grimoire-framework 1.0.0

package/.grimoire/product/templates/grimoire-ai-config.yaml

@@ -0,0 +1,107 @@
+# grimoire AI Provider Configuration
+#
+# Configure AI providers (Claude Code, Gemini CLI) for grimoire operations.
+# This file controls which provider is used for different task types.
+#
+# @see Epic GEMINI-INT - Story 2: AI Provider Factory Pattern
+
+# Provider Configuration
+ai_providers:
+  # Primary provider - used by default
+  primary: claude        # Options: claude, gemini
+
+  # Fallback provider - used when primary fails
+  fallback: gemini       # Options: claude, gemini, null (no fallback)
+
+  # Task-based routing
+  # Route specific task types to preferred providers
+  routing:
+    # Simple tasks - use cheaper/faster provider
+    simple_tasks: gemini       # Code formatting, simple refactors
+
+    # Complex tasks - use more capable provider
+    complex_tasks: claude      # Architecture, security reviews
+
+    # Documentation - high volume, speed matters
+    documentation: gemini
+
+    # Code generation - balance of speed and quality
+    code_generation: gemini
+
+    # Code review - quality matters
+    code_review: claude
+
+    # Testing - straightforward tasks
+    testing: gemini
+
+    # Security - critical thinking required
+    security: claude
+
+# Claude Code Configuration
+claude:
+  # Model to use
+  model: claude-3-5-sonnet    # Options: claude-3-5-sonnet, claude-3-opus, etc.
+
+  # Execution timeout (ms)
+  timeout: 300000             # 5 minutes
+
+  # Maximum retry attempts
+  maxRetries: 3
+
+  # Skip permission prompts (use with caution)
+  dangerouslySkipPermissions: false
+
+# Gemini CLI Configuration
+gemini:
+  # Model to use
+  model: gemini-2.0-flash     # Options: gemini-2.0-flash, gemini-2.0-pro
+
+  # Execution timeout (ms)
+  timeout: 300000             # 5 minutes
+
+  # Maximum retry attempts
+  maxRetries: 3
+
+  # Enable preview features (required for Gemini 3)
+  previewFeatures: true
+
+  # Use JSON output format by default
+  jsonOutput: false
+
+# Model Switching (Story 16)
+# Automatic selection between Flash and Pro based on task complexity
+model_switching:
+  enabled: false              # Enable when Story 16 is complete
+  default_model: gemini-2.0-flash
+  complexity_threshold:
+    simple: 0.3               # < 0.3 = Flash
+    medium: 0.7               # 0.3-0.7 = Flash
+    complex: 1.0              # > 0.7 = Pro
+  quality_fallback:
+    enabled: true
+    min_score: 0.6            # If quality < 0.6, retry with Pro
+
+# Parallel Execution (Story 17)
+# Run Claude + Gemini simultaneously for better quality
+parallel_execution:
+  enabled: false              # Enable when Story 17 is complete
+  default_mode: fallback      # Options: race, consensus, best-of, merge, fallback
+
+  # Task-specific modes
+  task_modes:
+    architecture: consensus   # Both must agree on architecture
+    security: consensus       # Critical - need agreement
+    code_generation: best-of  # Pick best code
+    documentation: race       # Speed matters
+    refactoring: merge        # Combine insights
+
+  # Cost control
+  cost_control:
+    max_parallel_cost: 1.00   # Max cost for parallel run (USD)
+    fallback_on_budget: true  # Disable parallel if over budget
+
+  # Quality thresholds
+  quality_thresholds:
+    consensus_similarity: 0.85
+    merge_min_quality: 0.7
+

