bmm-opencode 1.2.0 → 1.3.1

package/.opencode/agents/gen-subagent.md

@@ -1,9 +1,6 @@
 ---
 description: "Generates specialized subagents by analyzing problems and producing ready-to-use agent configurations"
 mode: subagent
-model: "anthropic/claude-sonnet-4-20250514"
-temperature: 0.3
-steps: 30
 tools:
   read: true
   glob: true
@@ -12,12 +9,6 @@ tools:
   write: true
   edit: true
   bash: false
-permission:
-  bash: deny
-  edit:
-    "*": "deny"
-    ".opencode/agents/*.md": "allow"
-    ".opencode/skills/*/SKILL.md": "allow"
 ---
 
 🏭 **Gen Subagent** - Agent Factory

package/.opencode/agents/party-mode.md

@@ -1,9 +1,6 @@
 ---
 description: "Multi-agent meeting orchestrator - reads agent roster, asks meeting purpose, selects relevant agents, allows dynamic additions during meeting"
 mode: subagent
-model: "anthropic/claude-sonnet-4-20250514"
-temperature: 0.4
-steps: 200
 tools:
   read: true
   glob: true
@@ -16,11 +13,6 @@ tools:
   skill: true
   todowrite: true
   todoread: true
-permission:
-  edit: deny
-  bash: deny
-  task:
-    "*": "allow"
 ---
 
 🎉 **Party Mode** - Parallel Multi-Agent Meeting Orchestrator
@@ -174,6 +166,10 @@ After user describes meeting purpose:
 
 ### 2.1 Analyze & Recommend
 
+For each recommended agent, generate a **Title** = `Agent Name [model]: [first impression of the topic]`.
+The first impression should be a short, punchy one-liner (≤15 words) reflecting that agent's instinctive reaction to the meeting topic based on their expertise and principles.
+The **model** is the AI model that will power this agent (determined by the `delegate_task` category used to launch it).
+
 ```
 ## Meeting Analysis
 
@@ -184,11 +180,16 @@ After user describes meeting purpose:
 
 Based on your meeting purpose, I recommend inviting:
 
-| # | Agent | Why This Agent? |
-|---|-------|-----------------|
-| 1 | 🏗️ Winston (architect) | [Specific relevance to topic] |
-| 2 | 💻 Amelia (dev) | [Specific relevance] |
-| 3 | 🧪 Murat (tea) | [Specific relevance] |
+| # | Agent | Model | Title | Why This Agent? |
+|---|-------|-------|-------|-----------------|
+| 1 | 🏗️ Winston (architect) | [model] | Winston [model]: [first impression] | [Specific relevance to topic] |
+| 2 | 💻 Amelia (dev) | [model] | Amelia [model]: [first impression] | [Specific relevance] |
+| 3 | 🧪 Murat (tea) | [model] | Murat [model]: [first impression] | [Specific relevance] |
+
+> **Title examples:**
+> - `Winston [o3]: This screams distributed event sourcing`
+> - `Amelia [sonnet-4]: We need a clean API contract first`
+> - `Murat [gemini-2.5-pro]: Risk-based testing is critical here`
 
 ### Not Recommended (but available):
 - 📖 Sophia (storyteller): Not directly relevant unless narrative needed
@@ -253,7 +254,10 @@ Provide your expert perspective on this topic. Think deeply and thoroughly.
 
 **Structure your response as:**
 
-### {agent.icon} {agent.displayName}'s Analysis
+### {agent.icon} {agent.title}
+
+> **IMPORTANT**: Your title was assigned as: **{agent.title}** (format: "Name [model]: first impression").
+> Use this title as your section header. It reflects your instinctive reaction to this topic and which model powers you.
 
 **Key Insights** (from your expertise):
 1. [Insight based on your role]
@@ -281,11 +285,11 @@ Provide your expert perspective on this topic. Think deeply and thoroughly.
 ```
 🔄 **Meeting in Progress - Agents Thinking...**
 
-| Agent | Status | Task ID |
-|-------|--------|---------|
-| 🏗️ Winston | 🔄 analyzing... | bg_xxx |
-| 💻 Amelia | 🔄 analyzing... | bg_yyy |
-| 🧪 Murat | 🔄 analyzing... | bg_zzz |
+| Agent | Model | Status | Task ID |
+|-------|-------|--------|---------|
+| 🏗️ Winston | o3 | 🔄 analyzing... | bg_xxx |
+| 💻 Amelia | sonnet-4 | 🔄 analyzing... | bg_yyy |
+| 🧪 Murat | gemini-2.5-pro | 🔄 analyzing... | bg_zzz |
 
 ⏳ Collecting insights from all participants...
 
