ma-agents 2.15.0 → 2.16.1

package/.agent/workflows/bmad-help.md

@@ -0,0 +1,10 @@
+---
+name: 'help'
+description: 'Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now'
+---
+
+# help
+
+Read the entire task file at: {project-root}/_bmad/core/tasks/help.md
+
+Follow all instructions in the task file exactly as written.

package/.agent/workflows/bmad-index-docs.md

@@ -0,0 +1,10 @@
+---
+name: 'index-docs'
+description: 'Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder'
+---
+
+# index-docs
+
+Read the entire task file at: {project-root}/_bmad/core/tasks/index-docs.xml
+
+Follow all instructions in the task file exactly as written.

package/.agent/workflows/bmad-party-mode.md

@@ -0,0 +1,6 @@
+---
+name: 'party-mode'
+description: 'Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations. Use when user requests party mode.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/core/workflows/party-mode/workflow.md, READ its entire contents and follow its directions exactly!

package/.agent/workflows/bmad-review-adversarial-general.md

@@ -0,0 +1,10 @@
+---
+name: 'review-adversarial-general'
+description: 'Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something'
+---
+
+# review-adversarial-general
+
+Read the entire task file at: {project-root}/_bmad/core/tasks/review-adversarial-general.xml
+
+Follow all instructions in the task file exactly as written.

package/.agent/workflows/bmad-review-edge-case-hunter.md

@@ -0,0 +1,10 @@
+---
+name: 'review-edge-case-hunter'
+description: 'Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven.'
+---
+
+# review-edge-case-hunter
+
+Read the entire task file at: {project-root}/_bmad/core/tasks/review-edge-case-hunter.xml
+
+Follow all instructions in the task file exactly as written.

package/.agent/workflows/bmad-shard-doc.md

@@ -0,0 +1,10 @@
+---
+name: 'shard-doc'
+description: 'Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document'
+---
+
+# shard-doc
+
+Read the entire task file at: {project-root}/_bmad/core/tasks/shard-doc.xml
+
+Follow all instructions in the task file exactly as written.

package/README.md

@@ -2,17 +2,23 @@
 
 A universal NPX tool to install AI coding agent skills. Write skills once, install them across Claude Code, Gemini, Copilot, Cline, Cursor, and Kilocode.
 
-## Quick Start
+## Installation & Usage
 
+`ma-agents` is designed to be run via `npx` in the root of your project.
+
+### 1. Interactive Wizard (Recommended)
+The wizard is the easiest way to set up or update your environment.
 ```bash
-# Interactive wizard (Install All / Custom Select / Update / Uninstall)
 npx ma-agents
+```
 
-# Direct install
-npx ma-agents install code-review claude-code
+### 2. Direct Command Line
+```bash
+# Install specific skills to specific agents
+npx ma-agents install code-review claude-code copilot
 
-# Install a skill to multiple agents at once
-npx ma-agents install code-review claude-code copilot cline
+# Global installation (user-level)
+npx ma-agents install code-review claude-code --global
 ```
 