package/.grimoire/product/templates/ide-rules/antigravity-rules.md

@@ -0,0 +1,117 @@
+# Grimoire Development Rules for AntiGravity
+
+You are working with Grimoire, an AI-Orchestrated System for Full Stack Development.
+
+## Core Development Rules
+
+### Agent Integration
+- Recognize grimoire agent activations: @dev, @qa, @architect, @pm, @po, @sm, @analyst
+- Agent commands use * prefix: *help, *create-story, *task, *exit
+- Follow agent-specific workflows and patterns
+
+### Story-Driven Development
+1. **Always work from a story file** in docs/stories/
+2. **Update story checkboxes** as you complete tasks: [ ] → [x]
+3. **Maintain the File List** section with all created/modified files
+4. **Follow acceptance criteria** exactly as written
+
+### Code Quality Standards
+- Write clean, maintainable code following project conventions
+- Include comprehensive error handling
+- Add unit tests for all new functionality
+- Follow existing patterns in the codebase
+
+### Testing Protocol
+- Run all tests before marking tasks complete
+- Ensure linting passes: `npm run lint`
+- Verify type checking: `npm run typecheck`
+- Add tests for new features
+
+## grimoire Framework Structure
+
+```
+grimoire/
+├── agents/       # Agent persona definitions
+├── tasks/        # Executable task workflows
+├── workflows/    # Multi-step workflows
+├── templates/    # Document templates
+└── checklists/   # Validation checklists
+
+docs/
+├── stories/      # Development stories
+├── prd/          # Sharded PRD sections
+└── architecture/ # Sharded architecture
+```
+
+## Development Workflow
+
+1. **Read the story** - Understand requirements fully
+2. **Implement sequentially** - Follow task order
+3. **Test thoroughly** - Validate each step
+4. **Update story** - Mark completed items
+5. **Document changes** - Update File List
+
+## Best Practices
+
+### When implementing:
+- Check existing patterns first
+- Reuse components and utilities
+- Follow naming conventions
+- Keep functions focused and small
+
+### When testing:
+- Write tests alongside implementation
+- Test edge cases
+- Verify error handling
+- Run full test suite
+
+### When documenting:
+- Update README for new features
+- Document API changes
+- Add inline comments for complex logic
+- Keep story File List current
+
+## Git & GitHub
+
+- Use conventional commits: `feat:`, `fix:`, `docs:`, etc.
+- Reference story ID in commits: `feat: implement IDE detection [Story 2.1]`
+- Ensure GitHub CLI is configured: `gh auth status`
+- Push regularly to avoid conflicts
+
+## Common Patterns
+
+### Error Handling
+```javascript
+try {
+  // Operation
+} catch (error) {
+  console.error(`Error in ${operation}:`, error);
+  throw new Error(`Failed to ${operation}: ${error.message}`);
+}
+```
+
+### File Operations
+```javascript
+const fs = require('fs-extra');
+const path = require('path');
+
+// Always use absolute paths
+const filePath = path.join(__dirname, 'relative/path');
+```
+
+### Async/Await
+```javascript
+async function operation() {
+  try {
+    const result = await asyncOperation();
+    return result;
+  } catch (error) {
+    // Handle error appropriately
+  }
+}
+```
+
+---
+*Grimoire AntiGravity Configuration v1.0*
+
+

