Verdent for VS Code provides multiple execution modes that control how the AI interacts with your files and executes commands. Each mode offers different trade-offs between control, speed, and safety.
What You’ll Learn
- How each execution mode works and when to use it
- Permission models and safety considerations
- Mode comparison and switching strategies
- Think Hard Mode for complex reasoning tasks
Key Modes Available
Manual Accept Mode
Default mode with permission requests for every protected operation. Maximum control and oversight.
Auto-Run Mode
Automatic file operations, permission required for commands. Balances speed and safety.
Skip Permission Mode
Full autonomy for isolated environments. No permission prompts for anything.
Plan Mode
Read-only planning mode. Review complete plan before execution begins.
Execution Modes
- Manual Accept Mode
- Auto-Run Mode
- Skip Permission Mode
Manual Accept Mode is the default execution mode that provides control over file modifications and command execution.Automatic Operations:
- File reading and code analysis
- Directory browsing
- File editing (create, modify, delete)
- Command execution (terminal commands, tests, builds)
When to Use
- Learning Verdent’s capabilities and workflow patterns
- Working in unfamiliar codebases requiring careful oversight
- Critical changes to production code or security-sensitive areas
- Compliance requirements needing explicit approval trails
Activation
Manual Accept Mode is active by default. To switch back:1
Open Permission Menu
Click “Switch Permission” button in Input Box
2
Select Manual Accept Mode
Choose “Manual Accept Mode” from the dropdown
3
Verify Activation
Button displays “Manual” to confirm mode is active
Safety Considerations
Advantages:- First-use approval per tool type (file edits, commands, tools)
- Complete visibility before granting access
- Maximum control and transparency
- After first approval of a tool type, subsequent uses proceed without prompts
- Approval is per tool type, not per operation
- Start new sessions when working on critical code to reset tool approvals
Plan Mode
Plan Mode is a read-only interaction mode where Verdent analyzes code, creates detailed plans, and asks clarifying questions, but cannot modify files or execute commands until you approve.How It Works
- Analysis - Reads files automatically
- Planning - Creates structured plan with todo list
- Clarification - Asks questions to remove uncertainty
- Approval - You review and decide to proceed
- Execution - Switches to your permission mode to execute
When to Use
- Complex multi-file changes (understand scope before committing)
- Unfamiliar codebases (safe exploration without risk)
- Architectural decisions (review approach before implementation)
- Avoiding Manual Accept fatigue (review once vs 50 individual prompts)
- High-stakes production changes (full visibility before execution)
Activation
1
Open Mode Menu
Click “Switch Mode” button in Input Box
2
Select Plan Mode
Choose “Plan Mode” from the dropdown
3
Verify Activation
Mode indicator changes to “Plan” to confirm mode is active
Safety Considerations
Advantages:- Zero execution risk during planning
- Full visibility before committing
- Interactive clarification removes uncertainty
- Safe for production analysis
- Approval doesn’t guarantee correctness (plans can have logical errors)
- Execution safety depends on chosen permission mode after approval
- Plan quality depends on prompt clarity
- Review plans for logical errors or misunderstandings
- Ask follow-up questions if unclear
- Refine prompts before approving execution
- Consider which permission mode will execute (Manual Accept for oversight, Auto-Run for speed)
Think Hard Mode
Think Hard Mode allocates maximum computational resources for complex reasoning tasks. The model explores multiple approaches and provides more thorough solutions. Characteristics:- