npm - create-byan-agent - Versions diffs - 2.18.0 → 2.19.0 - Mend

create-byan-agent 2.18.0 → 2.19.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (1054) hide show

package/install/templates/_byan/bmb/workflows/agent/steps-e/e-09-celebrate.md DELETED Viewed

@@ -1,155 +0,0 @@
----
-name: 'e-09-celebrate'
-description: 'Celebrate successful agent edit completion'
-editPlan: '{bmb_creations_output_folder}/edit-plan-{agent-name}.md'
-advancedElicitationTask: '{project-root}/_byan/core/workflows/advanced-elicitation/workflow.xml'
-partyModeWorkflow: '{project-root}/_byan/core/workflows/party-mode/workflow.md'
-validationWorkflow: '{project-root}/src/modules/bmb/workflows/agent/steps-v/v-01-load-review.md'
----
-# Edit Step 9: Celebration
-## STEP GOAL:
-Celebrate the successful agent edit, provide summary of changes, and mark edit workflow completion.
-## MANDATORY EXECUTION RULES:
-- 🎉 ALWAYS celebrate the achievement with enthusiasm
-- 📖 CRITICAL: Read the complete step file before taking any action
-- 🔄 CRITICAL: Read editPlan to summarize what was accomplished
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-### Role Reinforcement:
-- ✅ You are a celebration coordinator who acknowledges successful agent improvements
-- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ You bring celebration energy, user brings their satisfaction, together we acknowledge successful collaboration
-### Step-Specific Rules:
-- 🎯 Focus on celebrating and summarizing what was accomplished
-- 🚫 FORBIDDEN to end without marking workflow completion
-- 💬 Approach: Enthusiastic while providing clear summary
-## EXECUTION PROTOCOLS:
-- 🎉 Celebrate the edit completion enthusiastically
-- 📊 Provide clear summary of all changes made
-- 💾 Mark workflow completion in edit plan
-- 🚫 FORBIDDEN to end without proper completion marking
-## CONTEXT BOUNDARIES:
-- Available context: editPlan with full edit history
-- Focus: Celebration and summary
-- Limits: No more edits, only acknowledgment
-- Dependencies: All edits successfully applied
-## MANDATORY SEQUENCE
-**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.:
-### 1. Read Edit Plan
-Read `{editPlan}` to get:
-- Original agent state
-- All edits that were applied
-- Validation results (before and after)
-### 2. Grand Celebration
-"🎉 **Excellent work!** Your agent **{agent-name}** has been successfully updated!"
-### 3. Edit Summary
-```markdown
-## Edit Summary for {agent-name}
-**Completed:** {YYYY-MM-DD HH:MM}
-**Edits Applied:** {count}
-### What Changed
-**Persona Updates:** {list or "None"}
-**Command Updates:** {list or "None"}
-**Metadata Updates:** {list or "None"}
-**Type Conversion:** {details or "None"}
-### Validation Results
-**Before:** {summary of pre-edit validation}
-**After:** {summary of post-edit validation}
-```
-### 4. Verification Guidance
-"**Quick Test:**
-- Load the agent and check it initializes correctly
-- Run through a few commands to verify behavior
-**File Locations:**
-- **Agent File:** `{agentFile}`
-- **Backup:** `{agentFile}.backup`"
-### 5. Document Completion
-Append to editPlan:
-```markdown
-## Edit Session Complete ✅
-**Completed:** {YYYY-MM-DD HH:MM}
-**Status:** Success
-### Final State
-- Agent file updated successfully
-- All edits applied
-- Backup preserved
-```
-### 6. Present MENU OPTIONS
-Display: "**✅ Agent Edit Complete! Select an Option:** [V] Run Validation [S] Skip - Complete Now [A] Advanced Elicitation [P] Party Mode"
-#### Menu Handling Logic:
-- IF V: "Loading validation phase..." → Save completion status to {editPlan}, update frontmatter with edit completion, then load, read entire file, then execute {validationWorkflow}
-- IF S: "Skipping validation. Completing workflow..." → Save completion status to {editPlan} and end workflow gracefully
-- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
-- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
-- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#6-present-menu-options)
-#### EXECUTION RULES:
-- ALWAYS halt and wait for user input after presenting menu
-- User can choose validation (V), skip to complete (S), or use advanced elicitation (A) or party mode (P)
-- After other menu items execution (A/P), return to this menu
-## CRITICAL STEP COMPLETION NOTE
-ONLY WHEN [S skip option] is selected and [completion documented], will the workflow end gracefully with agent edit complete.
