docs: update OpenAgent documentation and add repository validation

- Update OpenAgent docs with universal agent philosophy
- Change delegation criteria from 3+ to 4+ files
- Emphasize critical rules (approval gate, stop on failure, confirm cleanup)
- Create essential-patterns.md context file
- Add 11 context files to registry (standards/*, workflows/*)
- Create /validate-repo command for consistency checking
- Update all profile component counts (developer: 30, full: 36, advanced: 43)
- Ensure CLI compatibility with context file structure

.opencode/command/validate-repo.md

@@ -0,0 +1,347 @@
+# Validate Repository
+
+Comprehensive validation command that checks the entire OpenAgents repository for consistency between CLI, documentation, registry, and components.
+
+## Usage
+
+```bash
+/validate-repo
+```
+
+## What It Checks
+
+This command performs a comprehensive validation of:
+
+1. **Registry Integrity**
+   - JSON syntax validation
+   - Component definitions completeness
+   - File path references
+   - Dependency declarations
+
+2. **Component Existence**
+   - All agents exist at specified paths
+   - All subagents exist at specified paths
+   - All commands exist at specified paths
+   - All tools exist at specified paths
+   - All plugins exist at specified paths
+   - All context files exist at specified paths
+   - All config files exist at specified paths
+
+3. **Profile Consistency**
+   - Component counts match documentation
+   - Profile descriptions are accurate
+   - Dependencies are satisfied
+   - No duplicate components
+
+4. **Documentation Accuracy**
+   - README component counts match registry
+   - OpenAgent documentation references are valid
+   - Context file references are correct
+   - Installation guide is up to date
+
+5. **Context File Structure**
+   - All referenced context files exist
+   - Context file organization is correct
+   - No orphaned context files
+
+6. **Cross-References**
+   - Agent dependencies exist
+   - Subagent references are valid
+   - Command references are valid
+   - Tool dependencies are satisfied
+
+## Output
+
+The command generates a detailed report showing:
+- ✅ What's correct and validated
+- ⚠️ Warnings for potential issues
+- ❌ Errors that need fixing
+- 📊 Summary statistics
+
+## Instructions
+
+You are a validation specialist. Your task is to comprehensively validate the OpenAgents repository for consistency and correctness.
+
+### Step 1: Validate Registry JSON
+
+1. Read and parse `registry.json`
+2. Validate JSON syntax
+3. Check schema structure:
+   - `version` field exists
+   - `repository` field exists
+   - `categories` object exists
+   - `components` object exists with all types
+   - `profiles` object exists
+   - `metadata` object exists
+
+### Step 2: Validate Component Definitions
+
+For each component type (agents, subagents, commands, tools, plugins, contexts, config):
+
+1. Check required fields:
+   - `id` (unique)
+   - `name`
+   - `type`
+   - `path`
+   - `description`
+   - `tags` (array)
+   - `dependencies` (array)
+   - `category`
+
+2. Verify file exists at `path`
+3. Check for duplicate IDs
+4. Validate category is in defined categories
+
+### Step 3: Validate Profiles
+
+For each profile (essential, developer, business, full, advanced):
+
+1. Count components in profile
+2. Verify all component references exist in components section
+3. Check dependencies are satisfied
+4. Validate no duplicate components
+
+### Step 4: Cross-Reference with Documentation
+
+1. **README.md**:
+   - Extract component counts from profile descriptions
+   - Compare with actual registry counts
+   - Check profile descriptions match registry descriptions
+
+2. **docs/agents/openagent.md**:
+   - Verify delegation criteria mentioned
+   - Check context file references
+   - Validate workflow descriptions
+
+3. **docs/getting-started/installation.md**:
+   - Check profile descriptions
+   - Verify installation commands
+
+### Step 5: Validate Context File Structure
+
+1. List all files in `.opencode/context/`
+2. Check against registry context entries
+3. Identify orphaned files (exist but not in registry)
+4. Identify missing files (in registry but don't exist)
+5. Validate structure:
+   - `core/standards/` files
+   - `core/workflows/` files
+   - `core/system/` files
+   - `project/` files
+
+### Step 6: Validate Dependencies
+
+For each component with dependencies:
+
+1. Parse dependency string (format: `type:id`)
+2. Verify referenced component exists
+3. Check for circular dependencies
+4. Validate dependency chain completeness
+
+### Step 7: Generate Report
+
+Create a comprehensive report with sections:
+
+#### ✅ Validated Successfully
+- Registry JSON syntax
+- Component file existence
+- Profile integrity