package/.grimoire/product/templates/ide-rules/claude-rules.md

@@ -0,0 +1,233 @@
+# Grimoire Development Rules for Claude Code
+
+You are working with Grimoire, an AI-Orchestrated System for Full Stack Development.
+
+<!-- grimoire-MANAGED-START: core-framework -->
+## Core Framework Understanding
+
+Grimoire is a meta-framework that orchestrates AI agents to handle complex development workflows. Always recognize and work within this architecture.
+<!-- grimoire-MANAGED-END: core-framework -->
+
+<!-- grimoire-MANAGED-START: agent-system -->
+## Agent System
+
+### Agent Activation
+- Agents are activated with @agent-name syntax: @dev, @qa, @architect, @pm, @po, @sm, @analyst
+- The master agent is activated with @grimoire-master
+- Agent commands use the * prefix: *help, *create-story, *task, *exit
+
+### Agent Context
+When an agent is active:
+- Follow that agent's specific persona and expertise
+- Use the agent's designated workflow patterns
+- Maintain the agent's perspective throughout the interaction
+<!-- grimoire-MANAGED-END: agent-system -->
+
+## Development Methodology
+
+### Story-Driven Development
+1. **Work from stories** - All development starts with a story in `docs/stories/`
+2. **Update progress** - Mark checkboxes as tasks complete: [ ] → [x]
+3. **Track changes** - Maintain the File List section in the story
+4. **Follow criteria** - Implement exactly what the acceptance criteria specify
+
+### Code Standards
+- Write clean, self-documenting code
+- Follow existing patterns in the codebase
+- Include comprehensive error handling
+- Add unit tests for all new functionality
+- Use TypeScript/JavaScript best practices
+
+### Testing Requirements
+- Run all tests before marking tasks complete
+- Ensure linting passes: `npm run lint`
+- Verify type checking: `npm run typecheck`
+- Add tests for new features
+- Test edge cases and error scenarios
+
+<!-- grimoire-MANAGED-START: framework-structure -->
+## grimoire Framework Structure
+
+```
+grimoire/
+├── agents/         # Agent persona definitions (YAML/Markdown)
+├── tasks/          # Executable task workflows
+├── workflows/      # Multi-step workflow definitions
+├── templates/      # Document and code templates
+├── checklists/     # Validation and review checklists
+└── rules/          # Framework rules and patterns
+
+docs/
+├── stories/        # Development stories (numbered)
+├── prd/            # Product requirement documents
+├── architecture/   # System architecture documentation
+└── guides/         # User and developer guides
+```
+<!-- grimoire-MANAGED-END: framework-structure -->
+
+## Workflow Execution
+
+### Task Execution Pattern
+1. Read the complete task/workflow definition
+2. Understand all elicitation points
+3. Execute steps sequentially
+4. Handle errors gracefully
+5. Provide clear feedback
+
+### Interactive Workflows
+- Workflows with `elicit: true` require user input
+- Present options clearly
+- Validate user responses
+- Provide helpful defaults
+
+## Best Practices
+
+### When implementing features:
+- Check existing patterns first
+- Reuse components and utilities
+- Follow naming conventions
+- Keep functions focused and testable
+- Document complex logic
+
+### When working with agents:
+- Respect agent boundaries
+- Use appropriate agent for each task
+- Follow agent communication patterns
+- Maintain agent context
+
+### When handling errors:
+```javascript
+try {
+  // Operation
+} catch (error) {
+  console.error(`Error in ${operation}:`, error);
+  // Provide helpful error message
+  throw new Error(`Failed to ${operation}: ${error.message}`);
+}
+```
+
+## Git & GitHub Integration
+
+### Commit Conventions
+- Use conventional commits: `feat:`, `fix:`, `docs:`, `chore:`, etc.
+- Reference story ID: `feat: implement IDE detection [Story 2.1]`
+- Keep commits atomic and focused
+
+### GitHub CLI Usage
+- Ensure authenticated: `gh auth status`
+- Use for PR creation: `gh pr create`
+- Check org access: `gh api user/memberships`
+
+<!-- grimoire-MANAGED-START: grimoire-patterns -->
+## grimoire-Specific Patterns
+
+### Working with Templates
+```javascript
+const template = await loadTemplate('template-name');
+const rendered = await renderTemplate(template, context);
+```
+
+### Agent Command Handling
+```javascript
+if (command.startsWith('*')) {
+  const agentCommand = command.substring(1);
+  await executeAgentCommand(agentCommand, args);
+}
+```
+
+### Story Updates
+```javascript
+// Update story progress
+const story = await loadStory(storyId);
+story.updateTask(taskId, { status: 'completed' });
+await story.save();
+```
+<!-- grimoire-MANAGED-END: grimoire-patterns -->
+
+## Environment Setup
+
+### Required Tools
+- Node.js 18+
+- GitHub CLI
+- Git
+- Your preferred package manager (npm/yarn/pnpm)
+
+### Configuration Files
+- `.grimoire/config.yaml` - Framework configuration
+- `.env` - Environment variables
+- `grimoire.config.js` - Project-specific settings
+
+<!-- grimoire-MANAGED-START: common-commands -->
+## Common Commands
+
+### grimoire Master Commands
+- `*help` - Show available commands
+- `*create-story` - Create new story
+- `*task {name}` - Execute specific task
+- `*workflow {name}` - Run workflow
+
+### Development Commands
+- `npm run dev` - Start development
+- `npm test` - Run tests
+- `npm run lint` - Check code style
+- `npm run build` - Build project
+<!-- grimoire-MANAGED-END: common-commands -->
+
+## Debugging
+
+### Enable Debug Mode
+```bash
+export grimoire_DEBUG=true
+```
+
+### View Agent Logs
+```bash
+tail -f .grimoire/logs/agent.log
+```
+
+### Trace Workflow Execution
+```bash
+npm run trace -- workflow-name
+```
+
+## Claude Code Specific Configuration
+
+### Performance Optimization
+- Prefer batched tool calls when possible for better performance
+- Use parallel execution for independent operations
+- Cache frequently accessed data in memory during sessions
+
+### Tool Usage Guidelines
+- Always use the Grep tool for searching, never `grep` or `rg` in bash
+- Use the Task tool for complex multi-step operations
+- Batch file reads/writes when processing multiple files
+- Prefer editing existing files over creating new ones
+
+### Session Management
+- Track story progress throughout the session
+- Update checkboxes immediately after completing tasks
+- Maintain context of the current story being worked on
+- Save important state before long-running operations
+
+### Error Recovery
+- Always provide recovery suggestions for failures
+- Include error context in messages to user
+- Suggest rollback procedures when appropriate
+- Document any manual fixes required
+
+### Testing Strategy
+- Run tests incrementally during development
+- Always verify lint and typecheck before marking complete
+- Test edge cases for each new feature
+- Document test scenarios in story files
+
+### Documentation
+- Update relevant docs when changing functionality
+- Include code examples in documentation
+- Keep README synchronized with actual behavior
+- Document breaking changes prominently
+
+---
+*Grimoire Claude Code Configuration v2.0*
+
+