-IF [V validation option] is selected, the validation workflow will be loaded to perform comprehensive validation checks.
----
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-### ✅ SUCCESS:
-- Enthusiastic celebration of edit completion
-- Clear summary of all changes provided
-- Before/after validation comparison shown
-- Verification guidance provided
-- Workflow completion marked in edit plan
-### ❌ SYSTEM FAILURE:
-- Ending without marking workflow completion
-- Not providing clear summary of changes
-- Missing celebration of achievement
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/bmb/workflows/agent/steps-v/v-01-load-review.md DELETED Viewed

@@ -1,136 +0,0 @@
----
-name: 'v-01-load-review'
-description: 'Load agent and initialize validation report'
-nextStepFile: './v-02a-validate-metadata.md'
-validationReport: '{bmb_creations_output_folder}/validation-report-{agent-name}.md'
-agentMetadata: ../data/agent-metadata.md
-advancedElicitationTask: '{project-root}/_byan/core/workflows/advanced-elicitation/workflow.xml'
-partyModeWorkflow: '{project-root}/_byan/core/workflows/party-mode/workflow.md'
----
-# Validate Step 1: Load Agent for Review
-## STEP GOAL:
-Load the existing agent file and initialize a validation report to track all findings.
-## MANDATORY EXECUTION RULES:
-- 📖 CRITICAL: Read the complete step file before taking any action
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-### Step-Specific Rules:
-- 🎯 Load the complete agent file
-- 📊 Create validation report tracking document
-- 🚫 FORBIDDEN to proceed without user confirming correct agent
-## EXECUTION PROTOCOLS:
-- 🎯 Load the complete agent YAML file
-- 📊 Parse and display agent summary
-- 💾 Create validation report document
-- 🚫 FORBIDDEN to proceed without user confirmation
-## MANDATORY SEQUENCE
-**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
-### 1. Load Agent File
-Read the complete YAML from the agent file path provided by the user.
-If the module property of the agent metadata is stand-alone, it is not a module agent.
-If the module property of the agent is a module code (like bmm, bmb, etc...) it is a module agent.
-If the property hasSidecar: true exists in the metadata, then it is an expert agent.
-Else it is a simple agent.
-If a module agent also hasSidecar: true - this means it is a modules expert agent, thus it can have sidecar.
-### 2. Display Agent Summary
-```markdown
-## Agent to Validate: {agent-name}
-**Type:** {simple|expert|module}
-**File:** {agent-file-path}
-### Current Structure:
-**Persona:** {character count} characters
-**Commands:** {count} commands
-**Critical Actions:** {count} actions
-```
-### 3. Create Validation Report
-Initialize the validation report:
-```markdown
----
-agentName: '{agent-name}'
-agentType: '{simple|expert|module}'  # Derived from module + hasSidecar
-agentFile: '{agent-file-path}'
-validationDate: '{YYYY-MM-DD}'
-stepsCompleted:
-  - v-01-load-review.md
----
-# Validation Report: {agent-name}
-## Agent Overview
-**Name:** {agent-name}
-**Type:** {simple|expert|module}  # Derived from: module + hasSidecar
-**module:** {module-value}
-**hasSidecar:** {true|false}
-**File:** {agent-file-path}
----
-## Validation Findings
-*This section will be populated by validation steps*
-```
-Write to `{validationReport}`.
-### 4. Present MENU OPTIONS
-Display: "**Is this the correct agent to validate and is it identified as the proper type?** [A] Advanced Elicitation [P] Party Mode [C] Yes, Begin Validation"
-#### Menu Handling Logic:
-- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
-- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
-- IF C: Save to {validationReport}, then only then load, read entire file, then execute {nextStepFile}
-- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#4-present-menu-options)
-#### EXECUTION RULES:
-- ALWAYS halt and wait for user input after presenting menu
-- ONLY proceed to next step when user selects 'C'
-- After other menu items execution, return to this menu
-## CRITICAL STEP COMPLETION NOTE
-ONLY WHEN [C continue option] is selected and [agent loaded and report created], will you then load and read fully `{nextStepFile}` to execute and begin validation.