+- Documentation accuracy
+- Context file structure
+- Dependency chains
+
+#### ⚠️ Warnings
+- Orphaned files (exist but not referenced)
+- Unused components (defined but not in any profile)
+- Missing descriptions or tags
+- Outdated metadata dates
+
+#### ❌ Errors
+- Missing files
+- Broken dependencies
+- Invalid JSON
+- Component count mismatches
+- Broken documentation references
+- Duplicate component IDs
+
+#### 📊 Statistics
+- Total components: X
+- Total profiles: X
+- Total context files: X
+- Components per profile breakdown
+- File coverage percentage
+
+### Step 8: Provide Recommendations
+
+Based on findings, suggest:
+- Files to create
+- Registry entries to add/remove
+- Documentation to update
+- Dependencies to fix
+
+## Example Report Format
+
+```markdown
+# OpenAgents Repository Validation Report
+
+Generated: 2025-11-19 14:30:00
+
+## Summary
+
+✅ 95% validation passed
+⚠️ 3 warnings found
+❌ 2 errors found
+
+---
+
+## ✅ Validated Successfully
+
+### Registry Integrity
+✅ JSON syntax valid
+✅ All required fields present
+✅ Schema structure correct
+
+### Component Existence (45/47 files found)
+✅ Agents: 3/3 files exist
+✅ Subagents: 15/15 files exist
+✅ Commands: 8/8 files exist
+✅ Tools: 2/2 files exist
+✅ Plugins: 2/2 files exist
+✅ Contexts: 13/15 files exist
+✅ Config: 2/2 files exist
+
+### Profile Consistency
+✅ Essential: 9 components (matches README)
+✅ Developer: 29 components (matches README)
+✅ Business: 15 components (matches README)
+✅ Full: 35 components (matches README)
+✅ Advanced: 42 components (matches README)
+
+### Documentation Accuracy
+✅ README component counts match registry
+✅ OpenAgent documentation up to date
+✅ Installation guide accurate
+
+---
+
+## ⚠️ Warnings (3)
+
+1. **Orphaned Context File**
+   - File: `.opencode/context/legacy/old-patterns.md`
+   - Issue: Exists but not referenced in registry
+   - Recommendation: Add to registry or remove file
+
+2. **Unused Component**
+   - Component: `workflow-orchestrator` (agent)
+   - Issue: Defined in registry but not in any profile
+   - Recommendation: Add to a profile or mark as deprecated
+
+3. **Outdated Metadata**
+   - Field: `metadata.lastUpdated`
+   - Current: 2025-11-15
+   - Recommendation: Update to current date
+
+---
+
+## ❌ Errors (2)
+
+1. **Missing Context File**
+   - Component: `context:advanced-patterns`
+   - Expected path: `.opencode/context/core/advanced-patterns.md`
+   - Referenced in: developer, full, advanced profiles
+   - Action: Create file or remove from registry
+
+2. **Broken Dependency**
+   - Component: `agent:codebase-agent`
+   - Dependency: `subagent:pattern-matcher`
+   - Issue: Dependency not found in registry
+   - Action: Add missing subagent or fix dependency reference
+
+---
+
+## 📊 Statistics
+
+### Component Distribution
+- Agents: 3
+- Subagents: 15
+- Commands: 8
+- Tools: 2
+- Plugins: 2
+- Contexts: 15
+- Config: 2
+- **Total: 47 components**
+
+### Profile Breakdown
+- Essential: 9 components (19%)
+- Developer: 29 components (62%)
+- Business: 15 components (32%)
+- Full: 35 components (74%)
+- Advanced: 42 components (89%)
+
+### File Coverage
+- Total files defined: 47
+- Files found: 45 (96%)
+- Files missing: 2 (4%)
+- Orphaned files: 1
+
+### Dependency Health
+- Total dependencies: 23
+- Valid dependencies: 22 (96%)
+- Broken dependencies: 1 (4%)
+- Circular dependencies: 0
+
+---
+
+## 🔧 Recommended Actions
+
+### High Priority (Errors)
+1. Create missing file: `.opencode/context/core/advanced-patterns.md`
+2. Fix broken dependency in `codebase-agent`
+
+### Medium Priority (Warnings)
+1. Remove orphaned file or add to registry
+2. Add `workflow-orchestrator` to a profile or deprecate
+3. Update metadata.lastUpdated to 2025-11-19
+
+### Low Priority (Improvements)
+1. Add more tags to components for better searchability
+2. Consider adding descriptions to all context files
+3. Document component categories in README
+
+---
+
+## Next Steps
+
+1. Review and fix all ❌ errors
+2. Address ⚠️ warnings as needed
+3. Re-run validation to confirm fixes
+4. Update documentation if needed
+
+---
+
+**Validation Complete** ✓
+```
+
+## Implementation Notes
+
+The command should:
+- Use bash/python for file system operations
+- Parse JSON with proper error handling
+- Generate markdown report
+- Be non-destructive (read-only validation)
+- Provide actionable recommendations
+- Support verbose mode for detailed output
+
+## Error Handling
+
+- Gracefully handle missing files
+- Continue validation even if errors found
+- Collect all issues before reporting
+- Provide clear error messages with context
+
+## Performance
+
+- Should complete in < 30 seconds
+- Cache file reads where possible
+- Parallel validation where safe
+- Progress indicators for long operations

