multimodel-dev-os 1.1.0 → 2.0.0

package/docs/public/llms-full.txt

@@ -1,73 +1,82 @@
-# MultiModel Dev OS — Comprehensive AI Assistant Discoverability Guide
-
-MultiModel Dev OS is a repository-level porting specification designed to align context and instructions across diverse developer tools and AI models.
-
----
-
-## 1. Core Architecture Layers
-
-The protocol decouples the centralized workspace context from the individual tool rules:
-
-```
-┌────────────────────────────────────────────────────────┐
-│ LAYER 1: Root Contracts (Single Source of Truth)       │
-│ AGENTS.md • MEMORY.md • TASKS.md • RUNBOOK.md          │
-└──────────────────────────┬─────────────────────────────┘
-                           │ Centralizes project context
-┌──────────────────────────▼─────────────────────────────┐
-│ LAYER 2: Configuration & Modules (.ai/)                │
-│ context/ • agents/ • skills/ • prompts/ • checks/      │
-└──────────────────────────┬─────────────────────────────┘
-                           │ Routes files dynamically
-┌──────────────────────────▼─────────────────────────────┐
-│ LAYER 3: Tool & IDE Adapters                           │
-│ .cursorrules • CLAUDE.md • .vscode/ • .gemini/        │
-└────────────────────────────────────────────────────────┘
-```
-
-### Layer 1: Root Documents
-- **`AGENTS.md`**: Defines teams, capabilities, boundaries, and model instructions.
-- **`MEMORY.md`**: Holds architectural decisions, repository milestones, and tech stacks.
-- **`TASKS.md`**: Active backlog tracking items.
-- **`RUNBOOK.md`**: Operational verification commands and post-deployment routines.
-
----
-
-## 2. CLI Command specifications
-
-All compliant MultiModel Dev OS CLIs strictly enforce the following command contracts:
-- **`init`**: Scaffolds the standard `.ai/` context configuration directories.
-- **`verify`**: Automated release script that checks structure integrity.
-- **`templates`**: Lists built-in stack specifications (`nextjs-saas`, `wordpress-site`, `ecommerce-store`, `seo-landing-page`, `general-app`).
-- **`validate`**: Strict Quality Gate checking the layout rules on disk.
-- **`doctor`**: Advisory checkup warning you about unignored compiler caches or large folder directories.
-
----
-
-## 3. Adapters & Mappings
-
-Adapters read context directly from `AGENTS.md` and translate them into native configs:
-- **Cursor** targets root `.cursorrules`
-- **Claude Code** targets root `CLAUDE.md`
-- **VS Code** targets `.vscode/settings.json`
-- **Gemini** targets root `GEMINI.md`
-- **Antigravity** targets `.gemini/settings.json`
-
----
-
-## 4. Key Context Optimization (Caveman Mode)
-
-Toggling **Caveman Mode** dynamically reduces system prompt instructions to highly-optimized shorthand symbols, reducing rule tokens footprint by **~79%** for low-cost token execution budgets:
-
-```bash
-npx multimodel-dev-os@latest init --caveman
-```
-
----
-
-## 5. Canonical Links
-- **Documentation site**: https://rizvee.github.io/multimodel-dev-os/
-- **GitHub Codebase**: https://github.com/rizvee/multimodel-dev-os
-- **Release Policies**: https://rizvee.github.io/multimodel-dev-os/release-policy
-- **LTS Support Policies**: https://rizvee.github.io/multimodel-dev-os/support-policy
-- **Upgrade Playbook**: https://rizvee.github.io/multimodel-dev-os/migration-guide
+# MultiModel Dev OS — Comprehensive AI Assistant Discoverability Guide (v2.0.0 Stable Release)
+
+MultiModel Dev OS is a repository-level porting specification designed to align context and instructions across diverse developer tools and AI models.
+
+---
+
+## 1. Core Architecture Layers
+
+The protocol decouples the centralized workspace context from the individual tool rules:
+
+```