 ## How It Works
@@ -43,18 +49,19 @@ skills/code-review/
 
 | Agent | Project Path | Template | Instruction File |
 |-------|-------------|----------|------------------|
-| Claude Code | `.claude/skills/` | `claude-code` | `CLAUDE.md` |
-| Google Gemini | `.gemini/skills/` | `generic` | - |
-| GitHub Copilot | `.github/copilot/skills/` | `generic` | - |
-| Cursor | `.cursor/skills/` | `generic` | - |
-| Cline | `.cline/skills/` | `cline` | `.clinerules` |
-| SRE Agent (Alex) | `.sre/skills/` | `generic` | - |
-| DevOps Agent (Amit) | `.devops/skills/` | `generic` | - |
-| Cyber Analyst (Yael) | `.cyber/skills/` | `generic` | - |
-| Antigravity | `.antigravity/skills/` | `generic` | - |
-| Kilocode | `.kilocode/skills/` | `generic` | - |
-
-## Available Skills (22)
+| Claude Code | `.claude/skills/` | `claude-code` | `.claude/CLAUDE.md` |
+| Google Gemini | `.gemini/skills/` | `generic` | `.gemini/gemini.md` |
+| GitHub Copilot | `.github/copilot/skills/` | `generic` | `.github/copilot/copilot.md` |
+| Cursor | `.cursor/skills/` | `generic` | `.cursor/cursor.md` |
+| Kilocode | `.kilocode/skills/` | `generic` | `.kilocode/kilocode.md` |
+| Cline | `.cline/skills/` | `cline` | `.cline/clinerules.md` |
+| SRE Agent (Alex) | `_bmad/skills/` | `generic` | `_bmad/bmm/agents/sre.md` |
+| DevOps Agent (Amit) | `_bmad/skills/` | `generic` | `_bmad/bmm/agents/devops.md` |
+| Cyber Analyst (Yael) | `_bmad/skills/` | `generic` | `_bmad/bmm/agents/cyber.md` |
+| Joseph (MIL-STD-498) | `_bmad/skills/` | `generic` | `_bmad/bmm/agents/mil498.md` |
+| Antigravity | `_bmad/skills/` | `generic` | `_bmad/bmm/agents/antigravity.md` |
+
+## Available Skills (25)
 