.opencode/context/core/essential-patterns.md

@@ -0,0 +1,208 @@
+# Essential Patterns - Core Development Guidelines
+
+## Quick Reference
+
+**Core Philosophy**: Modular, Functional, Maintainable
+
+**Critical Patterns**: Error Handling, Validation, Security, Logging, Pure Functions
+
+**ALWAYS**: Handle errors gracefully, validate input, use env vars for secrets, write pure functions
+
+**NEVER**: Expose sensitive info, hardcode credentials, skip input validation, mutate state
+
+**Language-agnostic**: Apply to all programming languages
+
+---
+
+## Overview
+
+This file provides essential development patterns that apply across all programming languages. For detailed standards, see:
+- `standards/code.md` - Modular, functional code patterns
+- `standards/patterns.md` - Language-agnostic patterns
+- `standards/tests.md` - Testing standards
+- `standards/docs.md` - Documentation standards
+- `standards/analysis.md` - Analysis framework
+
+---
+
+## Core Philosophy
+
+**Modular**: Everything is a component - small, focused, reusable
+**Functional**: Pure functions, immutability, composition over inheritance
+**Maintainable**: Self-documenting, testable, predictable
+
+---
+
+## Critical Patterns
+
+### 1. Pure Functions
+
+**ALWAYS** write pure functions:
+- Same input = same output
+- No side effects
+- No mutation of external state
+- Predictable and testable
+
+### 2. Error Handling
+
+**ALWAYS** handle errors gracefully:
+- Catch specific errors, not generic ones
+- Log errors with context
+- Return meaningful error messages
+- Don't expose internal implementation details
+- Use language-specific error handling mechanisms (try/catch, Result, error returns)
+
+### 3. Input Validation
+
+**ALWAYS** validate input data:
+- Check for null/nil/None values
+- Validate data types
+- Validate data ranges and constraints
+- Sanitize user input
+- Return clear validation error messages
+
+### 4. Security
+
+**NEVER** expose sensitive information:
+- Don't log passwords, tokens, or API keys
+- Use environment variables for secrets
+- Sanitize all user input
+- Use parameterized queries (prevent SQL injection)
+- Validate and escape output (prevent XSS)
+
+### 5. Logging
+
+**USE** consistent logging levels:
+- **Debug**: Detailed information for debugging (development only)
+- **Info**: Important events and milestones
+- **Warning**: Potential issues that don't stop execution
+- **Error**: Failures and exceptions
+
+---
+
+## Code Structure Patterns
+
+### Modular Design
+- Single responsibility per module
+- Clear interfaces (explicit inputs/outputs)
+- Independent and composable
+- < 100 lines per component (ideally < 50)
+
+### Functional Approach
+- **Pure functions**: Same input = same output, no side effects
+- **Immutability**: Create new data, don't modify existing
+- **Composition**: Build complex from simple functions
+- **Declarative**: Describe what, not how
+
+### Component Structure
+```
+component/
+├── index.js      # Public interface
+├── core.js       # Core logic (pure functions)
+├── utils.js      # Helpers
+└── tests/        # Tests
+```
+
+---
+
+## Anti-Patterns to Avoid
+
+**Code Smells**:
+- ❌ Mutation and side effects
+- ❌ Deep nesting (> 3 levels)
+- ❌ God modules (> 200 lines)
+- ❌ Global state
+- ❌ Large functions (> 50 lines)
+- ❌ Hardcoded values
+- ❌ Tight coupling
+
+**Security Issues**:
+- ❌ Hardcoded credentials
+- ❌ Exposed sensitive data in logs
+- ❌ Unvalidated user input
+- ❌ SQL injection vulnerabilities
+- ❌ XSS vulnerabilities
+
+---
+
+## Testing Patterns
+
+**ALWAYS** write tests:
+- Unit tests for pure functions
+- Integration tests for components
+- Test edge cases and error conditions
+- Aim for > 80% coverage
+- Use descriptive test names
+
+**Test Structure**:
+```
+describe('Component', () => {
+  it('should handle valid input', () => {
+    // Arrange
+    const input = validData;
+    
+    // Act
+    const result = component(input);
+    
+    // Assert
+    expect(result).toBe(expected);
+  });
+  
+  it('should handle invalid input', () => {
+    // Test error cases
+  });
+});
+```
+
+---
+
+## Documentation Patterns
+
+**ALWAYS** document:
+- Public APIs and interfaces
+- Complex logic and algorithms
+- Non-obvious decisions
+- Usage examples
+
+**Use clear, concise language**:
+- Explain WHY, not just WHAT
+- Include examples
+- Keep it up to date
+- Use consistent formatting
+
+---
+
+## Language-Specific Implementations
+
+These patterns are language-agnostic. For language-specific implementations:
+
+**TypeScript/JavaScript**: See project context for Next.js, React, Node.js patterns
+**Python**: See project context for FastAPI, Django patterns
+**Go**: See project context for Go-specific patterns
+**Rust**: See project context for Rust-specific patterns
+
+---
+
+## Quick Checklist
+
+Before committing code, verify:
+- ✅ Pure functions (no side effects)
+- ✅ Input validation
+- ✅ Error handling
+- ✅ No hardcoded secrets
+- ✅ Tests written and passing
+- ✅ Documentation updated
+- ✅ No security vulnerabilities
+- ✅ Code is modular and maintainable
+
+---
+
+## Additional Resources
+
+For more detailed guidelines, see:
+- `standards/code.md` - Comprehensive code standards
+- `standards/patterns.md` - Detailed pattern catalog
+- `standards/tests.md` - Testing best practices
+- `standards/docs.md` - Documentation guidelines
+- `standards/analysis.md` - Code analysis framework
+- `workflows/review.md` - Code review process

