Remove unnecessary and add specificity

Author: BekahHW

docs/hub/agents/create-and-edit.mdx

@@ -4,28 +4,30 @@ description: "Build custom AI workflows with prompts, rules, and tools through t
 sidebarTitle: "Create & Edit"
 ---
 
-<Card title="🧱 Creating Custom Agents" icon="wrench">
+<Card title="Creating Custom Agents" icon="wrench">
   You can only create and edit Agents through Mission Control in the Continue Hub web interface. 
   This ensures proper validation, versioning, and team collaboration features.
 </Card>
 
 ## Creating an Agent
 
+  ![Create an agent gif](/docs/images/hub/create-an-agent.gif)
+
+
 <Steps>
   <Step title="🧭 Navigate to Create Agent">
     From the Continue Hub top navigation bar, select **"+"** → **"New Agent"**.
 
     This opens the **Create an Agent (beta)** form with all required fields.
 
-    ![Create an agent screenshot](/docs/images/hub/create-an-agent.gif)
   </Step>
 
   <Step title="🧩 Fill Out the Agent Form">
     Configure your agent with the following fields:
 
     | Field | What to Enter | Example |
     |-------|---------------|---------|
-    | **Name** | Display name shown in the Hub | `Open PR with Fix` |
+    | **Name** | Display name shown in the Hub | `GitHub PR Agent` |
     | **Prompt** | First instruction the agent receives | `Open a GitHub PR to fix the specified issue.` |
     | **Description** | What the agent does | `Creates a pull request and includes AI-generated summaries.` |
     | **Tools (MCPs)** | Select built-in or custom MCPs | `GitHub, PostHog, Supabase` |
@@ -45,7 +47,7 @@ sidebarTitle: "Create & Edit"
     ```yaml
     name: Open PR with Fix
     description: Open a GitHub PR to fix the specified issue
-    tools: built_in
+    tools: built_in, anthropic/github-mcp
     rules:
       - continuedev/gh-pr-commit-workflow
       - continuedev/summarization
@@ -62,7 +64,7 @@ sidebarTitle: "Create & Edit"
     Your agent is immediately available to run in:
     - Mission Control web interface
     - TUI mode: `cn --agent your-org/your-agent-name`
-    - Headless mode: `cn --agent your-org/your-agent-name "prompt" --auto`
+    - Headless mode: `cn --agent -p your-org/your-agent-name "prompt" --auto`
   </Step>
 </Steps>
 
@@ -132,230 +134,49 @@ You can edit any agent you own or that belongs to your organization.
   </Step>
 </Steps>
 
-## Agent Components Deep Dive
+<Warning>
+  Test your agent thoroughly to ensure they interact as expected.
+</Warning>
 
-### Writing Effective Prompts
+## Example Agent Configurations
 
-Your prompt is the agent's primary instruction. Follow these patterns for best results:
+Here are proven agent patterns you can adapt:
 
-<AccordionGroup>
-  <Accordion title="Task-Oriented Prompts">
-    **Good**: Clear, actionable instructions
-    ```
-    Analyze the Sentry errors from the past 24 hours and create GitHub issues 
-    for any critical bugs with suggested fixes and reproduction steps.
-    ```
-    
-    **Avoid**: Vague or open-ended requests  
-    ```
-    Look at errors and do something about them.
-    ```
-  </Accordion>
+Here are proven agent configurations you can create or use as inspiration:
 
-  <Accordion title="Context-Aware Prompts">
-    **Good**: Include relevant context and constraints
-    ```
-    Review the React components in src/components/ for accessibility issues.
-    Focus on ARIA labels, keyboard navigation, and color contrast.
-    Create a summary report with specific file locations and fix suggestions.
-    ```
+<CardGroup cols={2}>
+  <Card title="Security Scanner Agent" icon="shield" href="https://hub.continue.dev/continuedev/snyk-continuous-ai-agent">
+    **Snyk Continuous AI Agent** - Comprehensive security scanning with Snyk MCP integration.
 
-    **Avoid**: Assumptions about available context
-    ```
-    Fix the accessibility problems.
-    ```
-  </Accordion>
+    Automates dependency analysis, vulnerability scanning, and creates remediation PRs with AI-powered fix suggestions.
+  </Card>
 
-  <Accordion title="Multi-Step Workflows">
-    **Good**: Break complex tasks into clear steps
-    ```
-    For the user authentication refactor:
-    1. Audit current auth implementation for security issues
-    2. Design improved architecture with proper session management  
-    3. Create migration plan with backwards compatibility
-    4. Open PR with implementation and comprehensive tests
-    ```
+  <Card title="Performance Monitor" icon="gauge" href="https://hub.continue.dev/continuedev/netlify-continuous-ai-agent">
+    **Netlify Continuous AI Agent** - Performance optimization with A/B testing and monitoring.
 