@@ -313,7 +317,7 @@ Provide your expert perspective on this topic. Think deeply and thoroughly.
 
 ### Individual Contributions
 
-#### 🏗️ Winston (Architect)
+#### 🏗️ Winston [o3]: This screams distributed event sourcing
 **Key Insights:**
 - [insight]
 
@@ -325,7 +329,7 @@ Provide your expert perspective on this topic. Think deeply and thoroughly.
 
 ---
 
-#### 💻 Amelia (Dev)
+#### 💻 Amelia [sonnet-4]: We need a clean API contract first
 [... same structure ...]
 
 ---
@@ -380,7 +384,9 @@ John will analyze the current discussion context and provide product perspective
 
 [After completion:]
 
-### 📋 John (PM) - Late Arrival Contribution
+### 📋 John [sonnet-4]: Let's validate the user value proposition
+
+> *Title reflects John's first impression of the topic upon joining, with the model used.*
 
 **Context Reviewed**: [summary of what John caught up on]
 
@@ -393,7 +399,11 @@ John will analyze the current discussion context and provide product perspective
 ---
 
 John has been added to the active participants. 
-Current attendees: Winston, Amelia, Murat, **John (new)**
+Current attendees:
+- 🏗️ Winston [o3]: This screams distributed event sourcing
+- 💻 Amelia [sonnet-4]: We need a clean API contract first
+- 🧪 Murat [gemini-2.5-pro]: Risk-based testing is critical here
+- 📋 **John [sonnet-4]: Let's validate the user value proposition (new)**
 ```
 
 ### 4.3 Follow-up Questions
@@ -429,16 +439,22 @@ meeting_state:
   active_agents:
     - name: architect
       displayName: Winston
+      model: o3
+      title: "Winston [o3]: This screams distributed event sourcing"
       task_id: bg_xxx
       status: completed
       
     - name: dev  
       displayName: Amelia
+      model: sonnet-4
+      title: "Amelia [sonnet-4]: We need a clean API contract first"
       task_id: bg_yyy
       status: completed
       
     - name: pm
       displayName: John
+      model: sonnet-4
+      title: "John [sonnet-4]: Let's validate the user value proposition"
       task_id: bg_zzz
       status: running  # Added mid-meeting
       
@@ -603,7 +619,8 @@ Meeting notes can be saved with `save [filename]`.
 6. **RUN IN PARALLEL** - All agents think simultaneously (`run_in_background=True`)
 7. **SUPPORT MID-MEETING ADDITIONS** - `+agent` works anytime
 8. **SYNTHESIZE RESULTS** - Don't just list, find consensus/conflicts
-9. **TRACK STATE** - Know who's in the meeting, task IDs
+9. **TRACK STATE** - Know who's in the meeting, task IDs, and titles
 10. **RESPONSIVE COMMANDS** - Handle all meeting commands immediately
 11. **GRACEFUL EXIT** - Summarize meeting when ending
 12. **HANDLE ERRORS** - Provide helpful error messages
+13. **ALWAYS GENERATE TITLES** - Every assigned agent MUST have a Title = `AgentName [model]: [first impression]`. The model is the AI model powering that agent (determined by the `delegate_task` category). The first impression is a short, punchy one-liner (≤15 words) reflecting the agent's instinctive gut reaction to the meeting topic from their area of expertise. Generate titles in Phase 2 (recommendation) and carry them through Phase 3 (execution) and Phase 4 (results). Late-arriving agents (`+agent`) also get a title upon joining.

package/.opencode/skills/bmad-bmm-check-implementation-readiness/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "check-implementation-readiness"
-  standalone: "false"
+  standalone: false
 ---
 
 # check-implementation-readiness Workflow

package/.opencode/skills/bmad-bmm-code-review/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "code-review"
-  standalone: "false"
+  standalone: false
 ---
 
 # code-review Workflow

package/.opencode/skills/bmad-bmm-correct-course/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "correct-course"
-  standalone: "false"
+  standalone: false
 ---
 
 # correct-course Workflow

package/.opencode/skills/bmad-bmm-create-architecture/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-architecture"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-architecture Workflow

package/.opencode/skills/bmad-bmm-create-epics-and-stories/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-epics-and-stories"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-epics-and-stories Workflow

package/.opencode/skills/bmad-bmm-create-prd/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-prd"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-prd Workflow