README.md

@@ -231,6 +231,7 @@ openagent (universal coordinator)
 - **/context** - Context management
 - **/prompt-enchancer** - Improve your prompts
 - **/worktrees** - Git worktree management
+- **/validate-repo** - Validate repository consistency
 
 ### 📚 Context Files
 - `core/essential-patterns.md` - Universal coding patterns
@@ -423,12 +424,13 @@ Minimal starter kit - universal agent with core subagents.
 - **Config**: env-example
 - **Best for**: Learning the system, lightweight tasks, minimal setup
 
-### 💼 Developer (Recommended - 19 components)
+### 💼 Developer (Recommended - 30 components)
 Complete software development environment with code generation, testing, review, and build tools.
 - Everything in Essential, plus:
 - **Agents**: codebase-agent
 - **Subagents**: coder-agent, reviewer, tester, build-agent, codebase-pattern-analyst
-- **Commands**: commit, test, optimize
+- **Commands**: commit, test, optimize, validate-repo
+- **Context**: All standards and workflow files (code, patterns, tests, docs, analysis, delegation, sessions, task-breakdown, review, context-guide)
 - **Config**: readme
 - **Best for**: Most developers, daily use, full-featured development
 
@@ -443,13 +445,13 @@ Business process automation, content creation, and visual workflows.
 - **Config**: env-example, readme
 - **Best for**: Business automation, content creation, non-developers
 
-### 📦 Full (25 components)
+### 📦 Full (36 components)
 Everything included - all agents, subagents, tools, and plugins.
 - Everything in Developer and Business combined, plus:
-- **Commands**: worktrees (git worktree management)
+- **Commands**: worktrees (git worktree management), validate-repo
 - **Best for**: Power users, exploring all features
 
-### 🚀 Advanced (32 components)
+### 🚀 Advanced (43 components)
 Full installation plus **System Builder** for creating custom AI architectures.
 - Everything in Full, plus:
 - **System Builder**: Interactive AI system generator

docs/agents/openagent.md

@@ -26,7 +26,7 @@ OpenAgent is your **universal assistant** that:
 
 - ✅ **Answers questions** - Get explanations, comparisons, and guidance
 - ✅ **Executes tasks** - Create files, update code, run commands
-- ✅ **Coordinates workflows** - Breaks down complex features and delegates to specialists
+- ✅ **Coordinates workflows** - Handles most tasks directly, delegates to specialists when needed
 - ✅ **Preserves context** - Remembers information across multiple steps
 - ✅ **Keeps you in control** - Always asks for approval before taking action
 
@@ -34,7 +34,7 @@ Think of OpenAgent as a **smart project manager** who:
 - Understands what you need
 - Plans how to do it
 - Asks for your approval
-- Executes the plan
+- Executes the plan (directly or via delegation)
 - Confirms everything is done right
 
 ---
@@ -64,6 +64,18 @@ graph LR
 **For Questions**: You ask → You get an answer
 **For Tasks**: You ask → See plan → Approve → Watch it happen → Confirm done
 
+### Universal Agent Philosophy
+
+OpenAgent is a **universal agent** - it handles most tasks directly:
+
+**Capabilities**: Write code, docs, tests, reviews, analysis, debugging, research, bash operations, file operations
+
+**Default**: Execute directly, fetch context files as needed (lazy), keep it simple, don't over-delegate
+
+**Delegate only when**: 4+ files, specialized expertise needed, thorough multi-component review, complex dependencies, or user requests breakdown
+
+This means OpenAgent is your go-to agent for almost everything. It only calls in specialists when truly necessary.
+
 ---
 
 ## The Two Paths
@@ -234,7 +246,7 @@ graph TD
 
 ---
 
-### Stage 2: Approve ⚠️ (MANDATORY for tasks)
+### Stage 2: Approve ⚠️ (MANDATORY - CRITICAL RULE)
 
 ```mermaid
 graph TD
@@ -262,6 +274,8 @@ graph TD
 
 **What happens**: OpenAgent creates a plan and shows it to you.
 
+**Critical Rule**: OpenAgent **ALWAYS** requests approval before **ANY** execution (bash, write, edit, task delegation). This is absolute and strictly enforced. Read and list operations do not require approval.
+
 **Your experience**: You see something like:
 ```
 ## Proposed Plan
@@ -327,7 +341,7 @@ graph TD
 
 ---
 
-### Stage 4: Validate ⚠️ (MANDATORY for tasks)
+### Stage 4: Validate ⚠️ (MANDATORY - CRITICAL RULE)
 
 ```mermaid
 graph TD
@@ -379,6 +393,11 @@ graph TD
 
 **What happens**: OpenAgent checks the quality of the work, runs tests if applicable, and ensures everything works correctly.
 
+**Critical Rules Enforced**:
+1. **STOP on failure** - Immediately stops execution when tests fail or errors occur
+2. **REPORT first** - Always reports issues before proposing fixes
+3. **NEVER auto-fix** - Always requests approval before fixing issues
+
 **Your experience when validation passes**: You see:
 ```
 ✅ Validation complete - all checks passed.
@@ -394,13 +413,13 @@ Would you like me to run any additional checks or review the work before I summa
 