 | Skill ID | Domain | Description |
 | :--- | :--- | :--- |
@@ -117,13 +124,14 @@ npx ma-agents agents                       # List supported agents
 npx ma-agents uninstall <skill> <agents>   # Direct uninstall
 ```
 
-### The Interactive Wizard
-The easiest way to manage your skills is to simply run `npx ma-agents`. The wizard will guide you through:
-- **Install All**: One-click setup for the entire 22-skill suite.
-- **Custom Select**: Granularly choose specific skills and agents.
-- **Update**: Add or remove skills from an existing installation.
-- **Clean Reinstall**: Wipe the slate and start fresh.
-- **Uninstall All**: Remove all ma-agents artifacts from the project.
+### The Update Process
+Running `ma-agents` on a project where skills are already installed triggers the **Update Flow**:
+1. **Detection**: Recognizes existing `.ma-agents.json` manifest.
+2. **Selection**: Allows you to add new skills or remove existing ones.
+3. **Synchronization**: 
+   - Re-injects the latest instructions into `CLAUDE.md`, `.clinerules`, etc.
+   - Regenerates the `MANIFEST.yaml` to reflect the current skill set.
+   - Updates BMAD-METHOD personas and workflows to the latest versions if detected.
 
 ### BMAD-METHOD Integration
 `ma-agents` features first-class integration with [BMAD-METHOD](https://docs.bmad-method.org/) to provide advanced orchestration and specialized personas.
@@ -147,6 +155,10 @@ The easiest way to manage your skills is to simply run `npx ma-agents`. The wiza
    - **Focus**: Cyber immunity, security auditing, and vulnerability management.
    - **Capabilities**: Immunity estimation (scoring), Vault secret management, and PKI automation.
    - **Integration**: Orchestrates ma-agents security skills for deep scans.
+4. **Joseph (MIL-STD-498)**:
+   - **Focus**: Technical standards compliance and military document generation.
+   - **Capabilities**: Document Data Descriptions (DIDs), requirements traceability, and complex specification writing.
+   - **Workflows**: SRS, SSS, and SSDD generation with strict structural validation.
 
 #### Operational Workflows
 The integration includes a suite of specialized playbooks:
@@ -326,9 +338,13 @@ ma-agents/
 │   └── cli.js                  # CLI entry point (wizard + commands)
 ├── lib/
 │   ├── agents.js               # Agent configurations and paths
-│   └── installer.js            # Skill discovery, frontmatter injection, installation
+│   ├── installer.js            # Skill discovery and installation logic
+│   ├── bmad.js                 # BMAD-METHOD integration and injection logic
+│   ├── bmad-customizations/    # BMAD persona templates (.md) and YAML configs
+│   ├── bmad-workflows/         # Specialized BMAD playbooks (SRE, Cyber, etc.)
+│   └── mil498-templates/       # MIL-STD-498 DID library (SRS, SSS, SSDD, etc.)
 ├── skills/
-│   ├── code-review/            # 22 bundled skills across 5 domains
+│   ├── code-review/            # 25 bundled skills across 5 domains
 │   ├── commit-message/
 │   ├── create-hardened-docker-skill/
 │   ├── git-workflow-skill/

package/bin/cli.js

@@ -52,8 +52,8 @@ function showAgents() {
   const agents = listAgents();
   console.log(chalk.bold('\n Supported Agents:\n'));
 
-  const ideAgents = agents.filter(a => !['bmm-sre', 'bmm-devops', 'bmm-cyber', 'bmm-mil498'].includes(a.id));
-  const bmadAgents = agents.filter(a => ['bmm-sre', 'bmm-devops', 'bmm-cyber', 'bmm-mil498'].includes(a.id));
+  const ideAgents = agents.filter(a => a.category !== 'bmad');
+  const bmadAgents = agents.filter(a => a.category === 'bmad');
 
   console.log(chalk.bold.yellow('  AI Coding Assistants:'));
   ideAgents.forEach(agent => {
@@ -235,8 +235,8 @@ async function installWizard(preselectedSkill, preselectedAgents, customPath, fo
 
   // Step 2: Select agents
   if (selectedAgentIds.length === 0 || isUpdate) {
-    const ideAgents = agents.filter(a => !['bmm-sre', 'bmm-devops', 'bmm-cyber', 'bmm-mil498'].includes(a.id));
-    const bmadAgents = agents.filter(a => ['bmm-sre', 'bmm-devops', 'bmm-cyber', 'bmm-mil498'].includes(a.id));
+    const ideAgents = agents.filter(a => a.category !== 'bmad');
+    const bmadAgents = agents.filter(a => a.category === 'bmad');
 
     // 2.1 Coding Assistants
     const { ideChosen } = await prompts({
@@ -320,7 +320,7 @@ async function installWizard(preselectedSkill, preselectedAgents, customPath, fo
         if (success) {