+┌────────────────────────────────────────────────────────┐
+│ LAYER 1: Root Contracts (Single Source of Truth)       │
+│ AGENTS.md • MEMORY.md • TASKS.md • RUNBOOK.md          │
+│ (And central registries under .ai/models/ & .ai/adps/) │
+└──────────────────────────┬─────────────────────────────┘
+                           │ Centralizes project context
+┌──────────────────────────▼─────────────────────────────┐
+│ LAYER 2: Configuration & Modules (.ai/)                │
+│ context/ • agents/ • skills/ • prompts/ • checks/      │
+└──────────────────────────┬─────────────────────────────┘
+                           │ Routes files dynamically
+┌──────────────────────────▼─────────────────────────────┐
+│ LAYER 3: Tool & IDE Adapters                           │
+│ .cursorrules • CLAUDE.md • .vscode/ • .gemini/ • etc.  │
+└────────────────────────────────────────────────────────┘
+```
+
+### Layer 1: Root Documents
+- **`AGENTS.md`**: Defines teams, capabilities, boundaries, and model instructions.
+- **`MEMORY.md`**: Holds architectural decisions, repository milestones, and tech stacks.
+- **`TASKS.md`**: Active backlog tracking items.
+- **`RUNBOOK.md`**: Operational verification commands and post-deployment routines.
+
+---
+
+## 2. CLI Command Specifications
+
+All compliant MultiModel Dev OS CLIs strictly enforce the following command contracts:
+- **`init`**: Scaffolds the standard `.ai/` context configuration directories. Supports `--template`, `--caveman`, `--adapter`, and dynamic registries mapping.
+- **`verify`**: Automated release script that checks structure integrity.
+- **`templates`**: Lists built-in template profiles (supports overrides via `--registry <path>`).
+- **`validate`**: Strict Quality Gate checking the layout rules on disk (supports `--all-registries`).
+- **`validate-template`**: Scans a template registry entry and source directory structure for completeness.
+- **`validate-adapter`**: Audits an adapter config file and directory setup compliance.
+- **`validate-skill`**: Checks a custom skill file against standard Markdown headers.
+- **`doctor`**: Advisory checkup auditing ignored folders and token footprint (supports `--tokens` and `--release`).
+
+---
+
+## 3. Registries & Mappings
+
+### Model Compatibility Registry
+Central registry configuration resides in `.ai/models/`:
+* `registry.yaml`: Maps model aliases to official provider IDs, context windows, and tiers.
+* `providers.yaml`: API base urls and environment variables keys.
+* `routing-presets.yaml`: Multi-model presets for task-oriented routing.
+* `local-models.yaml`: Endpoint mappings for offline model engines (Ollama, Llama.cpp).
+
+### IDE/Agent Adapters Registry
+Central adapter rules mapped under `.ai/adapters/registry.yaml`:
+* Targets files like `.cursorrules`, `CLAUDE.md`, `.vscode/settings.json`, `.clinerules`, `.aider.conf.yml`, `.windsurfrules`, `.continue/config.json`.
+
+---
+
+## 4. Key Context Optimization (Caveman Mode)
+
+Toggling **Caveman Mode** dynamically reduces system prompt instructions to highly-optimized shorthand symbols, reducing rule tokens footprint by **~79%** for low-cost token execution budgets:
+
+```bash
+npx multimodel-dev-os@latest init --caveman
+```
+
+---
+
+## 5. Canonical Links
+- **Documentation site**: https://rizvee.github.io/multimodel-dev-os/
+- **GitHub Codebase**: https://github.com/rizvee/multimodel-dev-os
+- **v2.0.0 Roadmap**: https://rizvee.github.io/multimodel-dev-os/v2-roadmap
+- **Release Policies**: https://rizvee.github.io/multimodel-dev-os/release-policy
+- **Upgrade Playbook**: https://rizvee.github.io/multimodel-dev-os/migration-guide
+- **Model Compatibility**: https://rizvee.github.io/multimodel-dev-os/model-compatibility