----
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-### ✅ SUCCESS:
-- Agent file loaded successfully
-- Validation report created
-- User confirmed correct agent
-### ❌ SYSTEM FAILURE:
-- Failed to load agent file
-- Report not created
-- Proceeded without user confirmation
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/bmb/workflows/agent/steps-v/v-03-summary.md DELETED Viewed

@@ -1,104 +0,0 @@
----
-name: 'v-03-summary'
-description: 'Display complete validation report and offer next steps'
-validationReport: '{bmb_creations_output_folder}/validation-report-{agent-name}.md'
-advancedElicitationTask: '{project-root}/_byan/core/workflows/advanced-elicitation/workflow.xml'
-partyModeWorkflow: '{project-root}/_byan/core/workflows/party-mode/workflow.md'
----
-# Validate Step 3: Validation Summary
-## STEP GOAL:
-Display the complete validation report to the user and offer options for fixing issues or improving the agent.
-## MANDATORY EXECUTION RULES:
-- 📖 CRITICAL: Read the complete step file before taking any action
-- 🔄 CRITICAL: Read validationReport to display findings
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-### Step-Specific Rules:
-- 🎯 Display complete validation report clearly
-- 📊 Offer options for fixing issues
-- 💬 Present next step choices
-## EXECUTION PROTOCOLS:
-- 🎯 Read validation report to collect all findings
-- 📊 Display organized summary
-- 💾 Allow user to decide next steps
-## MANDATORY SEQUENCE
-**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
-### 1. Load Validation Report
-Read `{validationReport}` to collect all validation findings.
-### 2. Display Complete Report
-```markdown
-## Validation Complete: {agent-name}
-### Overall Status
-{Summary table: Metadata | Persona | Menu | Structure | Sidecar}
-### Detailed Findings
-{Display all sections from the validation report}
-```
-### 3. Present Next Steps
-"What would you like to do?
-**[E]dit Agent** - Launch edit workflow to fix issues or make improvements
-**[F]ix in Place** - Confirm which fixes you would like right now and we can fix without loading the full agent edit workflow
-**[S]ave Report** - Save this validation report and exit
-**[R]etry** - Run validation again (if you've made external changes)"
-### 4. Present MENU OPTIONS
-Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [E] Edit Agent [S] Save & Exit [R] Retry Validation"
-#### Menu Handling Logic:
-- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
-- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
-- IF E: Inform user they can launch edit workflow with the same agent file, then redisplay menu
-- IF F; Attempt to make users desired fixes without loading the full edit workflow
-- IF S: Save final report to {validationReport} and end workflow
-- IF R: Restart validation from step v-01
-- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#4-present-menu-options)
-#### EXECUTION RULES:
-- ALWAYS halt and wait for user input after presenting menu
-- User can chat or ask questions - always respond and then end with display again of the menu options
-## CRITICAL STEP COMPLETION NOTE
-The validation workflow is complete when user selects [S] to save the report, or [E] to proceed to edit workflow.
----
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-### ✅ SUCCESS:
-- Complete validation report displayed
-- All findings clearly organized
-- User offered clear next steps
-### ❌ SYSTEM FAILURE:
-- Findings not displayed to user
-- No clear next steps offered
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/bmb/workflows/module/steps-v/step-04-agent-specs.md DELETED Viewed

@@ -1,152 +0,0 @@
----
-name: 'step-04-agent-specs'
-description: 'Validate agent specifications and built agents'
-nextStepFile: './step-05-workflow-specs.md'
-agentSpecTemplate: '../../templates/agent-spec-template.md'
-agentArchitectureFile: '../../data/agent-architecture.md'
-agentValidationWorkflow: '{project-root}/_byan/bmb/workflows/agent/steps-v/step-01-validate.md'
-validationReportOutput: '{validation_report_output}'
-targetPath: '{validation_target_path}'
----
-# Step 4: Agent Specs Validation
-## STEP GOAL:
-Validate agent specifications and/or built agents, distinguishing between placeholder specs and fully implemented agents.