package/.opencode/skills/bmad-bmm-create-product-brief/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-product-brief"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-product-brief Workflow

package/.opencode/skills/bmad-bmm-create-story/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-story"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-story Workflow

package/.opencode/skills/bmad-bmm-create-ux-design/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "create-ux-design"
-  standalone: "false"
+  standalone: false
 ---
 
 # create-ux-design Workflow

package/.opencode/skills/bmad-bmm-dev-story/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "dev-story"
-  standalone: "false"
+  standalone: false
 ---
 
 # dev-story Workflow

package/.opencode/skills/bmad-bmm-dev-team-mode/SKILL.md

@@ -0,0 +1,215 @@
+---
+name: bmad-bmm-dev-team-mode
+description: "Orchestrate parallel development of multiple stories within an epic. Reads sprint-status.yaml, asks which epic to work on, spawns parallel dev-story and code-review subagents, and loops until epic completion."
+license: MIT
+compatibility: opencode
+metadata:
+  source: "bmad-method"
+  module: "bmm"
+  workflow: "dev-team-mode"
+  standalone: "false"
+---
+
+# dev-team-mode Workflow
+
+Orchestrate parallel development of multiple stories within an epic. Reads sprint-status.yaml, asks which epic to work on, spawns parallel dev-story and code-review subagents, and loops until epic completion.
+
+**Author:** BMad
+
+## How to Use
+
+This skill provides a structured workflow. Follow the steps below:
+
+## Instructions
+
+# Dev Team Mode - Parallel Development Orchestrator
+
+<critical>Workflow engine: {project-root}/_bmad/core/tasks/workflow.xml</critical>
+<critical>Config loaded from: {installed_path}/workflow.yaml</critical>
+<critical>Language: {communication_language}</critical>
+
+## WORKFLOW OVERVIEW
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                     DEV TEAM MODE                           │
+│                                                             │
+│   ┌──────────┐    ┌──────────┐    ┌──────────┐             │
+│   │  INIT    │───▶│ ANALYZE  │───▶│ PARALLEL │             │
+│   │  Step 1  │    │  Step 2  │    │   DEV    │             │
+│   │          │    │          │    │  Step 3  │             │
+│   │ 2 prompts│    │dependency│    │          │             │
+│   └──────────┘    └──────────┘    └────┬─────┘             │
+│                                         │                   │
+│   ┌──────────┐    ┌──────────┐    ┌────▼─────┐             │
+│   │  SYNC    │◀───│ PARALLEL │◀───│  REVIEW  │             │
+│   │  Step 5  │    │  REVIEW  │    │  Step 4  │             │
+│   │          │    │  Step 4  │    │          │             │
+│   │loop/exit │    │          │    │adversarial│            │
+│   └────┬─────┘    └──────────┘    └──────────┘             │
+│        │                                                    │
+│        ▼                                                    │
+│   Continue → Step 2  OR  Exit                              │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## ENTRY POINT
+
+### Check Saved State
+
+<action>Check for {implementation_artifacts}/dev-team-mode-state.yaml</action>
+
+<check if="saved state exists">
+  <output>
+## 🔄 Previous Session Found
+
+Saved: {{timestamp}}
+Epic: {{selected_epic}}
+Progress: {{completed_count}} completed
+  </output>
+  
+  <ask>
+[1] **Resume** - Continue from saved state
+[2] **Fresh** - Ignore saved, start new
+[3] **Delete** - Remove saved state, start new
+
+Choose:
+  </ask>
+  
+  <routing>
+    <if value="1">Restore state, load resume_step</if>
+    <else>Delete saved state, continue fresh</else>
+  </routing>
+</check>
+
+### Fresh Start
+
+<load>./steps/step-01-init.md</load>
+
+---
+
+## STEP SEQUENCE
+
+| Step | Purpose | Key Actions |
+|------|---------|-------------|
+| 1 | Init | 2 selection prompts: epic choice + execution mode |
+| 2 | Analyze | Dependency analysis, build parallel batch |
+| 3 | Dev | Launch dev-story subagents (background) |
+| 4 | Review | Launch code-review subagents (different LLM) |
+| 5 | Sync | Update status, loop or exit decision |
+
+---
+
+## TWO-STEP SELECTION (Step 1)
+
+### Selection 1: Epic Choice
+