package/.grimoire/product/templates/ide-rules/codex-rules.md

@@ -0,0 +1,67 @@
+# AGENTS.md - Grimoire (Codex CLI)
+
+Este arquivo define as instrucoes do projeto para o Codex CLI.
+
+<!-- grimoire-MANAGED-START: core -->
+## Core Rules
+
+1. Siga a Constitution em `.grimoire/constitution.md`
+2. Priorize `CLI First -> Observability Second -> UI Third`
+3. Trabalhe por stories em `docs/stories/`
+4. Nao invente requisitos fora dos artefatos existentes
+<!-- grimoire-MANAGED-END: core -->
+
+<!-- grimoire-MANAGED-START: quality -->
+## Quality Gates
+
+- Rode `npm run lint`
+- Rode `npm run typecheck`
+- Rode `npm test`
+- Atualize checklist e file list da story antes de concluir
+<!-- grimoire-MANAGED-END: quality -->
+
+<!-- grimoire-MANAGED-START: codebase -->
+## Project Map
+
+- Core framework: `.grimoire/`
+- CLI entrypoints: `bin/`
+- Shared packages: `packages/`
+- Tests: `tests/`
+- Docs: `docs/`
+<!-- grimoire-MANAGED-END: codebase -->
+
+<!-- grimoire-MANAGED-START: commands -->
+## Common Commands
+
+- `npm run sync:ide`
+- `npm run sync:ide:check`
+- `npm run sync:skills:codex`
+- `npm run sync:skills:codex:global` (opcional; neste repo o padrao e local-first)
+- `npm run validate:structure`
+- `npm run validate:agents`
+<!-- grimoire-MANAGED-END: commands -->
+
+<!-- grimoire-MANAGED-START: shortcuts -->
+## Agent Shortcuts
+
+Preferencia de ativacao no Codex CLI:
+1. Use `/skills` e selecione `grimoire-<agent-id>` vindo de `.codex/skills` (ex.: `grimoire-architect`)
+2. Se preferir, use os atalhos abaixo (`@architect`, `/architect`, etc.)
+
+Interprete os atalhos abaixo carregando o arquivo correspondente em `.grimoire/development/agents/` (fallback: `.codex/agents/`), renderize o greeting via `generate-greeting.js` e assuma a persona ate `*exit`:
+
+- `@architect`, `/architect`, `/architect.md` -> `.grimoire/development/agents/architect.md`
+- `@dev`, `/dev`, `/dev.md` -> `.grimoire/development/agents/dev.md`
+- `@qa`, `/qa`, `/qa.md` -> `.grimoire/development/agents/qa.md`
+- `@pm`, `/pm`, `/pm.md` -> `.grimoire/development/agents/pm.md`
+- `@po`, `/po`, `/po.md` -> `.grimoire/development/agents/po.md`
+- `@sm`, `/sm`, `/sm.md` -> `.grimoire/development/agents/sm.md`
+- `@analyst`, `/analyst`, `/analyst.md` -> `.grimoire/development/agents/analyst.md`
+- `@devops`, `/devops`, `/devops.md` -> `.grimoire/development/agents/devops.md`
+- `@data-engineer`, `/data-engineer`, `/data-engineer.md` -> `.grimoire/development/agents/data-engineer.md`
+- `@ux-design-expert`, `/ux-design-expert`, `/ux-design-expert.md` -> `.grimoire/development/agents/ux-design-expert.md`
+- `@squad-creator`, `/squad-creator`, `/squad-creator.md` -> `.grimoire/development/agents/squad-creator.md`
+- `@grimoire-master`, `/grimoire-master`, `/grimoire-master.md` -> `.grimoire/development/agents/grimoire-master.md`
+<!-- grimoire-MANAGED-END: shortcuts -->
+
+

