loadBmadHelp
Wrap file read and csv.parse in try/catch blocks so malformed or
unreadable CSV files gracefully degrade instead of aborting setup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use specific detection paths instead of .github configDir
Set configDir to null and use detectionPaths with
.github/copilot-instructions.md and .github/agents/ so the base
detect() doesn't false-positive on every GitHub repo.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add comments explaining hardcoded bmm/config.yaml in prompts
Clarify that bmm/config.yaml is safe to hardcode in generated prompt
content because these prompts are only created when bmm module data
(bmad-help.csv, agent artifacts) exists.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: guard against missing workflow-file in bmad-help.csv entries
Skip entries where workflow-file is empty/undefined to prevent
workflowFile.endsWith() from throwing during prompt generation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: guard escapeYamlSingleQuote against undefined input
Default to empty string when value is undefined/null to prevent
replaceAll from throwing on missing CSV fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: preserve customised tool permissions across reinstalls
Before this change, reinstalling would overwrite any user-customised
tools arrays in agent and prompt frontmatter with the hardcoded default.
Now the installer reads existing tool permissions from .agent.md and
.prompt.md files before cleanup, and re-applies them to the regenerated
files. Falls back to the default ['read', 'edit', 'search', 'execute']
for new files or files without prior customisation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: prevent cleanup from stripping copilot-instructions.md markers before generation
The cleanup() method was removing the BMAD marker section from
copilot-instructions.md, leaving user content without markers.
generateCopilotInstructions() then treated the markerless file as
legacy, backed it up, and overwrote user content.
Fix: remove the copilot-instructions.md block from cleanup() entirely.
generateCopilotInstructions() already handles marker-based replacement
in a single read-modify-write pass that correctly preserves user content.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: update manager.js comments to include github-copilot.js
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: make agent capabilities data-driven via agent YAML metadata
Replace the hardcoded getAgentCapabilities() map with a data-driven
pipeline. Capabilities are now defined in each .agent.yaml source file,
compiled into the XML output, extracted into agent-manifest.csv by the
manifest generator, and read by the GitHub Copilot handler at install
time. New agents automatically get their capabilities without code
changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use this.bmadFolderName instead of hardcoded _bmad in template paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(cli): complete @clack/prompts migration
Full migration of BMAD CLI installer from legacy terminal libraries
(chalk, ora, boxen, figlet, wrap-ansi, cli-table3, readline) to unified
@clack/prompts v1.0.0 visual system.
Foundation (prompts.js + cli-utils.js):
- Extended prompts.js wrapper with box, spinner, progress, taskLog,
path, autocomplete, selectKey, stream, color re-export
- Refactored cli-utils.js: displayLogo uses box(), sections use note(),
steps use log.step(), removed boxen/figlet/wrap-ansi/cli-table3
UI orchestration (ui.js):
- Replaced ~100 console.log+chalk calls with log.*, note(), box()
- Replaced ora spinner with @clack spinner
- Module selection: autocompleteMultiselect with locked core module,
bulleted post-selection display, maxItems for no-scroll
Spinner migration (installer.js):
- Replaced 40+ ora spinner calls with @clack spinner
- All spinner.stop() calls include meaningful messages
- Failure paths use spinner.error() (red cross) instead of stop()
Readline migration (agent/installer.js + config-collector.js):
- Migrated readline prompts to @clack text/confirm/select
- Fixed chalk.dim bug (chalk was never imported)
- Removed chalk from config-collector.js
IDE handlers + modules (7 files):
- Replaced chalk+ora across all IDE handlers and module manager
- Fixed options.installer undefined bug in manager.js update()
Cleanup:
- Removed ora, boxen, figlet, wrap-ansi, cli-table3 from dependencies
- chalk stays (used outside tools/cli/ scope)
- Replaced hand-drawn Unicode update box in bmad-cli.js with box()
- Added process.stdin.setMaxListeners(25) for sequential prompts
Spinner wrapper adds isSpinning state tracking (not native to @clack).
Removed dead groupMultiselect and sortKey sort calls.
Ref: tech-spec-installer-clack-migration-ui-enhancement.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(cli): consolidate installer output to single spinner + summary
Replace ~40 lines of output from 15+ spinner start/stop cycles with a
single animated spinner during installation and a final note() summary
block showing checkmarks per step.