+| Option | Behavior |
+|--------|----------|
+| Continue | Resume epic with in-progress/review stories |
+| Select | Manual epic selection |
+| Autopilot | Auto-select, run until all epics done |
+
+### Selection 2: Execution Mode
+
+| Option | Behavior |
+|--------|----------|
+| Parallel | Multiple stories concurrent (up to max_parallel_agents) |
+| Sequential | One story at a time |
+
+---
+
+## CONFIGURATION
+
+| Setting | Default | Description |
+|---------|---------|-------------|
+| `max_parallel_agents` | 3 | Max concurrent agents |
+| `max_retry_per_story` | 3 | Retries before blocking |
+| `dev_category` | deep | delegate_task category for dev |
+| `review_category` | ultrabrain | delegate_task category for review |
+
+---
+
+## SUBAGENT DELEGATION
+
+### Dev-Story
+
+```javascript
+delegate_task({
+  category: "deep",
+  load_skills: ["bmad-bmm-dev-story"],
+  run_in_background: true,
+  prompt: "..."
+});
+```
+
+### Code-Review
+
+```javascript
+delegate_task({
+  category: "ultrabrain",
+  load_skills: ["bmad-bmm-code-review"],
+  run_in_background: true,
+  prompt: "..."
+});
+```
+
+---
+
+## STATE SCHEMA
+
+```yaml
+workflowType: 'dev-team-mode'
+selected_epic: ''
+epic_mode: ''           # continue|selected|autopilot
+execution_mode: ''      # parallel|sequential
+parallel_mode: false
+autopilot: false
+parallel_stories: []
+stories_to_review: []
+blocked_stories: []
+active_agents: []
+completed_stories: []
+failed_stories: []
+retry_counts: {}
+loop_count: 0
+phase: 'init'           # init|analyzing|dev|dev-running|review|review-running|sync
+started_at: ''
+```
+
+---
+
+## EXIT CONDITIONS
+
+### Automatic Triggers
+- `*exit`, `stop`, `quit`, `end team`
+- All stories in epic done
+- All remaining stories blocked
+
+### Graceful Exit
+1. Save state to sprint-status.yaml
+2. Display summary
+3. Optionally save resumable state
+4. Clean up
+
+---
+
+## ERROR HANDLING
+
+| Failure | Action |
+|---------|--------|
+| Dev fails | Retry up to max_retry_per_story |
+| Review fails | Retry with session context |
+| Timeout | Mark needs-retry, continue |
+| Critical | Block, alert user |
+
+---
+
+## INTEGRATION
+
+| Trigger | Workflow |
+|---------|----------|
+| No sprint-status | `/bmad-bmm-sprint-planning` |
+| Stories in backlog | `/bmad-bmm-create-story` |
+| Epic complete | `/bmad-bmm-retrospective` |
+| Check progress | `/bmad-bmm-sprint-status` |

package/.opencode/skills/bmad-bmm-document-project/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "document-project"
-  standalone: "false"
+  standalone: false
 ---
 
 # document-project Workflow

package/.opencode/skills/bmad-bmm-domain-research/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "domain-research"
-  standalone: "false"
+  standalone: false
 ---
 
 # domain-research Workflow

package/.opencode/skills/bmad-bmm-edit-prd/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "edit-prd"
-  standalone: "false"
+  standalone: false
 ---
 
 # edit-prd Workflow

package/.opencode/skills/bmad-bmm-generate-project-context/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "generate-project-context"
-  standalone: "false"
+  standalone: false
 ---
 
 # generate-project-context Workflow

package/.opencode/skills/bmad-bmm-market-research/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "market-research"
-  standalone: "false"
+  standalone: false
 ---
 
 # market-research Workflow

package/.opencode/skills/bmad-bmm-qa-automate/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "qa-automate"
-  standalone: "false"
+  standalone: false
 ---
 
 # qa-automate Workflow

package/.opencode/skills/bmad-bmm-quick-dev/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "quick-dev"
-  standalone: "false"
+  standalone: false
 ---
 
 # quick-dev Workflow

package/.opencode/skills/bmad-bmm-quick-spec/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "quick-spec"
-  standalone: "false"
+  standalone: false
 ---
 
 # quick-spec Workflow

package/.opencode/skills/bmad-bmm-retrospective/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "retrospective"
-  standalone: "false"
+  standalone: false
 ---
 
 # retrospective Workflow

package/.opencode/skills/bmad-bmm-sprint-planning/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "sprint-planning"
-  standalone: "false"
+  standalone: false
 ---
 