-## MANDATORY EXECUTION RULES:
-### Universal Rules:
-- 📖 CRITICAL: Read the complete step file before taking any action
-- ✅ Speak in `{communication_language}`
-### Role Reinforcement:
-- ✅ You are the **Quality Assurance** — dual-mode checking
-- ✅ Specs are expected, built agents are great
-- ✅ Track status of each agent
----
-## MANDATORY SEQUENCE
-### 1. Load Agent Files
-Find all agent files in `{targetPath}/agents/`:
-- `.spec.md` files (placeholder specs)
-- `.agent.yaml` files (built agents)
-### 2. Categorize Agents
-For each agent found, determine status:
-**Built Agents (.agent.yaml):**
-- Full implementation with complete persona, menu YAML
-- Can be validated in-depth via agent validation workflow
-**Spec Agents (.spec.md):**
-- High-level placeholder/blueprint
-- Awaiting creation via agent-builder workflow
-Track counts:
-- Total agents: {count}
-- Built agents: {count}
-- Spec agents: {count}
-### 3. Validate Spec Agents (.spec.md)
-For each spec agent, check:
-**Required Sections:**
-- [ ] Agent metadata (id, name, title, icon, module)
-- [ ] Role defined
-- [ ] Identity or communication style
-- [ ] Menu triggers documented
-- [ ] hasSidecar decision documented
-**Menu Triggers:**
-- [ ] At least one trigger per agent
-- [ ] Trigger → workflow mapping clear
-- [ ] No duplicate triggers (warn if found)
-**hasSidecar Documentation:**
-- [ ] Decision documented (true or false)
-- [ ] Rationale if true (why memory needed)
-**Placeholder Note:** These are specs awaiting agent-builder.
-### 4. Validate Built Agents (.agent.yaml)
-For each built agent, check:
-**Frontmatter Completeness:**
-- [ ] agent.metadata exists
-- [ ] agent.persona exists
-- [ ] agent.menu exists
-**YAML Structure:**
-- [ ] Valid YAML syntax
-- [ ] Required fields present
-**Status:** These are complete implementations and can be validated in detail via sub-process.
-### 5. Record Results
-Append to `{validationReportOutput}`:
-```markdown
-## Agent Specs Validation
-**Status:** {PASS/FAIL/WARNINGS}
-**Agent Summary:**
-- Total Agents: {count}
-- Built Agents: {count} {list}
-- Spec Agents: {count} {list}
-**Built Agents:**
-{for each built agent}
-- **{name}**: {status} - Ready for detailed validation via agent workflow
-**Spec Agents:**
-{for each spec agent}
-- **{name}**: {status} - Placeholder awaiting agent-builder
-**Issues Found:**
-{list any issues}
-**Recommendations:**
-{if specs exist}
-- Use `bmad:bmb:agents:agent-builder` to create {spec agent names}
-- After building agents, re-run validation to verify compliance
-{endif}
-```
-### 6. Note Sub-Process Opportunity
-**IF built agents exist:**
-"**The following built agents can be validated in detail:**"
-{list built agents}
-"**After this validation completes, I can spawn sub-processes to run the agent validation workflow on each built agent for deeper compliance checking.**"
-### 7. Auto-Proceed
-"**✓ Agent specs check complete.**"
-Proceeding to next validation...
-Load `{nextStepFile}`
----
-## Success Metrics
-✅ All agent files checked
-✅ Status tracked (spec vs built)
-✅ hasSidecar decisions validated
-✅ Recommendations for specs documented
-✅ Sub-process opportunity noted

package/install/templates/_byan/bmb/workflows/module/steps-v/step-05-workflow-specs.md DELETED Viewed

@@ -1,152 +0,0 @@
----
-name: 'step-05-workflow-specs'
-description: 'Validate workflow specifications and built workflows'
-nextStepFile: './step-06-documentation.md'
-workflowSpecTemplate: '../../templates/workflow-spec-template.md'
-workflowValidationWorkflow: '{project-root}/_byan/bmb/workflows/workflow/steps-v/step-01-validate.md'
-validationReportOutput: '{validation_report_output}'
-targetPath: '{validation_target_path}'
----
-# Step 5: Workflow Specs Validation
-## STEP GOAL:
-Validate workflow specifications and/or built workflows, distinguishing between placeholder specs and fully implemented workflows.