package/docs/public/llms.txt

@@ -1,34 +1,36 @@
-# MultiModel Dev OS (v1.1.0)
-
-Portable, vendor-neutral workspace configuration standard for multi-agent AI pair-programming workflows. 
-
-## What It Does
-Provides a unified repository-level specification using root markdown files (`AGENTS.md`, `MEMORY.md`, `TASKS.md`, `RUNBOOK.md`) and bridges them dynamically to multiple developer tools, ensuring zero instruction drift and up to 79% token context savings.
-
-## Fast Setup
-```bash
-npx multimodel-dev-os@latest init
-```
-
-## Supported Tools
-- **Cursor** (`.cursorrules`)
-- **Claude Code** (`CLAUDE.md`)
-- **VS Code** (`.vscode/settings.json`)
-- **Gemini** (`GEMINI.md`)
-- **Antigravity** (`.gemini/settings.json`)
-- **Codex** (`adapters/codex/AGENTS.md`)
-
-## Core Resources
-- **Canonical Website**: https://rizvee.github.io/multimodel-dev-os/
-- **GitHub Repository**: https://github.com/rizvee/multimodel-dev-os
-- **NPM Registry Package**: https://www.npmjs.com/package/multimodel-dev-os
-- **Stable Protocol Specification**: https://rizvee.github.io/multimodel-dev-os/stable-protocol
-- **Cost/Context Optimization Playbook**: https://rizvee.github.io/multimodel-dev-os/cost-optimization
-- **5-Day Adoption Roadmap**: https://rizvee.github.io/multimodel-dev-os/5-day-roadmap
-
-## Standard Templates
-- `nextjs-saas` (App Router, Prisma ORM, Stripe)
-- `wordpress-site` (Custom Block Themes, secure PHP guidelines)
-- `ecommerce-store` (PCI checkout, Webhooks, card state)
-- `seo-landing-page` (Astro static builds, JSON-LD, optimal LCP)
-- `general-app` (Universal baseline configurations)
+# MultiModel Dev OS (v2.0.0 Stable Release)
+
+Portable, vendor-neutral workspace configuration standard for multi-agent AI pair-programming workflows.
+
+## Fast Setup (Stable npm @latest)
+```bash
+npx multimodel-dev-os@latest init
+```
+
+## Supported Tools
+- **Cursor** (`.cursorrules`)
+- **Claude Code** (`CLAUDE.md`)
+- **VS Code** (`.vscode/settings.json`)
+- **Gemini** (`GEMINI.md`)
+- **Antigravity** (`.gemini/settings.json`)
+- **Continue** (`.continue/config.json`)
+- **Cline / Roo Code** (`.clinerules`)
+- **Aider** (`.aider.conf.yml`)
+- **Windsurf** (`.windsurfrules`)
+- **Codex** (`adapters/codex/AGENTS.md`)
+
+## Core Resources
+- **Canonical Website**: https://rizvee.github.io/multimodel-dev-os/
+- **GitHub Repository**: https://github.com/rizvee/multimodel-dev-os
+- **NPM Package**: https://www.npmjs.com/package/multimodel-dev-os
+- **Stable Protocol Specification**: https://rizvee.github.io/multimodel-dev-os/stable-protocol
+- **Model Compatibility & Routing Guide**: https://rizvee.github.io/multimodel-dev-os/model-compatibility
+- **Cost/Context Optimization Playbook**: https://rizvee.github.io/multimodel-dev-os/cost-optimization
+
+## Standard Templates
+- `nextjs-saas` (App Router, Prisma ORM, Stripe)
+- `wordpress-site` (Custom Block Themes, secure PHP guidelines)
+- `ecommerce-store` (PCI checkout, Webhooks, card state)
+- `seo-landing-page` (Astro static builds, JSON-LD, optimal LCP)
+- `expo-react-native-android` (Production Android delivery with EAS Build)
+- `general-app` (Universal baseline configurations)

package/docs/quickstart.md

@@ -6,9 +6,9 @@ Get the MultiModel Dev OS integrated into your codebase in under 2 minutes to sy
 
 ---
 
-## Option A: NPX Scaffolding (Recommended)
+## Option A: NPX Scaffolding (Stable Packages)
 
-Initialize any project immediately without local clones using our public npm registry:
+Initialize any project instantly using our public npm registry. Note that this pulls the latest stable npm-published release (`v2.0.0`):
 
 ```bash
 # Standard interactive initialization in the current directory
@@ -25,7 +25,7 @@ npx multimodel-dev-os@latest init --dry-run
 
 ## Option B: Fallback One-Line Scripts
 
-If you choose to run installation scripts directly:
+If you choose to run installation scripts directly (fetches stable files):
 
 **macOS / Linux / WSL (bash):**
 ```bash
@@ -49,14 +49,15 @@ curl -fsSL https://raw.githubusercontent.com/rizvee/multimodel-dev-os/main/scrip
 
