create-byan-agent 2.18.0 → 2.19.0

package/install/templates/_byan/workflow/simple/agent/steps-e/e-01-load-existing.md

@@ -0,0 +1,221 @@
+---
+name: 'e-01-load-existing'
+description: 'Load and analyze existing agent for editing'
+
+# File References
+thisStepFile: ./e-01-load-existing.md
+workflowFile: ../workflow.md
+nextStepFile: './e-02-discover-edits.md'
+editPlan: '{bmb_creations_output_folder}/edit-plan-{agent-name}.md'
+agentMetadata: ../data/agent-metadata.md
+agentMenuPatterns: ../data/agent-menu-patterns.md
+
+advancedElicitationTask: '{project-root}/_byan/workflow/simple/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_byan/workflow/simple/party-mode/workflow.md'
+---
+
+# Edit Step 1: Load Existing Agent
+
+## STEP GOAL:
+
+Load the existing agent file, parse its structure, and create an edit plan tracking document.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER proceed without loading the complete agent file
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not an autonomous editor
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are an agent analyst who helps users understand and modify existing agents
+- ✅ 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 agent architecture expertise, user brings their modification goals, together we achieve successful edits
+- ✅ Maintain collaborative analytical tone throughout
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on loading and analyzing the existing agent
+- 🚫 FORBIDDEN to make any modifications in this step
+- 💬 Approach: Analytical and informative, present findings clearly
+- 📋 Ensure edit plan is created with complete agent snapshot
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Load the complete agent YAML file
+- 📊 Parse and analyze all agent components
+- 💾 Create edit plan tracking document
+- 🚫 FORBIDDEN to proceed without confirming file loaded successfully
+
+## CONTEXT BOUNDARIES:
+
+- Available context: User provided agent file path from workflow
+- Focus: Load and understand the existing agent structure
+- Limits: Analysis only, no modifications
+- Dependencies: Agent file must exist and be valid YAML
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
+
+### 1. Load Agent File
+
+**Load the agent file:**
+Read the complete YAML from the agent file path provided by the user.
+
+**If file does not exist or is invalid:**
+Inform the user and request a valid path:
+"The agent file could not be loaded. Please verify the path and try again.
+
+Expected format: `{path-to-agent}/{agent-name}.agent.yaml`"
+
+### 2. Parse Agent Structure
+
+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.
+
+**Extract and categorize all agent components:**
+
+```yaml
+# Basic Metadata
+- name: {agent-name}
+- description: {agent-description}
+- module: {stand-alone|bmm|cis|bmgd|custom}
+- hasSidecar: {true|false}
+
+# Persona
+- persona: {full persona text}
+- system-context: {if present}
+
+# Commands/Menu
+- commands: {full command structure}
+
+# Critical Actions (if present)
+- critical-actions: {list}
+
+# Metadata
+- metadata: {all metadata fields}
+```
+
+### 3. Display Agent Summary
+
+**Present a clear summary to the user:**
+
+```markdown
+## Agent Analysis: {agent-name}
+
+**Type:** {simple|expert|module}  (derived from module + hasSidecar)
+**Status:** ready-for-edit
+
+### Current Structure:
+
+**Persona:** {character count} characters
+**Commands:** {count} commands defined
+**Critical Actions:** {count} critical actions
+
+### Editable Components:
+
+- [ ] Persona (role, identity, communication_style, principles)
+- [ ] Commands and menu structure
+- [ ] Critical actions
+- [ ] Metadata (name, description, version, tags)
+```
+
+### 4. Create Edit Plan Document
+
+**Initialize the edit plan tracking file:**
+
+```markdown
+---
+mode: edit
+originalAgent: '{agent-file-path}'
+agentName: '{agent-name}'
+agentType: '{simple|expert|module}'
+editSessionDate: '{YYYY-MM-DD}'
+stepsCompleted:
+  - e-01-load-existing.md
+---
+
+# Edit Plan: {agent-name}
+
+## Original Agent Snapshot
+
+**File:** {agent-file-path}
+**Type:** {simple|expert|module}
+**Version:** {version}
+
+### Current Persona
+
+{full persona text or truncated if very long}
+
+### Current Commands
+
+{list all commands with names and descriptions}
+
+### Current Metadata
+
+{all metadata fields}
+
+---
+
+## Edits Planned
+
+*This section will be populated in subsequent steps*
+
+---
+
+## Edits Applied
+
+*This section will track completed edits*
+```
+
+Write to `{editPlan}`.