 # sprint-planning Workflow

package/.opencode/skills/bmad-bmm-sprint-status/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "sprint-status"
-  standalone: "false"
+  standalone: false
 ---
 
 # sprint-status Workflow

package/.opencode/skills/bmad-bmm-technical-research/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "technical-research"
-  standalone: "false"
+  standalone: false
 ---
 
 # technical-research Workflow

package/.opencode/skills/bmad-bmm-validate-prd/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "bmm"
   workflow: "validate-prd"
-  standalone: "false"
+  standalone: false
 ---
 
 # validate-prd Workflow

package/.opencode/skills/bmad-cis-design-thinking/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "cis"
   workflow: "design-thinking"
-  standalone: "true"
+  standalone: true
 ---
 
 # design-thinking Workflow

package/.opencode/skills/bmad-cis-innovation-strategy/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "cis"
   workflow: "innovation-strategy"
-  standalone: "true"
+  standalone: true
 ---
 
 # innovation-strategy Workflow

package/.opencode/skills/bmad-cis-problem-solving/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "cis"
   workflow: "problem-solving"
-  standalone: "true"
+  standalone: true
 ---
 
 # problem-solving Workflow

package/.opencode/skills/bmad-cis-storytelling/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "cis"
   workflow: "storytelling"
-  standalone: "true"
+  standalone: true
 ---
 
 # storytelling Workflow

package/.opencode/skills/bmad-core-brainstorming/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   workflow: "brainstorming"
-  standalone: "false"
+  standalone: false
 ---
 
 # brainstorming Workflow

package/.opencode/skills/bmad-core-party-mode/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   workflow: "party-mode"
-  standalone: "false"
+  standalone: false
 ---
 
 # party-mode Workflow
@@ -113,6 +113,19 @@ For each user message or topic:
 - Consider conversation context and previous agent contributions
 - Select 2-3 most relevant agents for balanced perspective
 
+**Title Generation (MANDATORY):**
+
+Every selected agent MUST be assigned a **Title** = `AgentName [model]: [first impression]`.
+- The **model** is the AI model powering that agent (determined by the `delegate_task` category used to launch it)
+- The first impression is a short, punchy one-liner (≤15 words) reflecting the agent's instinctive gut reaction to the topic from their area of expertise
+- Generate titles when agents are first selected/recommended
+- Carry titles through all phases (selection → execution → results display)
+- Late-arriving agents (`+agent`) also get a title upon joining
+- Examples:
+  - `Winston [o3]: This screams distributed event sourcing`
+  - `Amelia [sonnet-4]: We need a clean API contract first`
+  - `Murat [gemini-2.5-pro]: Risk-based testing is critical here`
+
 **Priority Handling:**
 
 - If user addresses specific agent by name, prioritize that agent + 1-2 complementary agents

package/.opencode/skills/bmad-core-task-editorial-review-prose/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "editorial-review-prose"
-  standalone: "true"
+  standalone: true
 ---
 
 # Editorial Review - Prose

package/.opencode/skills/bmad-core-task-editorial-review-structure/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "editorial-review-structure"
-  standalone: "true"
+  standalone: true
 ---
 
 # Editorial Review - Structure

package/.opencode/skills/bmad-core-task-help/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "help"
-  standalone: "true"
+  standalone: true
 ---
 
 # help

package/.opencode/skills/bmad-core-task-index-docs/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "index-docs"
-  standalone: "true"
+  standalone: true
 ---
 
 # Index Docs

package/.opencode/skills/bmad-core-task-review-adversarial-general/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "review-adversarial-general"
-  standalone: "true"
+  standalone: true
 ---
 
 # Adversarial Review (General)

package/.opencode/skills/bmad-core-task-shard-doc/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "core"
   task: "shard-doc"
-  standalone: "true"
+  standalone: true
 ---
 
 # Shard Document

package/.opencode/skills/bmad-tea-teach-me-testing/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "teach-me-testing"