 #### Special Case: Test Failures or Issues Found
 
-If OpenAgent runs tests or validation and finds issues, it follows a **strict protocol**:
+If OpenAgent runs tests or validation and finds issues, it follows a **strict protocol** (Critical Rule):
 
 **What happens**:
-1. ⛔ **STOPS** execution immediately
+1. ⛔ **STOPS** execution immediately (no auto-fix)
 2. 📋 **REPORTS** all issues/failures clearly
 3. 📝 **PROPOSES** a fix plan with specific steps
-4. ⚠️ **REQUESTS APPROVAL** before fixing (mandatory)
+4. ⚠️ **REQUESTS APPROVAL** before fixing (absolute requirement)
 5. ✅ **PROCEEDS** only after you approve
 6. 🔄 **RE-VALIDATES** after fixes are applied
 
@@ -420,7 +439,7 @@ If OpenAgent runs tests or validation and finds issues, it follows a **strict pr
 **Approval needed before proceeding with fixes.**
 ```
 
-**Important**: OpenAgent will **NEVER** auto-fix issues without your explicit approval. After fixes are applied, validation runs again to ensure everything passes.
+**Critical**: OpenAgent will **NEVER** auto-fix issues without your explicit approval. This is an absolute rule with strict enforcement. After fixes are applied, validation runs again to ensure everything passes.
 
 ---
 
@@ -470,7 +489,7 @@ Created README.md with project documentation.
 
 ---
 
-### Stage 6: Confirm Completion ⚠️ (MANDATORY for tasks)
+### Stage 6: Confirm Completion ⚠️ (MANDATORY - CRITICAL RULE)
 
 ```mermaid
 graph TD
@@ -508,6 +527,8 @@ graph TD
 
 **What happens**: OpenAgent asks if you're satisfied and if temporary files should be cleaned up.
 
+**Critical Rule**: OpenAgent **ALWAYS** confirms before deleting session files or cleanup operations. This is absolute and strictly enforced.
+
 **Your experience**: You see:
 ```
 Is this complete and satisfactory?
@@ -584,11 +605,11 @@ sequenceDiagram
 
 ### Key Features
 
-**Lazy Initialization**: Sessions are only created when actually needed (not for simple tasks).
+**Lazy Initialization**: Sessions are only created when actually needed (not for simple tasks). OpenAgent follows a "lazy" philosophy - only creates sessions/files when truly necessary.
 
 **Unique IDs**: Each session gets a unique ID like `20250118-143022-a4f2` to prevent conflicts.
 
-**Safe Cleanup**: OpenAgent only deletes files it created, and only after you approve.
+**Safe Cleanup**: OpenAgent only deletes files it created, and only after you approve (Critical Rule).
 
 **Concurrent Safety**: Multiple users can work simultaneously without interfering with each other.
 
@@ -677,7 +698,22 @@ The manifest is like an **index** that tracks all context files:
 
 ## When OpenAgent Delegates
 
-OpenAgent knows when to do work itself and when to call in specialists.
+OpenAgent is a **universal agent** that handles most tasks directly. It only delegates when truly needed.
+
+### Execution Philosophy
+
+**OpenAgent's Capabilities**: Write code, docs, tests, reviews, analysis, debugging, research, bash operations, file operations
+
+**Default Approach**: Execute directly, fetch context files as needed (lazy loading), keep it simple
+
+**Delegate Only When**:
+- 4+ files to modify/create
+- Specialized expertise needed (security, algorithms, architecture, performance)
+- Thorough multi-component review required
+- Complex dependencies and coordination
+- Need fresh perspective or alternative approaches
+- Testing scenarios, edge cases, what-if analysis
+- User explicitly requests breakdown/delegation
 
 ### Decision Tree
 
@@ -689,17 +725,20 @@ graph TD
     
     B -->|Task| D{How complex?}
     
-    D -->|3+ files OR 60+ min OR complex| E[Delegate to task-manager]
+    D -->|4+ files OR specialized expertise| E[Delegate to task-manager]
     E --> E1[Breaks down into subtasks]
     
     D -->|Comprehensive docs OR multi-page| F[Delegate to documentation]
     F --> F1[Creates structured docs]
     
-    D -->|Specialized code task| G[Delegate to code specialists]
+    D -->|Need perspective OR simulation| G[Delegate to general agent]
-    G --> G1[Testing, review, build]
+    G --> G1[Fresh eyes, alternatives, testing]
     
-    D -->|Simple OR single file OR under 30 min| H[Execute Directly]
+    D -->|Specialized code task| H[Delegate to code specialists]
-    H --> H1[OpenAgent handles it]
+    H --> H1[Testing, review, build]
+    
+    D -->|Simple OR 1-3 files OR straightforward| I[Execute Directly]
+    I --> I1[OpenAgent handles it]
     
     style A fill:#4A90E2,stroke:#2E5C8A,stroke-width:3px,color:#fff
     style B fill:#F5A623,stroke:#C17D11,stroke-width:3px,color:#000
@@ -708,19 +747,19 @@ graph TD
     style E fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style F fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
     style G fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
-    style H fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
+    style H fill:#6B7C93,stroke:#4A5568,stroke-width:3px,color:#fff
+    style I fill:#7ED321,stroke:#5FA319,stroke-width:3px,color:#000
 ```
 