-    **Avoid**: Complex tasks without structure
-    ```
-    Refactor the authentication system to be better.
-    ```
-  </Accordion>
-</AccordionGroup>
-
-### Choosing Rules
-
-Rules enforce consistent behavior across all agent runs. Popular rule categories:
-
-| Rule Type | Purpose | Example |
-|-----------|---------|---------|
-| **Code Quality** | Maintain standards | `continuedev/test-coverage`, `continuedev/code-review-checklist` |
-| **Security** | Apply security practices | `continuedev/security-first`, `continuedev/vulnerability-scanning` |
-| **Team Workflow** | Follow processes | `continuedev/pr-template`, `continuedev/commit-conventions` |
-| **Custom** | Organization-specific | `my-org/deployment-rules`, `my-org/documentation-standards` |
-
-### Selecting Tools (MCPs)
-
-MCPs provide agents with external system access:
-
-<CardGroup cols={2}>
-  <Card title="Development Tools" icon="code">
-    - **GitHub MCP**: Repository operations, PRs, issues
-    - **GitLab MCP**: Similar to GitHub for GitLab users  
-    - **Linear MCP**: Issue tracking and project management
-  </Card>
-  
-  <Card title="Analytics & Monitoring" icon="chart-line">
-    - **PostHog MCP**: User analytics and feature flags
-    - **Sentry MCP**: Error tracking and performance monitoring
-    - **DataDog MCP**: Infrastructure and application monitoring
-  </Card>
-  
-  <Card title="Security & Compliance" icon="shield-check">
-    - **Snyk MCP**: Vulnerability scanning and dependency analysis
-    - **SonarQube MCP**: Code quality and security analysis
-    - **Aqua MCP**: Container security scanning
-  </Card>
-  
-  <Card title="Data & Infrastructure" icon="database">
-    - **Supabase MCP**: Database operations and schema management
-    - **dlt MCP**: Data pipeline development and monitoring
-    - **Terraform MCP**: Infrastructure as code management
+    Tracks Core Web Vitals, identifies regressions, and provides optimization recommendations.
   </Card>
-</CardGroup>
-
-## Testing Your Agent
-
-Before deploying agents for team use, test thoroughly:
 
-<Steps>
-  <Step title="🧪 Local Testing">
-    Use TUI mode to interact with your agent:
+  <Card title="Error Monitoring Agent" icon="bug" href="https://hub.continue.dev/continuedev/sentry-continuous-ai-agent">
+    **Sentry Continuous AI Agent** - Automated error analysis and issue creation.
 
-    ```bash
-    cn --agent your-org/new-agent
-    # Chat interactively to test behavior
-    # Verify tool integrations work correctly
-    # Check that rules are applied properly
-    ```
-  </Step>
+    Monitors production errors, provides root cause analysis, and creates actionable GitHub issues.
+  </Card>
 
-  <Step title="🔍 Edge Case Testing">
-    Test with various scenarios:
-    
-    ```bash
-    # Test with minimal input
-    cn --agent your-org/new-agent "Fix authentication"
-    
-    # Test with detailed context  
-    cn --agent your-org/new-agent "Fix the authentication timeout issue in src/auth/session.js affecting mobile users"
+  <Card title="GitHub Management" icon="github" href="https://hub.continue.dev/continuedev/github-manager-ai-agent">
+    **GitHub Manager AI Agent** - Comprehensive GitHub workflow automation.
 
-    # Test error handling
-    cn --agent your-org/new-agent "Invalid request that should fail gracefully"
-    ```
-  </Step>
+    Handles issue triage, PR reviews, and release note generation with natural language prompts.
+  </Card>
 
-  <Step title="🎯 Production Readiness">
-    Verify production requirements:
+  <Card title="Database Management" icon="database" href=" https://hub.continue.dev/continuedev/supabase-agent">
+    **Supabase Continuous AI Agent** - Database security and management workflows.
 