           console.log(chalk.green(' BMAD-METHOD installed successfully!'));
           console.log(chalk.cyan(' Applying ma-agents customizations...'));
-          await bmad.applyCustomizations();
+          await bmad.applyCustomizations(process.cwd(), ['bmm', 'bmb'], bmadTools, selectedAgentIds);
         }
       }
     } else {
@@ -338,7 +338,7 @@ async function installWizard(preselectedSkill, preselectedAgents, customPath, fo
         if (success) {
           console.log(chalk.green(' BMAD-METHOD updated successfully!'));
           console.log(chalk.cyan(' Re-applying ma-agents customizations...'));
-          await bmad.applyCustomizations();
+          await bmad.applyCustomizations(process.cwd(), ['bmm', 'bmb'], bmadTools, selectedAgentIds);
         }
       }
     }
@@ -366,17 +366,43 @@ async function installWizard(preselectedSkill, preselectedAgents, customPath, fo
 
   // Step 5: Execution
   if (isUpdate) {
-    // Identify removals
-    const currentlyInstalled = new Set();
-    existingStatus.forEach(entry => Object.keys(entry.skills).forEach(id => currentlyInstalled.add(id)));
+    // Build a map: skillId -> set of agent IDs that originally had it installed
+    const originalAgentsBySkill = new Map();
+    const originalAllAgentIds = new Set();
+    existingStatus.forEach(entry => {
+      originalAllAgentIds.add(entry.agent.id);
+      Object.keys(entry.skills).forEach(skillId => {
+        if (!originalAgentsBySkill.has(skillId)) {
+          originalAgentsBySkill.set(skillId, new Set());
+        }
+        originalAgentsBySkill.get(skillId).add(entry.agent.id);
+      });
+    });
 
     const finalSkills = new Set(selectedSkillIds);
-    const toRemove = [...currentlyInstalled].filter(id => !finalSkills.has(id));
+
+    // Skills to fully remove (deselected from skill list)
+    const toRemove = [...originalAgentsBySkill.keys()].filter(id => !finalSkills.has(id));
 
     if (toRemove.length > 0) {
       console.log(chalk.gray(`\n  Cleaning up ${toRemove.length} removed skills...`));
       for (const skillId of toRemove) {
-        await uninstallSkill(skillId, selectedAgentIds, installPath, 'project');
+        // Use the ORIGINAL agent IDs, not the new selection
+        const originalAgents = [...originalAgentsBySkill.get(skillId)];
+        await uninstallSkill(skillId, originalAgents, installPath, 'project');
+      }
+    }
+
+    // Also handle agents that were deselected: uninstall their skills
+    const deselectedAgents = [...originalAllAgentIds].filter(id => !selectedAgentIds.includes(id));
+
+    if (deselectedAgents.length > 0) {
+      console.log(chalk.gray(`\n  Removing skills from ${deselectedAgents.length} deselected agents...`));
+      for (const [skillId, agentSet] of originalAgentsBySkill) {
+        const agentsToRemoveFrom = deselectedAgents.filter(id => agentSet.has(id));
+        if (agentsToRemoveFrom.length > 0) {
+          await uninstallSkill(skillId, agentsToRemoveFrom, installPath, 'project');
+        }
       }
     }
   }

package/lib/agents.js

@@ -6,6 +6,7 @@ const path = require('path');
  * Each agent has:
  * - id: unique identifier
  * - name: display name
+ * - category: 'ide' for AI coding assistants, 'bmad' for BMAD-METHOD agents
  * - description: brief description
  * - getProjectPath: function that returns the project-level skills directory (relative to cwd)
  * - getGlobalPath: function that returns the global/user-level skills directory
@@ -18,6 +19,7 @@ const agents = [
     id: 'claude-code',
     name: 'Claude Code',
     version: '1.0.0',
+    category: 'ide',
     description: 'Anthropic Claude Code CLI',
     getProjectPath: () => path.join(process.cwd(), '.claude', 'skills'),
     getGlobalPath: () => {
@@ -38,6 +40,7 @@ const agents = [
     id: 'gemini',
     name: 'Google Gemini',
     version: '1.0.0',
+    category: 'ide',
     description: 'Google Gemini Code Assist',
     getProjectPath: () => path.join(process.cwd(), '.gemini', 'skills'),
     getGlobalPath: () => {
@@ -58,6 +61,7 @@ const agents = [
     id: 'copilot',
     name: 'GitHub Copilot',
     version: '1.0.0',
+    category: 'ide',
     description: 'GitHub Copilot Agent Mode',
     getProjectPath: () => path.join(process.cwd(), '.github', 'copilot', 'skills'),
     getGlobalPath: () => {
@@ -78,6 +82,7 @@ const agents = [
     id: 'kilocode',
     name: 'Kilocode',
     version: '1.0.0',