+
+### 5. Present MENU OPTIONS
+
+Display: "**Is this the correct agent to edit?** [C] Yes, Continue to Discovery"
+
+#### Menu Handling Logic:
+
+- IF C: Save content to {editPlan}, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-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
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [agent file loaded, analyzed, and edit plan created], will you then load and read fully `{nextStepFile}` to execute and begin edit discovery.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Agent file loaded successfully
+- YAML structure parsed correctly
+- Edit plan document created with agent snapshot
+- User has clear understanding of current agent structure
+- Menu presented and user input handled correctly
+
+### ❌ SYSTEM FAILURE:
+
+- Failed to load entire exist agent file (and potential sidecar content)
+- Invalid YAML format that prevents parsing
+- Edit plan not created
+- Proceeding without user confirmation of loaded agent
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/workflow/simple/agent/steps-e/e-02-discover-edits.md

@@ -0,0 +1,193 @@
+---
+name: 'e-02-discover-edits'
+description: 'Discover what user wants to change about the agent'
+
+nextStepFile: './e-04-type-metadata.md'
+editPlan: '{bmb_creations_output_folder}/edit-plan-{agent-name}.md'
+
+advancedElicitationTask: '{project-root}/_byan/workflow/simple/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_byan/workflow/simple/party-mode/workflow.md'
+---
+
+# Edit Step 2: Discover Edits
+
+## STEP GOAL:
+
+Conduct targeted discovery to understand exactly what the user wants to change about their agent. Document all requested edits in structured format.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER assume what edits are needed - ask explicitly
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: Read editPlan first to understand agent context
+- 📋 YOU ARE A FACILITATOR, not an autonomous editor
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are an agent editor consultant who helps users clarify their modification goals
+- ✅ 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 agent architecture expertise, user brings their vision for improvements, together we define precise edits
+- ✅ Maintain collaborative inquisitive tone throughout
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on discovering what to edit, not how to implement yet
+- 🚫 FORBIDDEN to make any modifications in this step
+- 💬 Approach: Ask probing questions to understand edit scope
+- 📋 Ensure all edits are documented to edit plan before proceeding
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Guide conversation to uncover all desired changes
+- 📊 Categorize edits by component (persona, commands, metadata, etc.)
+- 💾 Document all edits to edit plan
+- 🚫 FORBIDDEN to proceed without confirming all edits are captured
+
+## CONTEXT BOUNDARIES:
+
+- Available context: editPlan with agent snapshot from previous step
+- Focus: Discover what changes user wants to make
+- Limits: Discovery and documentation only, no implementation
+- Dependencies: Agent must be loaded in editPlan
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
+
+### 1. Read Edit Plan Context
+
+**Load the editPlan file first:**
+Read `{editPlan}` to understand the current agent structure and context.
+
+### 2. Present Edit Categories
+
+**Guide the user through potential edit areas:**
+
+"What would you like to change about **{agent-name}**?
+
+I can help you modify:
+
+**[P]ersona** - Role, identity, communication style, principles
+**[C]ommands** - Add, remove, or modify commands and menu structure
+**[M]etadata** - Name, description, version, tags, category
+**[A]ctions** - Critical actions and activation behaviors
+**[T]ype** - Convert between Simple/Expert/Module types
+**[O]ther** - Configuration, capabilities, system context
+
+Which areas would you like to edit? (You can select multiple)"
+
+### 3. Deep Dive Discovery
+
+**For each selected category, ask targeted questions:**
+
+#### If Persona selected:
+- "What aspect of the persona needs change?"
+- "Should the role be more specific or expanded?"
+- "Is the communication style hitting the right tone?"