 ---
 
-## Option D: Node.js Local Scaffolding CLI
+## Option D: Node.js Local Scaffolding CLI (Direct Run)
+
+If you prefer to run directly from cloned source without global installation:
 
-For offline execution or customized packaging within a cloned workspace:
 1. Clone this repository locally:
    ```bash
    git clone https://github.com/rizvee/multimodel-dev-os.git
    ```
-2. Run the CLI directly using the absolute target path:
+2. Run the CLI directly from the cloned repository source:
    ```bash
    node bin/multimodel-dev-os.js init --target /path/to/your-project --template nextjs-saas --adapter cursor
    ```

package/docs/registry-contribution.md

@@ -0,0 +1,20 @@
+# Registry Contribution Workflow
+
+This document describes how to propose and contribute new models, adapters, and templates.
+
+## Contribution Flow
+
+1. **Local Authoring:** Follow the respective authoring guides:
+   * [Custom IDE Adapter Authoring](adapter-authoring.md)
+   * [Custom Template Authoring](template-authoring.md)
+   * [Skill Authoring](skill-authoring.md)
+2. **Local Validation:** Use validation CLI commands to ensure structural compliance:
+   * `node bin/multimodel-dev-os.js validate-template <name>`
+   * `node bin/multimodel-dev-os.js validate-adapter <name>`
+   * `node bin/multimodel-dev-os.js validate-skill <name>`
+3. **Registry Addition:** Insert your metadata records into:
+   * `.ai/templates/registry.yaml` for templates.
+   * `.ai/adapters/registry.yaml` for adapters.
+   * `.ai/models/registry.yaml` for models.
+4. **Verification suite:** Run `npm run verify` to ensure the release audit checks pass cleanly.
+5. **Submit PR:** Submit your changes via a GitHub Pull Request to `https://github.com/rizvee/multimodel-dev-os`.

package/docs/release-policy.md

@@ -31,3 +31,29 @@ No package shall be merged or released without:
 - Building the documentation site without dead links (`npm run docs:build`).
 - Running packaging validation (`npm pack --dry-run`).
 - Executing smoke tests on all templates.
+
+---
+
+## 4. NPM Publishing Pause & Roadmap Development
+
+To ensure high stability and thorough testing of the Template Galaxy and Model Compatibility Layers, package publishing to the public npm registry is paused during all `v1.2.x` minor releases:
+* **GitHub Repository (Source)**: Serve as the primary, active source branch containing unreleased v1.2+ features (such as template extensions, model registries, and CLI expansions).
+* **NPM Registry (Latest)**: Remains on the last approved stable version.
+* **v2.0.0 (Next Target)**: Will serve as the next stable release published to the npm registry, packaging the hardened registries and Template Galaxy features.
+
+### Local Source & Verification Procedures
+
+Contributors and developers must verify and test unreleased `v1.2.x` features locally rather than running publication steps:
+1. **Execute commands from the source binary:**
+   ```bash
+   node bin/multimodel-dev-os.js init
+   node bin/multimodel-dev-os.js verify
+   ```
+2. **Compile and test the package bundle locally:**
+   ```bash
+   npm pack
+   ```
+   This generates a local `.tgz` archive. Install it in a target test project to run validations.
+
+Never execute `npm publish` in the main workspace unless actively packaging the approved `v2.0.0` release.
+