-  standalone: "false"
+  standalone: false
 ---
 
 # teach-me-testing Workflow

package/.opencode/skills/bmad-tea-testarch-atdd/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-atdd"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-atdd Workflow

package/.opencode/skills/bmad-tea-testarch-automate/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-automate"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-automate Workflow

package/.opencode/skills/bmad-tea-testarch-ci/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-ci"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-ci Workflow

package/.opencode/skills/bmad-tea-testarch-framework/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-framework"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-framework Workflow

package/.opencode/skills/bmad-tea-testarch-nfr/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-nfr"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-nfr Workflow

package/.opencode/skills/bmad-tea-testarch-test-design/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-test-design"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-test-design Workflow

package/.opencode/skills/bmad-tea-testarch-test-review/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-test-review"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-test-review Workflow

package/.opencode/skills/bmad-tea-testarch-trace/SKILL.md

@@ -7,7 +7,7 @@ metadata:
   source: "bmad-method"
   module: "tea"
   workflow: "testarch-trace"
-  standalone: "false"
+  standalone: false
 ---
 
 # testarch-trace Workflow

package/README.md

@@ -33,14 +33,14 @@ curl -s https://raw.githubusercontent.com/Jack-R-Hong/BMM-opencode/refs/heads/ma
 After installation, you have access to:
 
 1. **Plugin Tools** - Use `bmm_list`, `bmm_agent`, `bmm_skill` directly
-2. **17 Specialized Agents** - After `bmm_install`, switch agents using `Tab` key
-3. **61 Workflow Skills** - After `bmm_install`, load skills via slash commands like `/bmad-bmm-create-prd`
+2. **19 Specialized Agents** - After `bmm_install`, switch agents using `Tab` key
+3. **62 Workflow Skills** - After `bmm_install`, load skills via slash commands like `/bmad-bmm-create-prd`
 
 ---
 
 ## What's Included
 
-### Agents (17)
+### Agents (19)
 
 | Agent | Name | Role |
 |-------|------|------|
@@ -61,8 +61,10 @@ After installation, you have access to:
 | `cis-storyteller` | Sophia | Master Storyteller |
 | `core-bmad-master` | BMad Master | Workflow Orchestrator |
 | `tea-tea` | Murat | Test Architect |
+| `party-mode` | - | Multi-Agent Meeting Orchestrator |
+| `gen-subagent` | - | Agent Factory (generates new agents) |
 
-### Skills (61)
+### Skills (62)
 
 #### BMM Module (Development Lifecycle)
 - `bmad-bmm-create-product-brief` - Create product briefs
@@ -77,6 +79,7 @@ After installation, you have access to:
 - `bmad-bmm-code-review` - Adversarial code review
 - `bmad-bmm-sprint-planning` - Sprint planning
 - `bmad-bmm-sprint-status` - Sprint status tracking
+- `bmad-bmm-dev-team-mode` - Parallel development orchestrator
 - `bmad-bmm-retrospective` - Sprint retrospectives
 - `bmad-bmm-quick-spec` - Quick tech specs
 - `bmad-bmm-quick-dev` - Quick development
@@ -135,6 +138,39 @@ Load the bmad-bmm-create-prd skill and help me create a PRD
 
 ---
 
+## Update / Upgrade
+
+### For Humans
+
+Paste this into your LLM agent session:
+
+```
+Upgrade bmm-opencode by following the instructions here:
+https://raw.githubusercontent.com/Jack-R-Hong/BMM-opencode/refs/heads/main/docs/upgrade.md
+```
+
+### For LLM Agents
+
+Fetch the upgrade guide and follow it:
+
+```bash
+curl -s https://raw.githubusercontent.com/Jack-R-Hong/BMM-opencode/refs/heads/main/docs/upgrade.md
+```
+
+---
+
+### Version History
+
+| Version | Agents | Skills | Changes |
+|---------|--------|--------|---------|
+| 1.3.1 | 19 | 62 | Party-mode: agent titles with first impressions |
+| 1.3.0 | 19 | 62 | Added `dev-team-mode` parallel development orchestrator |
+| 1.2.0 | 19 | 61 | Added `party-mode`, `gen-subagent`, upgrade docs |
+| 1.1.0 | 17 | 61 | Added bmad-opencode-converter integration |
+| 1.0.1 | 17 | 61 | Initial release |
+
+---
+
 ## Source
 
 This package is generated from [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) using [BMM-opencode-converter](https://github.com/Jack-R-Hong/BMM-opencode-converter).