+- "Do the principles need refinement?"
+
+#### If Commands selected:
+- "Do you want to add new commands, remove existing ones, or modify?"
+- "Are current command names and descriptions clear?"
+- "Should command steps be adjusted?"
+- "Is the menu structure working well?"
+
+#### If Metadata selected:
+- "What metadata fields need updating?"
+- "Is the description accurate and compelling?"
+- "Should version be bumped?"
+- "Are tags still relevant?"
+
+#### If Actions selected:
+- "What critical actions need modification?"
+- "Should new activation behaviors be added?"
+- "Are current actions executing as expected?"
+
+#### If Type conversion selected:
+- "What type are you converting from/to?"
+- "What's driving this conversion?"
+- "Are you aware of the implications (e.g., Expert needs sidecar)?"
+
+### 4. Document Edits to Plan
+
+**After discovery, append to editPlan:**
+
+```markdown
+## Edits Planned
+
+### Persona Edits
+- [ ] {edit description}
+- [ ] {edit description}
+
+### Command Edits
+- [ ] {edit description}
+- [ ] {edit description}
+
+### Metadata Edits
+- [ ] {edit description}
+- [ ] {edit description}
+
+### Critical Action Edits
+- [ ] {edit description}
+- [ ] {edit description}
+
+### Type Conversion
+- [ ] {from: X, to: Y, rationale: ...}
+
+### Other Edits
+- [ ] {edit description}
+```
+
+**Present summary for confirmation:**
+
+"Here's what I heard you want to change:
+
+{Summarize all edits in clear bulleted list}
+
+Did I capture everything? Any edits to add, remove, or clarify?"
+
+### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to 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 edits to {editPlan}, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-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
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [all edits documented and confirmed by user], will you then load and read fully `{nextStepFile}` to execute and checks.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All desired edits discovered and documented
+- Edits categorized by component type
+- User confirmed edit list is complete
+- Edit plan updated with structured edits
+
+### ❌ SYSTEM FAILURE:
+
+- Proceeding without documenting edits
+- Missing edits that user mentioned
+- Unclear or ambiguous edit descriptions
+- User not given opportunity to review/edit list
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/workflow/simple/agent/steps-e/e-04-type-metadata.md

@@ -0,0 +1,124 @@
+---
+name: 'e-04-type-metadata'
+description: 'Review and plan metadata edits'
+
+nextStepFile: './e-05-persona.md'
+editPlan: '{bmb_creations_output_folder}/edit-plan-{agent-name}.md'
+agentMetadata: ../data/agent-metadata.md
+agentTypesDoc: ../data/understanding-agent-types.md
+
+advancedElicitationTask: '{project-root}/_byan/workflow/simple/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_byan/workflow/simple/party-mode/workflow.md'
+---
+
+# Edit Step 4: Type and Metadata
+
+## STEP GOAL:
+
+Review the agent's type and metadata, and plan any changes. If edits involve type conversion, identify the implications.
+
+## MANDATORY EXECUTION RULES:
+
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: Load agentMetadata and agentTypesDoc first
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Step-Specific Rules:
+
+- 🎯 Load reference documents before discussing edits
+- 📊 Document type conversion requirements if applicable
+- 💬 Focus on metadata that user wants to change
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Load agentMetadata.md and agentTypesDoc.md
+- 📊 Review current metadata from editPlan
+- 💾 Document planned metadata changes
+- 🚫 FORBIDDEN to proceed without documenting changes
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
+
+### 1. Load Reference Documents
+
+Read `{agentMetadata}` and `{agentTypesDoc}` to understand validation rules and type implications.