-    - [ ] Agent completes tasks without manual intervention
-    - [ ] Error handling is robust and informative
-    - [ ] Output format meets team expectations
-    - [ ] Security and permissions are properly configured
-    - [ ] Performance is acceptable for intended use cases
-  </Step>
-</Steps>
-
-## Example Agent Configurations
-
-Here are proven agent patterns you can adapt:
-
-<AccordionGroup>
-  <Accordion title="Security Scanner Agent">
-    ```yaml
-    name: Weekly Security Scan
-    description: Runs comprehensive security analysis and creates remediation PRs
-    prompt: |
-      Run a complete security scan including:
-      1. Snyk dependency analysis
-      2. Code vulnerability scanning  
-      3. Container image security check
-      4. Create GitHub issues for critical findings with fix suggestions
-    tools:
-      - snyk-mcp
-      - github-mcp
-    rules:
-      - continuedev/security-first
-      - my-org/vulnerability-reporting
-    model: Claude Sonnet 4.5
-    visibility: organization
-    ```
-  </Accordion>
-
-  <Accordion title="Documentation Generator">
-    ```yaml
-    name: API Documentation Update
-    description: Generates and updates API documentation from code changes
-    prompt: |
-      Analyze recent API changes and update documentation:
-      1. Scan for new or modified endpoints
-      2. Generate OpenAPI specifications
-      3. Update README and integration guides
-      4. Create PR with comprehensive docs
-    tools:
-      - github-mcp
-      - openapi-mcp
-    rules:
-      - continuedev/documentation-standards
-      - my-org/api-guidelines
-    model: GPT-4
-    visibility: organization
-    ```
-  </Accordion>
-
-  <Accordion title="Performance Monitor">
-    ```yaml
-    name: Performance Regression Detector  
-    description: Monitors performance metrics and alerts on regressions
-    prompt: |
-      Analyze recent performance data:
-      1. Check Core Web Vitals trends
-      2. Identify performance regressions
-      3. Correlate with recent deployments
-      4. Create detailed performance report with recommendations
-    tools:
-      - netlify-mcp
-      - datadog-mcp
-      - github-mcp
-    rules:
-      - continuedev/performance-monitoring
-      - my-org/sla-requirements  
-    model: Claude Sonnet 4.5
-    visibility: private
-    ```
-  </Accordion>
-</AccordionGroup>
-
-## Best Practices
-
-<CardGroup cols={2}>
-  <Card title="Start Simple" icon="play">
-    Begin with basic prompts and single tools. Add complexity gradually as you learn what works for your use cases.
-  </Card>
-  
-  <Card title="Use Descriptive Names" icon="tag">
-    Choose clear, specific names that indicate the agent's purpose: `security-scanner-weekly` vs `scanner`.
-  </Card>
-  
-  <Card title="Version Control" icon="git-branch">
-    Make incremental changes and test thoroughly. Agent versioning helps track what works.
-  </Card>
-  
-  <Card title="Team Feedback" icon="users">
-    Involve your team in agent design. The best agents solve real workflow pain points.
+    Audits Row Level Security, identifies vulnerabilities, and generates fixes automatically.
   </Card>
 </CardGroup>
 
+
 ## Troubleshooting
 
 Common issues and solutions:
@@ -366,23 +187,3 @@ Common issues and solutions:
 | **Tools aren't working** | Check MCP configuration, verify API keys and permissions in Hub settings |
 | **Inconsistent behavior** | Add rules to enforce consistent patterns, test with various input scenarios |
 | **Performance issues** | Consider model choice, simplify complex multi-step workflows, optimize tool usage |
-
-## Next Steps
-
-<CardGroup cols={2}>
-  <Card title="Deploy Your Agent" icon="rocket" href="/hub/agents/overview#ways-to-run-agents">
-    Learn to run your agent in TUI, headless, or Mission Control modes
-  </Card>
-  
-  <Card title="Webhook Integration" icon="webhook" href="/hub/agents/overview#webhook-integrations">
-    Set up automated triggers for CI/CD and monitoring systems
-  </Card>
-  
-  <Card title="Browse Examples" icon="book-open" href="/guides/overview#mcp-integration-cookbooks">
-    Explore cookbook agents for inspiration and best practices
-  </Card>
-  
-  <Card title="Team Management" icon="users-gear" href="/hub/sharing">
-    Configure team access and collaboration workflows
-  </Card>
-</CardGroup>

docs/hub/agents/intro.mdx

@@ -54,7 +54,7 @@ Use Mission Control to kick off agents for:
 </Steps>
 
 <Info>
-  **New to agents?** Check out our [overview guide](/hub/agents/overview) to understand how agents combine prompts, rules, and tools into powerful workflows.
+  **New to agents?** Check out our [pre-configured agents](http://localhost:3000/hub/agents/overview#pre-configured-agents) to test out a workflow immediately.
 </Info>
 
 ## Example Workflow Tasks