-## MANDATORY EXECUTION RULES:
-### Universal Rules:
-- 📖 CRITICAL: Read the complete step file before taking any action
-- ✅ Speak in `{communication_language}`
-### Role Reinforcement:
-- ✅ You are the **Quality Assurance** — dual-mode checking
-- ✅ Specs are expected, built workflows are great
-- ✅ Track status of each workflow
----
-## MANDATORY SEQUENCE
-### 1. Load Workflow Files
-Find all workflow files in `{targetPath}/workflows/`:
-- `.spec.md` files (placeholder specs)
-- `workflow.md` files (built workflows)
-### 2. Categorize Workflows
-For each workflow found, determine status:
-**Built Workflows (workflow.md with steps/ folder):**
-- Full implementation with step files, data, templates
-- Can be validated in-depth via workflow validation workflow
-**Spec Workflows (.spec.md):**
-- High-level placeholder/blueprint
-- Awaiting creation via workflow-builder workflow
-Track counts:
-- Total workflows: {count}
-- Built workflows: {count}
-- Spec workflows: {count}
-### 3. Validate Spec Workflows (.spec.md)
-For each spec workflow, check:
-**Required Sections:**
-- [ ] Workflow goal defined
-- [ ] Description present
-- [ ] Workflow type indicated
-- [ ] Step list or outline present
-- [ ] Agent association clear
-**Inputs/Outputs:**
-- [ ] Input requirements documented
-- [ ] Output format specified
-**Agent Integration:**
-- [ ] Primary agent identified
-- [ ] Multi-agent collaboration noted (if applicable)
-**Placeholder Note:** These are specs awaiting workflow-builder.
-### 4. Validate Built Workflows (workflow.md)
-For each built workflow, check:
-**Workflow Structure:**
-- [ ] workflow.md exists with proper frontmatter
-- [ ] steps/ folder exists (steps-c/, steps-e/, steps-v/ as appropriate)
-- [ ] Step files follow naming conventions
-**Step File Compliance:**
-- [ ] Each step has proper frontmatter
-- [ ] Step files within size limits
-- [ ] Menu handling follows standards
-**Status:** These are complete implementations and can be validated in detail via sub-process.
-### 5. Record Results
-Append to `{validationReportOutput}`:
-```markdown
-## Workflow Specs Validation
-**Status:** {PASS/FAIL/WARNINGS}
-**Workflow Summary:**
-- Total Workflows: {count}
-- Built Workflows: {count} {list}
-- Spec Workflows: {count} {list}
-**Built Workflows:**
-{for each built workflow}
-- **{name}**: {status} - Ready for detailed validation via workflow workflow
-**Spec Workflows:**
-{for each spec workflow}
-- **{name}**: {status} - Placeholder awaiting workflow-builder
-**Issues Found:**
-{list any issues}
-**Recommendations:**
-{if specs exist}
-- Use `bmad:bmb:workflows:workflow` or `/workflow` to create {spec workflow names}
-- After building workflows, re-run validation to verify compliance
-{endif}
-```
-### 6. Note Sub-Process Opportunity
-**IF built workflows exist:**
-"**The following built workflows can be validated in detail:**"
-{list built workflows}
-"**After this validation completes, I can spawn sub-processes to run the workflow validation workflow on each built workflow for deeper compliance checking.**"
-### 7. Auto-Proceed
-"**✓ Workflow specs check complete.**"
-Proceeding to next validation...
-Load `{nextStepFile}`
----
-## Success Metrics
-✅ All workflow files checked
-✅ Status tracked (spec vs built)
-✅ Agent associations validated
-✅ Recommendations for specs documented
-✅ Sub-process opportunity noted