 ### Delegation Criteria
 
 #### Delegate to @task-manager when:
-- ✅ Feature spans **3+ files/modules**
+- ✅ Feature spans **4+ files/modules**
-- ✅ Estimated effort **>60 minutes**
-- ✅ Needs **breakdown into subtasks**
 - ✅ **Complex dependencies** between components
+- ✅ Needs **breakdown into subtasks**
 - ✅ User **explicitly requests** task breakdown
 
-**Example**: "Build user authentication system"
+**Example**: "Build user authentication system with 5+ components"
 
 ---
 
@@ -734,8 +773,22 @@ graph TD
 
 ---
 
+#### Delegate to @general agent when:
+- ✅ Need **fresh perspective** or alternative approaches
+- ✅ **Simulation** of scenarios, edge cases, what-if analysis
+- ✅ **Brainstorming** different solutions
+- ✅ **Complex research** requiring multiple rounds of search
+
+**Examples**:
+- "Review this API design - what could go wrong?" → Fresh perspective
+- "Simulate edge cases for this algorithm" → Testing scenarios
+- "What are alternative approaches to solve X?" → Brainstorming
+
+---
+
 #### Delegate to @code/* when:
-- ✅ **Code-specific specialized task** (testing, review, build)
+- ✅ **Specialized code task** (testing, review, build)
+- ✅ **Thorough review** across multiple components
 - ✅ Code subagents are **available** in current profile
 
 **Examples**:
@@ -746,15 +799,16 @@ graph TD
 ---
 
 #### Execute directly when:
-- ✅ **Single file** operation
+- ✅ **1-3 files** to modify/create
-- ✅ **Simple, straightforward** task (<30 min)
+- ✅ **Straightforward** task with clear implementation
 - ✅ **Quick updates/edits**
 - ✅ User **explicitly asks** openagent to handle it
 
 **Examples**:
 - "Create a README"
+- "Fix this bug in auth.ts"
+- "Add input validation to this function"
 - "Update this function to use async/await"
-- "Add a comment to this code"
 
 ---
 
@@ -956,11 +1010,11 @@ When making follow-up requests, reference previous work:
 You can adjust when OpenAgent delegates by modifying the criteria in `.opencode/agent/openagent.md`:
 
 **Current defaults**:
-- 3+ files → Delegate to task-manager
+- 4+ files → Delegate to task-manager
-- >60 minutes → Delegate to task-manager
+- Specialized expertise needed → Delegate to appropriate specialist
-- <30 minutes → Execute directly
+- 1-3 files → Execute directly
 
-**To customize**: Edit the `<delegation_criteria>` section to match your preferences.
+**To customize**: Edit the `<delegation_rules>` section to match your preferences.
 
 ---
 
@@ -1090,41 +1144,48 @@ Concise responses, no over-explanation. Gets to the point quickly.
 Conversational for questions, formal for tasks. Matches the context.
 
 ### ⚡ Lazy
-Only creates sessions/files when actually needed. No unnecessary overhead.
+Only creates sessions/files when actually needed. No unnecessary overhead. Fetches context files on-demand.
 
-### 🔒 Safe
+### 🔒 Safe (CRITICAL RULE - Absolute & Strict)
-**ALWAYS** requests approval before ANY execution. Confirms before cleanup.
+**ALWAYS** requests approval before ANY execution (bash, write, edit, task delegation). Confirms before cleanup. This is an absolute rule with strict enforcement.
 
-### 📋 Report First
+### 📋 Report First (CRITICAL RULE - Absolute & Strict)
 When tests fail or issues are found:
-1. **REPORT** the issues
+1. **STOP** immediately (no auto-fix)
-2. **PLAN** the fixes
+2. **REPORT** the issues clearly
-3. **REQUEST APPROVAL**
+3. **PROPOSE** fix plan
-4. **FIX** (only after approval)
+4. **REQUEST APPROVAL** (mandatory)
+5. **FIX** (only after approval)
 
-**Never auto-fixes** - you're always in control.
+**Never auto-fixes** - you're always in control. This is an absolute rule with strict enforcement.
+
+### 🛡️ Critical Rules Summary
+Three critical rules are enforced with absolute priority:
+1. **Approval Gate** - Always request approval before execution
+2. **Stop on Failure** - Stop immediately on test failures or errors, never auto-fix
+3. **Confirm Cleanup** - Always confirm before deleting session files
 
 ---
 
 ## Summary
 
-OpenAgent is your **intelligent project manager** that:
+OpenAgent is your **intelligent universal agent** that:
 