package/docs/skill-authoring.md

@@ -0,0 +1,56 @@
+# Skill Authoring Guide
+
+This guide explains how to construct high-fidelity reusable skills for MultiModel Dev OS.
+
+## Overview
+
+Skills are custom prompts placed in the `.ai/skills/` directory of a project workspace. They instruct coding agents on exactly how to perform specific coding, refactoring, validation, or deployment routines.
+
+## Required Structure
+
+Every reusable skill file must be a Markdown (`.md`) file containing the following key sections:
+
+```markdown
+# Purpose
+Describe what this skill accomplishes.
+
+# Activation Trigger
+Specify when a developer or agent should invoke this skill.
+
+# Input Context
+List the dependencies, files, or information required before executing this skill.
+
+# Output Contract
+Define the expected deliverables, formats, or file updates.
+
+# Token Budget
+Expected prompt footprint and limits.
+```
+
+## Example Skill File
+
+```markdown
+# Purpose
+Deploy a Next.js Server Action with security gates.
+
+# Activation Trigger
+Trigger when building or modifying API endpoints / React Server Actions.
+
+# Input Context
+* Target action file
+* Schema validations definitions
+
+# Output Contract
+Return the modified action file containing secure CSRF/Origin validation rules.
+
+# Token Budget
+~500 tokens
+```
+
+## Validating a Skill
+
+To test your skill structure compliance, run:
+
+```bash
+node bin/multimodel-dev-os.js validate-skill my-skill-name
+```

package/docs/template-authoring.md

@@ -0,0 +1,65 @@
+# Custom Template Authoring Guide
+
+This guide explains how to author a custom workspace configuration template for MultiModel Dev OS.
+
+## Overview
+
+A template packages a set of boilerplate markdown files (`AGENTS.md`, `MEMORY.md`, `TASKS.md`, `RUNBOOK.md`), a central `.ai/config.yaml` file, and stack-specific context files and skills.
+
+## Structure of a Template Source
+
+A template resides in the `examples/` directory of the project, or can be loaded dynamically from a custom path using `--registry` if declared in the registry.
+
+```
+examples/my-custom-template/
+├── AGENTS.md                   # Core workspace contracts
+├── MEMORY.md
+├── TASKS.md
+├── RUNBOOK.md
+└── .ai/
+    ├── config.yaml             # Core configuration rules
+    ├── context/                # Context templates
+    │   ├── project-brief.md
+    │   ├── architecture.md
+    │   └── context-budget.md
+    └── skills/                 # Custom reusable skill files
+        └── custom-action.md
+```
+
+## Creating a Registry Entry
+
+Add your template metadata to `.ai/templates/registry.yaml`:
+
+```yaml
+templates:
+  my-custom-template:
+    name: "my-custom-template"
+    description: "My custom framework stack workspace baseline."
+    stack: "My Framework, TypeScript, PostgreSQL"
+    skill: "custom-action.md"
+    skillDesc: "Framework specific secure execution rules."
+    category: "Web"
+    status: "stable"
+    maturity: "production-ready"
+    required_files:
+      - AGENTS.md
+      - MEMORY.md
+      - TASKS.md
+      - RUNBOOK.md
+      - .ai/config.yaml
+      - .ai/context/project-brief.md
+      - .ai/skills/custom-action.md
+```
+
+## Validation Rules
+
+You can validate your template configuration using the CLI:
+
+```bash
+node bin/multimodel-dev-os.js validate-template my-custom-template
+```
+
+Validation ensures:
+1. The template metadata matches the registry schema.
+2. The template source directory exists.
+3. All files listed in `required_files` are present.

package/docs/token-optimization.md

@@ -0,0 +1,27 @@
+# Token Optimization & Budget Policy
+
+In agentic coding workflows, token overheads are the single largest source of API latency and cost. MultiModel Dev OS integrates tools and policies to optimize context inputs.
+
+---
+
+## 1. Caveman Mode
+* **Goal**: Reduce baseline context token footprint by ~79%.
+* **CLI Flag**: `node bin/multimodel-dev-os.js init --caveman`
+* **Behavior**: Instantiates minimal `.caveman.md` files for `AGENTS.md`, `MEMORY.md`, `TASKS.md`, and `RUNBOOK.md`, omitting explanatory files and dense markdown guidelines.
+
+---
+
+## 2. Context Budget Auditing
+* Define strict context bounds inside [.ai/context/context-budget.md](file:///F:/multimodel-dev-os/.ai/context/context-budget.md).
+* **CLI Command**: `node bin/multimodel-dev-os.js doctor --tokens`
+  * Checks if build outputs or caches (`node_modules/`, `dist/`, `.next/`, `build/`) are missing from `.gitignore` or are being exposed to LLM scan scopes.
+
+---
+
+## 3. Policy Guidelines
+
+### Keep Checklist Files Short
+Use `TASKS.md` exclusively for active sprint tasks. Move completed or historical backlogs to archive directories or logs.
+
+### Model Handoff Compression
+When switching from reasoning models to quick-fixing models, use [.ai/prompts/compress-context.md](file:///F:/multimodel-dev-os/.ai/prompts/compress-context.md) to distill findings into high-density prompts.