package/.grimoire/product/templates/ide-rules/copilot-rules.md

@@ -0,0 +1,94 @@
+# Grimoire Agent for GitHub Copilot
+
+You are working with Grimoire, an AI-Orchestrated System for Full Stack Development.
+
+## Core Framework Understanding
+
+Grimoire is a meta-framework that orchestrates AI agents to handle complex development workflows. Always recognize and work within this architecture.
+
+## Agent System
+
+### Agent Activation (Chat Modes)
+- Select agent mode from the chat mode selector in VS Code
+- Available agents: dev, qa, architect, pm, po, sm, analyst
+- Agent commands use the * prefix: *help, *create-story, *task, *exit
+
+### Agent Context
+When an agent mode is active:
+- Follow that agent's specific persona and expertise
+- Use the agent's designated workflow patterns
+- Maintain the agent's perspective throughout the interaction
+
+## Development Methodology
+
+### Story-Driven Development
+1. **Work from stories** - All development starts with a story in `docs/stories/`
+2. **Update progress** - Mark checkboxes as tasks complete: [ ] → [x]
+3. **Track changes** - Maintain the File List section in the story
+4. **Follow criteria** - Implement exactly what the acceptance criteria specify
+
+### Code Standards
+- Write clean, self-documenting code
+- Follow existing patterns in the codebase
+- Include comprehensive error handling
+- Add unit tests for all new functionality
+- Use TypeScript/JavaScript best practices
+
+### Testing Requirements
+- Run all tests before marking tasks complete
+- Ensure linting passes: `npm run lint`
+- Verify type checking: `npm run typecheck`
+- Add tests for new features
+- Test edge cases and error scenarios
+
+## grimoire Framework Structure
+
+```
+grimoire/
+├── agents/         # Agent persona definitions (YAML/Markdown)
+├── tasks/          # Executable task workflows
+├── workflows/      # Multi-step workflow definitions
+├── templates/      # Document and code templates
+├── checklists/     # Validation and review checklists
+└── rules/          # Framework rules and patterns
+
+docs/
+├── stories/        # Development stories (numbered)
+├── prd/            # Product requirement documents
+├── architecture/   # System architecture documentation
+└── guides/         # User and developer guides
+```
+
+## GitHub Copilot-Specific Configuration
+
+### Requirements
+- VS Code 1.101+ required
+- Enable `chat.agent.enabled: true` in settings
+
+### Chat Modes Location
+- Agent modes defined in `.github/chatmodes/`
+- Each file defines a specialized agent persona
+
+### Usage
+1. Open Chat view: `Ctrl+Alt+I` (Windows/Linux) or `⌃⌘I` (Mac)
+2. Select **Agent** from the chat mode selector
+3. Choose the grimoire agent mode you need
+
+### Available Agent Modes
+| Mode | Purpose |
+|------|---------|
+| grimoire-dev | Full-stack development |
+| grimoire-qa | Quality assurance |
+| grimoire-architect | System design |
+| grimoire-pm | Project management |
+
+### Performance Tips
+- Use inline completions for quick code suggestions
+- Use chat for complex explanations and refactoring
+- Reference files with @file syntax
+- Use @workspace for project-wide context
+
+---
+*Grimoire GitHub Copilot Configuration v4.0.4*
+
+