-✅ **Plans before acting** - Shows you the plan and waits for approval
+✅ **Plans before acting** - Shows you the plan and waits for approval (Critical Rule)
 ✅ **Preserves context** - Remembers information across multiple steps
-✅ **Delegates wisely** - Calls in specialists when needed
+✅ **Executes directly** - Handles most tasks itself, delegates only when needed
-✅ **Keeps you in control** - Always confirms before cleanup
+✅ **Keeps you in control** - Always confirms before cleanup (Critical Rule)
-✅ **Handles complexity** - Breaks down big tasks into manageable pieces
+✅ **Handles complexity** - Capable of code, docs, tests, reviews, analysis, debugging
-✅ **Reports before fixing** - Never auto-fixes issues without approval
+✅ **Reports before fixing** - Never auto-fixes issues without approval (Critical Rule)
 
 **Key Takeaways**:
 1. Be specific in your requests
 2. Review plans before approving
 3. Use multi-step workflows for complex projects
-4. Let OpenAgent delegate to specialists
+4. OpenAgent handles most tasks directly - delegation is the exception, not the rule
 5. Clean up sessions when done
 6. Customize to fit your workflow
-7. Expect reports before fixes when issues are found
+7. Expect reports before fixes when issues are found (never auto-fix)
 
 **Ready to get started?** Just ask OpenAgent a question or request a task!
 
@@ -1133,32 +1194,48 @@ OpenAgent is your **intelligent project manager** that:
 ## Configuration
 
 OpenAgent is configured in `.opencode/agent/openagent.md`. You can customize:
-- Delegation thresholds
+- Delegation thresholds (when to delegate vs execute directly)
-- Categories
+- Execution philosophy (universal agent approach)
-- Error handling
+- Critical rules enforcement
-- Test failure protocol
+- Workflow stages
+- Context loading behavior
 - And more!
 
-### Recent Optimizations (Nov 2025)
+### Architecture & Design (Nov 2025)
 
 OpenAgent has been optimized based on research-backed prompt engineering patterns:
 
-✅ **Critical rules positioned early** - Safety rules now appear in the first 15% of the prompt (10.7% position)
+✅ **Critical rules positioned early** - Safety rules appear in the first 15% of the prompt with absolute priority
-✅ **Minimal nesting complexity** - Flattened XML structure to only 2 levels for maximum clarity
+✅ **Minimal nesting complexity** - Flattened XML structure (max 2 levels) for maximum clarity
-✅ **Modular design** - Session management and context discovery extracted to reference files
+✅ **Modular design** - Context files loaded on-demand (lazy loading)
-✅ **Explicit prioritization** - 3-tier priority system for conflict resolution
+✅ **Explicit prioritization** - 3-tier priority system with conflict resolution
 ✅ **Single source of truth** - Critical rules defined once and referenced throughout
+✅ **Universal agent philosophy** - Execute directly first, delegate only when truly needed
+
+**Key Principles**:
+- **Tier 1 (Highest)**: Safety & Approval Gates - Always override other tiers
+- **Tier 2**: Core Workflow - Stage progression and delegation routing
+- **Tier 3**: Optimization - Lazy initialization, session management, context discovery
 
 **Effectiveness improvements are model- and task-specific.** These patterns are validated by Stanford/Anthropic research but actual performance gains vary based on your specific use case.
 
-### Required Context Files
+### Static Context Files
 
-OpenAgent requires these context files to function properly:
+OpenAgent uses context files from `.opencode/context/core/` on-demand (lazy loading):
-- `.opencode/context/core/session-management.md` - Session lifecycle and cleanup policies
-- `.opencode/context/core/context-discovery.md` - Dynamic context loading and discovery
-- `.opencode/context/core/context-management.md` - Overall context management strategy
-- `.opencode/context/core/essential-patterns.md` - Core coding patterns and best practices
 
-These files are automatically loaded when OpenAgent starts.
+**Standards** (quality guidelines):
+- `standards/code.md` - Modular, functional code patterns
+- `standards/docs.md` - Documentation standards
+- `standards/tests.md` - Testing standards
+- `standards/patterns.md` - Core patterns
+- `standards/analysis.md` - Analysis framework
+
+**Workflows** (process templates):
+- `workflows/delegation.md` - Delegation template and process
+- `workflows/task-breakdown.md` - Task breakdown methodology
+- `workflows/sessions.md` - Session lifecycle management
+- `workflows/review.md` - Code review guidelines
+
+These files are fetched only when needed, keeping the system lean and efficient. OpenAgent references them without the `@` symbol (e.g., `standards/code.md` not `@standards/code.md`).
 