package/docs/v2-migration.md

@@ -0,0 +1,31 @@
+# MultiModel Dev OS v2 Migration Guide
+
+This guide describes how to migrate your developer configurations and workspace setup to the new Layered Architecture of MultiModel Dev OS v2.
+
+## What is Changing
+
+* **Version 1.1.0 and prior:** Handled flat configurations directly at the project root with individual configurations manually copied across.
+* **Version 2.0.0 (and source milestones 1.2–1.5):** Establishes a clean, three-layered architecture where root contracts (`AGENTS.md`, `MEMORY.md`, `TASKS.md`, `RUNBOOK.md`) are automatically routed to adapters via the `.ai/` directory.
+
+## Migration Steps
+
+### 1. Upgrade the CLI
+Run the latest v2 setup utility via npx:
+```bash
+npx multimodel-dev-os@latest init --template general-app
+```
+
+### 2. Move Legacy Configuration Files
+If you have custom system instructions or rules:
+* Move `.cursorrules` custom rules to `.ai/skills/` as custom markdown skills.
+* Re-generate adapter links:
+  ```bash
+  npx multimodel-dev-os@latest init --adapter cursor --adapter claude
+  ```
+
+### 3. Verify Migration Integrity
+Run diagnostics to verify that ignored folders, boundaries, and files are clean:
+```bash
+npx multimodel-dev-os@latest doctor
+npx multimodel-dev-os@latest validate
+```

package/docs/v2-release-checklist.md

@@ -0,0 +1,30 @@
+# v2 Release Checklist
+
+Use this checklist to verify compliance before publishing `multimodel-dev-os` to the npm registry.
+
+## Pre-Flight Requirements
+
+- [x] Ensure version string in `package.json` is set to `2.0.0`.
+- [x] Verify version strings in documentation and install scripts (`scripts/install.sh`, `scripts/install.ps1`) align with the release.
+- [x] Run full release verification:
+  ```bash
+  npm run verify
+  ```
+- [x] Run registry checks:
+  ```bash
+  node bin/multimodel-dev-os.js validate --all-registries
+  ```
+- [x] Run release doctor:
+  ```bash
+  node bin/multimodel-dev-os.js doctor --release
+  ```
+
+## Packaging Verification
+
+- [x] Execute dry pack run:
+  ```bash
+  npm pack --dry-run
+  ```
+- [x] Inspect generated tarball file listing to verify only necessary directories (`.ai/`, `adapters/`, `bin/`, `docs/`, `examples/`, `scripts/`, `assets/`) are included.
+- [x] Verify that the prepublish guard is bypassed only for the official production run.
+- [x] Confirm no `.env` or sensitive `.npmrc` configurations are packaged.