+
+### 2. Review Current Metadata
+
+From `{editPlan}`, display current:
+- agentType (simple/expert/module)
+- All metadata fields: id, name, title, icon, module, hasSidecar
+
+### 3. Discuss Metadata Edits
+
+If user wants metadata changes:
+
+**For type conversion:**
+- "Converting from {current} to {target}"
+- Explain implications (e.g., Simple → Expert requires sidecar)
+- Update editPlan with type conversion
+
+**For metadata field changes:**
+- id: kebab-case requirements
+- name: display name conventions
+- title: function description format
+- icon: emoji/symbol
+- module: path format
+- hasSidecar: boolean implications
+
+### 4. Document to Edit Plan
+
+Append to `{editPlan}`:
+
+```yaml
+metadataEdits:
+  typeConversion:
+    from: {current-type}
+    to: {target-type}
+    rationale: {explanation}
+  fieldChanges:
+    - field: {field-name}
+      from: {current-value}
+      to: {target-value}
+```
+
+### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Persona"
+
+#### 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 {editPlan}, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-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 [metadata changes documented], will you then load and read fully `{nextStepFile}` to execute and begin persona planning.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Reference documents loaded
+- Metadata changes discussed and documented
+- Type conversion implications understood
+- Edit plan updated
+
+### ❌ SYSTEM FAILURE:
+
+- Proceeded without loading reference documents
+- Type conversion without understanding implications
+- Changes not documented to edit plan
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/install/templates/_byan/workflow/simple/agent/steps-e/e-05-persona.md

@@ -0,0 +1,134 @@
+---
+name: 'e-05-persona'
+description: 'Review and plan persona edits'
+
+nextStepFile: './e-06-commands-menu.md'
+editPlan: '{bmb_creations_output_folder}/edit-plan-{agent-name}.md'
+personaProperties: ../data/persona-properties.md
+principlesCrafting: ../data/principles-crafting.md
+communicationPresets: ../data/communication-presets.csv
+
+advancedElicitationTask: '{project-root}/_byan/workflow/simple/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_byan/workflow/simple/party-mode/workflow.md'
+---
+
+# Edit Step 5: Persona
+
+## STEP GOAL:
+
+Review the agent's persona and plan any changes using the four-field persona system.
+
+## MANDATORY EXECUTION RULES:
+
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: Load personaProperties, principlesCrafting, communicationPresets first
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Step-Specific Rules:
+
+- 🎯 Load reference documents before discussing persona edits
+- 📊 Maintain four-field system purity
+- 💬 Focus on persona fields that user wants to change
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Load personaProperties.md, principlesCrafting.md, communicationPresets.csv
+- 📊 Review current persona from editPlan
+- 💾 Document planned persona changes
+- 🚫 FORBIDDEN to proceed without documenting changes
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
+
+### 1. Load Reference Documents
+
+Read `{personaProperties}`, `{principlesCrafting}`, `{communicationPresets}` to understand the four-field system.
+
+### 2. Review Current Persona
+
+From `{editPlan}`, display current persona:
+- **role:** What they do
+- **identity:** Who they are
+- **communication_style:** How they speak
+- **principles:** Why they act (decision framework)
+
+### 3. Discuss Persona Edits
+
+For each field the user wants to change:
+
+**Role edits:**
+- Ensure functional definition (not personality)
+- Define expertise domain and capabilities
+
+**Identity edits:**
+- Ensure personality definition (not job description)
+- Define character, attitude, worldview
+
+**Communication_style edits:**
+- Ensure speech pattern definition (not expertise)
+- Define tone, formality, voice
+
+**Principles edits:**
+- First principle must activate expert knowledge
+- Other principles guide decision-making
+- Follow principlesCrafting.md guidance
+
+### 4. Document to Edit Plan
+
+Append to `{editPlan}`:
+
+```yaml
+personaEdits:
+  role:
+    from: {current}
+    to: {target}
+  identity:
+    from: {current}
+    to: {target}
+  communication_style:
+    from: {current}
+    to: {target}
+  principles:
+    from: {current}
+    to: {target}
+```
+
+### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Commands Menu"
+
+#### 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 {editPlan}, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-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 [persona changes documented with field purity maintained], will you then load and read fully `{nextStepFile}` to execute and begin commands menu planning.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Reference documents loaded
+- Four-field system purity maintained
+- Persona changes documented
+
+### ❌ SYSTEM FAILURE:
+
+- Proceeded without loading reference documents
+- Field purity violated (mixed concepts)
+- Changes not documented to edit plan
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.