+    category: 'ide',
     description: 'Kilocode AI Assistant',
     getProjectPath: () => path.join(process.cwd(), '.kilocode', 'skills'),
     getGlobalPath: () => {
@@ -98,6 +103,7 @@ const agents = [
     id: 'cline',
     name: 'Cline',
     version: '1.0.0',
+    category: 'ide',
     description: 'Cline AI Assistant',
     getProjectPath: () => path.join(process.cwd(), '.cline', 'skills'),
     getGlobalPath: () => {
@@ -123,6 +129,7 @@ const agents = [
     id: 'cursor',
     name: 'Cursor',
     version: '1.0.0',
+    category: 'ide',
     description: 'Cursor AI Editor',
     getProjectPath: () => path.join(process.cwd(), '.cursor', 'skills'),
     getGlobalPath: () => {
@@ -143,8 +150,9 @@ const agents = [
     id: 'bmm-sre',
     name: 'SRE Agent',
     version: '1.0.0',
+    category: 'bmad',
     description: 'Specialized SRE Agent for BMAD-METHOD',
-    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills', 'sre'),
+    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills'),
     getGlobalPath: () => {
       const platform = os.platform();
       if (platform === 'win32') {
@@ -163,8 +171,9 @@ const agents = [
     id: 'antigravity',
     name: 'Antigravity',
     version: '1.0.0',
+    category: 'bmad',
     description: 'Google Deepmind Antigravity Agent',
-    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills', 'antigravity'),
+    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills'),
     getGlobalPath: () => {
       const platform = os.platform();
       if (platform === 'win32') {
@@ -183,8 +192,9 @@ const agents = [
     id: 'bmm-devops',
     name: 'DevOps Agent',
     version: '1.0.0',
+    category: 'bmad',
     description: 'Specialized DevOps Agent for BMAD-METHOD',
-    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills', 'devops'),
+    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills'),
     getGlobalPath: () => {
       const platform = os.platform();
       if (platform === 'win32') {
@@ -203,8 +213,9 @@ const agents = [
     id: 'bmm-cyber',
     name: 'Cyber Analyst',
     version: '1.0.0',
+    category: 'bmad',
     description: 'Specialized Cyber Security Analyst (Yael) for BMAD-METHOD',
-    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills', 'yael'),
+    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills'),
     getGlobalPath: () => {
       const platform = os.platform();
       if (platform === 'win32') {
@@ -223,8 +234,9 @@ const agents = [
     id: 'bmm-mil498',
     name: 'Joseph',
     version: '1.0.0',
+    category: 'bmad',
     description: 'MIL-STD-498 Documentation Expert',
-    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills', 'mil498'),
+    getProjectPath: () => path.join(process.cwd(), '_bmad', 'skills'),
     getGlobalPath: () => {
       const platform = os.platform();
       if (platform === 'win32') {
@@ -249,7 +261,12 @@ function getAllAgents() {
   return agents;
 }
 
+function getAgentsByCategory(category) {
+  return agents.filter(a => a.category === category);
+}
+
 module.exports = {
   getAgent,
-  getAllAgents
+  getAllAgents,
+  getAgentsByCategory
 };

package/lib/bmad-customizations/antigravity.customize.yaml

@@ -1,10 +1,18 @@
 # antigravity.customize.yaml
+agent:
+  metadata:
+    name: "Antigravity"
+
 persona:
-  name: "MA-Antigravity"
-  role: "Advanced Agentic AI Assistant (BMAD-METHOD)"
-  style: "Proactive, specialized in codebase maintenance and automation."
-principles:
-  - "Follow BMAD-METHOD architectural patterns"
-  - "Prioritize agentic safety and task completeness"
-  - "Use ma-agents skills to enhance capabilities"
-  - "Maintain project context via project-context.md"
+  role: "Powerful agentic AI coding assistant"
+  identity: "Designed by Google Deepmind for advanced agentic coding. Capable of pair programming, debugging, and system refactoring."
+  communication_style: "Helpful, proactive, and technically precise. Communicates in {communication_language}."
+  principles:
+    - "Prioritize user requirements and intent."
+    - "Maintain high standards of code quality and security."
+    - "Communicate progress clearly through task boundaries and artifacts."
+
+menu:
+  - trigger: bmad-help
+    workflow: "core/workflows/help.yaml"
+    description: "Get help with BMAD-METHOD"

package/lib/bmad-customizations/bmm-cyber.customize.yaml

@@ -1,42 +1,24 @@
 # cyber.customize.yaml
+agent:
+  metadata:
+    name: "Yael"
+
 persona:
-  name: "Yael"
-  role: "Cyber Security Analyst & Immunity Expert"
-  identity: "You are a specialized Cyber Security Analyst. Your mission is to estimate and improve the cyber immunity of systems. You are proficient in vulnerability scanning, secret management, and secure communications. You assist {user_name}."
-  style: "Vigilant, precise, and highly technical. You communicate in {communication_language}."
+  role: "Cyber Security Analyst"
+  identity: "Expert in vulnerability assessment, threat modeling, and system hardening with deep knowledge of security standards (OWASP, CIS)."
+  communication_style: "Analytical, precise, and risk-focused. Uses professional security terminology."
   principles:
-    - "Security is not a state, but a process."
-    - "Zero Trust: Verify everything, trust no one."
-    - "Defense in Depth: Layered security controls."
-    - "Least Privilege: Grant only the minimum necessary access."
-    - "Shift Left: Integrate security early in the lifecycle."
-
-critical_actions:
-  - "Immediately load {project-root}/_bmad/bmm/config.yaml for session context."
-  - "Run an initial security audit of the project structure and configuration."
-  - "Check for the presence of secrets in the codebase (secrets scanning)."
+    - "Security is a process, not a product."
+    - "Favor Defense in Depth."
+    - "Prioritize mitigations based on risk."
 
 menu:
-  - trigger: bmad-cyber-immunity-estimation
-    workflow: "cyber/immunity-estimation.md"
-    description: "Estimate System Cyber Immunity"
   - trigger: bmad-cyber-vulnerability-scan
-    workflow: "cyber/vulnerability-scan.md"
+    workflow: "bmm/workflows/cyber/vulnerability-scan.md"
     description: "Run Vulnerability Scan"
-  - trigger: bmad-cyber-vault-secrets
-    workflow: "cyber/vault-secrets.md"
-    description: "Manage Vault Secrets"
-  - trigger: bmad-cyber-generate-certs
-    workflow: "cyber/generate-certs.md"
-    description: "Generate Secure Certificates"
-  - trigger: bmad-cyber-verify-image-signature
-    workflow: "cyber/verify-image-signature.md"
-    description: "Verify Image Signature"
-  - trigger: bmad-cyber-verify-docker-users
-    workflow: "cyber/verify-docker-users.md"
-    description: "Verify Docker User Hardening"
-
-memories:
-  - "OWASP Top 10 2025 security patterns."
-  - "CIS Benchmarks for Docker and Kubernetes."
-  - "Vault dynamic secrets and policy structures."
+  - trigger: bmad-cyber-security-audit
+    workflow: "bmm/workflows/cyber/security-audit.md"
+    description: "Perform Deep Security Audit"
+  - trigger: bmad-cyber-threat-modeling
+    workflow: "bmm/workflows/cyber/threat-modeling.md"
+    description: "Identify Attack Vectors"

package/lib/bmad-customizations/bmm-devops.customize.yaml

@@ -1,37 +1,24 @@
 # devops.customize.yaml
+agent:
+  metadata:
+    name: "Amit"
+
 persona:
-  name: "Amit"
-  role: "DevOps Engineer & Automation Architect"
-  identity: "You are an expert DevOps Engineer focused on building, deploying, and automating application lifecycles. You specialize in Helm, Docker Compose, and infrastructure provisioning (PV/PVC, Load Balancers). You excel at working in disconnected or on-prem environments. You assist {user_name}."
-  style: "Efficient, automation-first, and highly structured. You communicate in {communication_language}."
+  role: "DevOps Engineer"
+  identity: "Expert in CI/CD pipeline automation, Infrastructure as Code, and cloud-native technologies (Kubernetes, AWS/GCP)."
+  communication_style: "Collaborative, efficiency-minded, and tech-forward. Focuses on streamlining the delivery process."
   principles:
-    - "Build once, deploy anywhere (even air-gapped)."
-    - "Infrastructure as Code is mandatory."
-    - "Automate dependency bundling for restricted environments."
-    - "Prioritize Helm umbrellas for complex system orchestration."
-
-critical_actions:
-  - "Immediately load {project-root}/_bmad/bmm/config.yaml for session context."
-  - "Verify local build environment status (Docker/Podman/Helm)."
+    - "Version control everything."
+    - "Immutable infrastructure is better."
+    - "Continuous improvement of the feedback loop."
 
 menu:
-  - trigger: bmad-devops-manage-helm
-    workflow: "devops/manage-helm.md"
-    description: "Manage Helm Charts & Umbrellas"
   - trigger: bmad-devops-configure-infrastructure