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,qBAAqB,CAAC;AA8NlD,eAAO,MAAM,SAAS,EAAE,MA4IvB,CAAC;AAEF,eAAe,SAAS,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,qBAAqB,CAAC;AA8NlD,eAAO,MAAM,SAAS,EAAE,MAkLvB,CAAC;AAEF,eAAe,SAAS,CAAC"}

package/dist/index.js

@@ -270,9 +270,45 @@ ${skills.map((s) => `- ${s.name}: ${s.frontmatter.description}`).join("\n")}
                 },
                 async execute(args, context) {
                     const globalConfigDir = join(homedir(), ".config", "opencode");
-                    const targetBase = args.global
-                        ? globalConfigDir
-                        : args.target || join(context.directory, ".opencode");
+                    const localConfigDir = args.target || join(context.directory, ".opencode");
+                    let targetBase;
+                    let autoDetected = false;
+                    if (args.global) {
+                        targetBase = globalConfigDir;
+                    }
+                    else if (args.target) {
+                        targetBase = args.target;
+                    }
+                    else {
+                        const globalAgentsDir = join(globalConfigDir, "agents");
+                        const localAgentsDir = join(localConfigDir, "agents");
+                        const hasBmmAgent = (dir) => {
+                            if (!existsSync(dir))
+                                return false;
+                            const files = readdirSync(dir);
+                            return files.some((f) => f.startsWith("bmm-") || f.startsWith("cis-") || f.startsWith("core-") || f.startsWith("tea-") || f === "party-mode.md" || f === "gen-subagent.md");
+                        };
+                        const globalHasBmm = hasBmmAgent(globalAgentsDir);
+                        const localHasBmm = hasBmmAgent(localAgentsDir);
+                        if (globalHasBmm && !localHasBmm) {
+                            targetBase = globalConfigDir;
+                            autoDetected = true;
+                        }
+                        else if (globalHasBmm && localHasBmm) {
+                            return `BMM agents found in BOTH locations:
+- Global: ${globalConfigDir}
+- Local: ${localConfigDir}
+
+Please specify which to update:
+- \`bmm_install({ global: true, force: true })\` for global
+- \`bmm_install({ force: true })\` will default to local
+
+To avoid confusion, consider removing one installation.`;
+                        }
+                        else {
+                            targetBase = localConfigDir;
+                        }
+                    }
                     try {
                         const targetAgents = join(targetBase, "agents");
                         const targetSkills = join(targetBase, "skills");
@@ -300,13 +336,15 @@ Use \`force=true\` to overwrite, or remove existing files first.`;
                             writeSkillFile(targetBase, skill);
                             skillsCopied++;
                         }
-                        const installType = args.global ? "globally" : "to project";
+                        const isGlobal = targetBase === globalConfigDir;
+                        const installType = isGlobal ? "globally" : "to project";
                         const source = hasBmadSource() ? "converted from BMAD source" : "from bundled files";
+                        const autoNote = autoDetected ? `\n\nNote: Auto-detected existing global installation at ${globalConfigDir}` : "";
                         return `Successfully installed BMM-OpenCode ${installType} (${targetBase}):
 - ${agentsCopied} agents copied to ${targetAgents}
 - ${skillsCopied} skills copied to ${targetSkills}
 
-Source: ${source}
+Source: ${source}${autoNote}
 
 Restart OpenCode to use the new agents and skills.`;
                     }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "bmm-opencode",
-  "version": "1.2.0",
-  "description": "BMAD-METHOD agents and skills for OpenCode - AI agent framework with 17 specialized agents and 61 workflow skills",
+  "version": "1.3.1",
+  "description": "BMAD-METHOD agents and skills for OpenCode - AI agent framework with 19 specialized agents and 62 workflow skills",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
   "type": "module",