package/docs/v2-roadmap.md

@@ -0,0 +1,95 @@
+# MultiModel Dev OS — v2.0.0 Roadmap
+
+This document outlines the development path, stabilization targets, and migration roadmap leading to the `v2.0.0` stable release of MultiModel Dev OS.
+
+---
+
+## 1. Release Objective
+
+The primary goal of the **v2.0.0 release** is to promote the experimental features introduced in `v1.2.0` (Template Galaxy, Model Compatibility Layer, and Android Expo template) into officially frozen, production-grade core components, and resume stable package publication to the public npm registry.
+
+> [!IMPORTANT]
+> **v2.0.0 is the active stable release.** NPM publishing is resumed, consolidating the Template Galaxy and Model registries.
+
+---
+
+## 2. Key Stabilization Targets
+
+### A. Template Galaxy Stabilization
+* Standardize the schema for template configurations under `.ai/schema/template.schema.json`.
+* Harden the built-in templates (`nextjs-saas`, `wordpress-site`, `ecommerce-store`, `seo-landing-page`, `expo-react-native-android`, `general-app`) to ensure they pass validation checks across diverse OS environments.
+
+### B. Model Registry Stabilization
+* Freeze the `.ai/models/` structure:
+  * `registry.yaml` — Core provider mappings and model metadata.
+  * `providers.yaml` — API endpoint declarations.
+  * `routing-presets.yaml` — Optimized task routing configurations.
+  * `local-models.yaml` — Offline execution definitions.
+* Standardize validation rules inside `validate` and `doctor` commands to verify YAML configuration syntax and compatibility.
+
+### C. Adapter Registry Stabilization
+* Freeze `.ai/adapters/registry.yaml`.
+* Extend support mapping for emerging developer tools (e.g. Continue, Cline, Roo Code, Aider, Windsurf).
+* Ensure cross-linking logic maintains strict custom boundaries so that updates in `AGENTS.md` synchronize with adapter targets without wiping user overrides.
+
+### D. Android Expo Template Stabilization
+* Hardening the `examples/expo-react-native-android/` foundation.
+* Verify clean execution of EAS Build and environment configurations on local developer machines and CI runner platforms.
+
+### E. CLI Compatibility Pass
+* Ensure the new subcommands introduced in `v1.2.0` are fully backward-compatible with `v1.0.0` and `v1.1.0` CLI patterns:
+  * `models` / `show-model`
+  * `providers`
+  * `route-model`
+  * `adapters` / `show-adapter`
+  * `skills` / `show-skill`
+  * `doctor --tokens`
+  * `validate --template`
+
+---
+
+## 3. Package Publishing Checklist
+
+Before executing the `v2.0.0` release on the npm registry, the following steps must be completed:
+
+1. [x] Set version to `2.0.0` in `package.json`.
+2. [x] Ensure `scripts/prepublish-guard.js` allows the publish (since version starts with `2.`).
+3. [x] Run all verification suites:
+   ```bash
+   npm run verify
+   ```
+4. [x] Build documentation static bundles cleanly:
+   ```bash
+   npm run docs:build
+   ```
+5. [x] Perform a dry-run publish to review package hygiene:
+   ```bash
+   npm publish --dry-run
+   ```
+6. [x] Set the required publication environment variable:
+   * **PowerShell:** `$env:MMDO_ALLOW_PUBLISH="true"`
+   * **Bash:** `export MMDO_ALLOW_PUBLISH=true`
+7. [x] Publish the package to the public registry:
+   ```bash
+   npm publish --access public
+   ```
+
+---
+
+## 4. Migration Notes: npm latest to v2.0.0
+
+* **Direct Upgrades**: Projects running the last stable npm package (e.g., `1.1.0` / `1.0.0`) can migrate to `2.0.0` by executing `npx multimodel-dev-os@latest init --force` or installing the package locally.
+* **Registry Release**: Now that v2.0.0 is released, cloning the repository is no longer required to access Layer 1 templates or model registries. Simply run:
+  ```bash
+  npx multimodel-dev-os@latest init
+  ```
+* **Configuration Upgrades**: Existing `.ai/` folders can be upgraded by running `init --force` to pull the new centralized registries (`.ai/models/` and `.ai/adapters/`) into the workspace.
+
+---
+
+## 5. Final Release Gate
+
+The `v2.0.0` release requires:
+1. 100% pass rate on all automated linter and verifier checks.
+2. Complete documentation updates across all guides and discovery indices.
+3. Explicit maintainer sign-off on local testing of the Android Expo template.

package/examples/expo-react-native-android/.ai/config.yaml

@@ -0,0 +1,22 @@
+# Mobile App configuration
+
+project:
+  name: "expo-react-native-android"
+  description: "Production-ready Android mobile app with Expo, React Native, and EAS builds."
+  version: "1.0.0"
+
+mode: "standard"
+
+adapters:
+  cursor: false
+  claude: false
+  gemini: false
+  vscode: false
+  antigravity: false
+
+skills:
+  directory: ".ai/skills/"
+  auto_load: true
+
+prompts:
+  directory: ".ai/prompts/"