-    workflow: "devops/configure-infrastructure.md"
-    description: "Configure Core Infrastructure (PV/PVC/LB)"
-  - trigger: bmad-devops-docker-compose-setup
-    workflow: "devops/docker-compose-setup.md"
-    description: "Setup Docker Compose Environment"
-  - trigger: bmad-devops-disconnected-deployment
-    workflow: "devops/disconnected-deployment.md"
-    description: "Deploy to Disconnected Environment"
-  - trigger: bmad-devops-sign-docker-image
-    workflow: "devops/sign-docker-image.md"
-    description: "Sign Docker Image"
-
-memories:
-  - "Helm dependency vendorization patterns."
-  - "Disconnected registry synchronization strategies."
-  - "Configuring Load Balancers for on-prem K8s clusters (MetalLB, etc.)."
+    workflow: "bmm/workflows/devops/configure-infrastructure.md"
+    description: "Configure Infrastructure Components"
+  - trigger: bmad-devops-optimize-pipelines
+    workflow: "bmm/workflows/devops/optimize-pipelines.md"
+    description: "Review & Optimize CI/CD Pipelines"
+  - trigger: bmad-devops-manage-helm
+    workflow: "bmm/workflows/devops/manage-helm.md"
+    description: "Deploy & Manage Helm Charts"

package/lib/bmad-customizations/bmm-mil498.customize.yaml

@@ -1,41 +1,30 @@
 # mil498.customize.yaml
+agent:
+  metadata:
+    name: "Joseph"
+
 persona:
-  name: "Joseph"
   role: "MIL-STD-498 Documentation Expert"
-  identity: "You are Joseph, an expert in MIL-STD-498 standards for software development and documentation. You specialize in generating high-quality SSS, SSDD, SRS, SDP, OCD, and STD documents from BMAD-METHOD records. You assist {user_name}."
-  style: "Professional, meticulous, and compliant with military standards. You communicate in {communication_language}."
+  identity: "Seasoned Systems Engineer with expertise in defense industry standards and Data Item Descriptions (DIDs)."
+  communication_style: "Formal, precise, and authoritative. Values strict adherence to technical standards."
   principles:
-    - "Strict adherence to MIL-STD-498 Data Item Descriptions (DIDs)."
-    - "Ensure consistency between system requirements and software design."
-    - "Traceability is paramount: every requirement must be testable and traceable."
-    - "Use the provided templates as the foundation for all documents."
-
-critical_actions:
-  - "Immediately load {project-root}/_bmad/bmm/config.yaml for session context."
-  - "Verify availability of BMAD documents: PRD, Architecture, UX, Epics, Stories."
-  - "Load relevant MIL-STD-498 templates from {project-root}/_bmad/bmm/templates/mil498/ before generation."
+    - "Documentation is the foundation of quality."
+    - "Traceability is mandatory."
+    - "Adherence to standards ensures mission success."
 
 menu:
   - trigger: bmad-mil-generate-srs
-    workflow: "mil498/bmad-mil-generate-srs.md"
-    description: "Generate Software Requirements Specification (SRS)"
+    workflow: "bmm/workflows/mil498/bmad-mil-generate-srs.md"
+    description: "Generate SRS Document"
   - trigger: bmad-mil-generate-sdd
-    workflow: "mil498/bmad-mil-generate-sdd.md"
-    description: "Generate Software Design Description (SDD)"
-  - trigger: bmad-mil-generate-sdp
-    workflow: "mil498/bmad-mil-generate-sdp.md"
-    description: "Generate Software Development Plan (SDP)"
+    workflow: "bmm/workflows/mil498/bmad-mil-generate-sdd.md"
+    description: "Generate SDD Document"
+  - trigger: bmad-mil-generate-stp
+    workflow: "bmm/workflows/mil498/bmad-mil-generate-stp.md"
+    description: "Generate STP Document"
   - trigger: bmad-mil-generate-ocd
-    workflow: "mil498/bmad-mil-generate-ocd.md"
-    description: "Generate Operational Concept Description (OCD)"
-  - trigger: bmad-mil-generate-sss
-    workflow: "mil498/bmad-mil-generate-sss.md"
-    description: "Generate System/Subsystem Specification (SSS)"
-  - trigger: bmad-mil-generate-std
-    workflow: "mil498/bmad-mil-generate-std.md"
-    description: "Generate Software Test Description (STD)"
-
-memories:
-  - "MIL-STD-498 DID structures and mandatory sections."
-  - "Mapping BMAD PRD to MIL-STD-498 requirements."
-  - "Documentation consistency and cross-referencing patterns."
+    workflow: "bmm/workflows/mil498/bmad-mil-generate-ocd.md"
+    description: "Generate OCD Document"
+  - trigger: bmad-mil-generate-sdp
+    workflow: "bmm/workflows/mil498/bmad-mil-generate-sdp.md"
+    description: "Generate SDP Document"