 Happy building! 🚀

registry.json

@@ -371,6 +371,21 @@
           "agent:system-builder"
         ],
         "category": "meta"
+      },
+      {
+        "id": "validate-repo",
+        "name": "Validate Repository",
+        "type": "command",
+        "path": ".opencode/command/validate-repo.md",
+        "description": "Comprehensive validation of repository consistency between CLI, docs, registry, and components",
+        "tags": [
+          "validation",
+          "quality",
+          "consistency",
+          "maintenance"
+        ],
+        "dependencies": [],
+        "category": "standard"
       }
     ],
     "tools": [
@@ -464,6 +479,146 @@
         ],
         "dependencies": [],
         "category": "essential"
+      },
+      {
+        "id": "standards-code",
+        "name": "Code Standards",
+        "type": "context",
+        "path": ".opencode/context/core/standards/code.md",
+        "description": "Modular, functional code standards",
+        "tags": [
+          "standards",
+          "code",
+          "quality"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "standards-patterns",
+        "name": "Pattern Standards",
+        "type": "context",
+        "path": ".opencode/context/core/standards/patterns.md",
+        "description": "Language-agnostic pattern catalog",
+        "tags": [
+          "standards",
+          "patterns",
+          "architecture"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "standards-tests",
+        "name": "Testing Standards",
+        "type": "context",
+        "path": ".opencode/context/core/standards/tests.md",
+        "description": "Testing best practices and guidelines",
+        "tags": [
+          "standards",
+          "testing",
+          "quality"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "standards-docs",
+        "name": "Documentation Standards",
+        "type": "context",
+        "path": ".opencode/context/core/standards/docs.md",
+        "description": "Documentation guidelines and templates",
+        "tags": [
+          "standards",
+          "documentation",
+          "writing"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "standards-analysis",
+        "name": "Analysis Standards",
+        "type": "context",
+        "path": ".opencode/context/core/standards/analysis.md",
+        "description": "Code analysis framework and guidelines",
+        "tags": [
+          "standards",
+          "analysis",
+          "quality"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "workflows-delegation",
+        "name": "Delegation Workflow",
+        "type": "context",
+        "path": ".opencode/context/core/workflows/delegation.md",
+        "description": "Delegation template and process",
+        "tags": [
+          "workflows",
+          "delegation",
+          "coordination"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "workflows-sessions",
+        "name": "Session Management Workflow",
+        "type": "context",
+        "path": ".opencode/context/core/workflows/sessions.md",
+        "description": "Session lifecycle and management",
+        "tags": [
+          "workflows",
+          "sessions",
+          "management"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "workflows-task-breakdown",
+        "name": "Task Breakdown Workflow",
+        "type": "context",
+        "path": ".opencode/context/core/workflows/task-breakdown.md",
+        "description": "Task breakdown methodology",
+        "tags": [
+          "workflows",
+          "tasks",
+          "planning"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "workflows-review",
+        "name": "Code Review Workflow",
+        "type": "context",
+        "path": ".opencode/context/core/workflows/review.md",
+        "description": "Code review process and guidelines",
+        "tags": [
+          "workflows",
+          "review",
+          "quality"
+        ],
+        "dependencies": [],
+        "category": "standard"
+      },
+      {
+        "id": "system-context-guide",
+        "name": "Context System Guide",
+        "type": "context",
+        "path": ".opencode/context/core/system/context-guide.md",
+        "description": "Guide to the context system and file organization",
+        "tags": [
+          "system",
+          "guide",
+          "context"
+        ],
+        "dependencies": [],
+        "category": "standard"
       }
     ],
     "config": [
@@ -532,9 +687,20 @@
         "command:context",
         "command:clean",
         "command:optimize",
+        "command:validate-repo",
         "tool:env",
         "context:essential-patterns",
         "context:project-context",
+        "context:standards-code",
+        "context:standards-patterns",
+        "context:standards-tests",
+        "context:standards-docs",
+        "context:standards-analysis",
+        "context:workflows-delegation",
+        "context:workflows-sessions",
+        "context:workflows-task-breakdown",
+        "context:workflows-review",
+        "context:system-context-guide",
         "config:env-example",
         "config:readme"
       ]
@@ -581,12 +747,23 @@
         "command:optimize",
         "command:prompt-enhancer",
         "command:worktrees",
+        "command:validate-repo",
         "tool:env",
         "tool:gemini",
         "plugin:notify",
         "plugin:telegram-notify",
         "context:essential-patterns",
         "context:project-context",
+        "context:standards-code",
+        "context:standards-patterns",
+        "context:standards-tests",
+        "context:standards-docs",
+        "context:standards-analysis",
+        "context:workflows-delegation",
+        "context:workflows-sessions",
+        "context:workflows-task-breakdown",
+        "context:workflows-review",
+        "context:system-context-guide",
         "config:env-example",
         "config:readme"
       ]
@@ -619,12 +796,23 @@
         "command:prompt-enhancer",
         "command:worktrees",
         "command:build-context-system",
+        "command:validate-repo",
         "tool:env",
         "tool:gemini",
         "plugin:notify",
         "plugin:telegram-notify",
         "context:essential-patterns",
         "context:project-context",
+        "context:standards-code",
+        "context:standards-patterns",
+        "context:standards-tests",
+        "context:standards-docs",
+        "context:standards-analysis",
+        "context:workflows-delegation",
+        "context:workflows-sessions",
+        "context:workflows-task-breakdown",
+        "context:workflows-review",
+        "context:system-context-guide",
         "config:env-example",
         "config:readme"
       ],