Key changes:
- Add results collector pattern in install() method
- Replace spinner.stop/start pairs with addResult + spinner.message
- Add renderInstallSummary() using prompts.note() with colored output
- Propagate silent flag through IDE handlers and module manager
- Add spinner race condition guards (start while spinning, stop while stopped)
- Add no-op spinner pattern for silent external module cloning
- Fix stdin listener limit to be defensive with Math.max
- Add GIT_TERMINAL_PROMPT=0 for non-interactive git operations
- Merge locked values into initialValue for autocomplete prompts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(cli): resolve code review findings from @clack/prompts migration
Address 31 issues across 14 CLI files found during PR #1586 review
(Augment Code + CodeRabbit):
- Fix bmadDir ReferenceError by hoisting declaration before try block
- Wrap console.log monkey-patch in try/finally for safe restoration
- Fix transformWorkflowPath dead code and undefined return path
- Fix broken symlink crash in _config-driven.js and codex.js cleanup
- Pass installer instance through update() for agent recompilation
- Fix @clack/prompts API: defaultValue→default, initialValue→default
- Use nullish coalescing (??) instead of logical OR for falsy values
- Forward options in recursive promptToolSelection calls
- Remove no-op replaceAll('_bmad','_bmad') in manager and generator
- Remove unused confirm prompt in config-collector hasNoConfig branch
- Guard spinner.message() when spinner is not running
- Add missing methods to silent spinner stub (cancel, clear, isSpinning)
- Wrap install.js error handler with inner try/catch + console fallback
- Gate codex per-entry error log with silent flag
- Add return statements to all stream wrapper methods
- Remove dead variables (availableNames, hasCustomContentItems)
- Filter core module from update flow selection
- Replace borderColor ternary chain with object map
- Fix Kilo "agents" label to "modes" in IDE manager
- Normalize error return shape for unsupported IDEs
- Fix spinner message timing before dependency resolution
- Guard undefined moduleDir in dependency-resolver
- Fix workflowsInstalled counter inflation in custom handler
- Migrate console.warn calls to prompts.log.warn
- Replace console.log() with prompts.log.message('')
- Fix legacyBmadPath hardcoded to .bmad instead of entry.name
- Fix focusedValue never assigned breaking SPACE toggle and hints
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: support CRLF line endings and add task/tool templates for all IDEs
* fix: preserve file extensions in IDE task/tool paths and update BMAD branding
* fix: double extension issue in wrapper filename generation
* fix: correct path handling and variable reference in task/tool command generator
* fix: change default BMAD folder name from 'bmad' to '_bmad' across all IDE components
* refactor: centralize BMAD_FOLDER_NAME constant in path-utils
* fix: Replace the rest of BMAD_FOLDER magic values
* fix: add safety checks for setBmadFolderName method calls in IdeManager
* fix: convert absolute paths to relative in task-tool-command-generator
* fix: support .xml task files in bmad-artifacts task discovery
* fix: skip internal tasks in manifest generation and IDE command discovery
* fix: skip empty artifact_types targets and remove unused vscode_settings target
* fix: skip internal tools in manifest generation and improve Windows path handling in command generator
* fix: use csv-parse library for proper CSV handling in manifest generation
* refactor: extract CSV text cleaning to reusable method in manifest generator
* fix: normalize path separators to forward slashes in agent file copying for cross-platform compatibility
---------
Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* docs: radical reduction of documentation scope for v6 beta
Archive and basement unreviewed content to ship a focused, minimal doc set.
Changes:
- Archive stale how-to workflow guides (will rewrite for v6)
- Archive outdated explanation and reference content
- Move unreviewed content to basement for later review
- Reorganize TEA docs into dedicated /tea/ section
- Add workflow-map visual reference page
- Simplify getting-started tutorial and sidebar navigation
- Add explanation pages: brainstorming, adversarial-review, party-mode,
quick-flow, advanced-elicitation
- Fix base URL handling for subdirectory deployments (GitHub Pages forks)
The goal is a minimal, accurate doc set for beta rather than
comprehensive but potentially misleading content.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: restructure BMM and agents documentation by consolidating and flattening index files.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
## 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>
Alex Verkhovsky
Davor Racic
jheyworth
Brian Madison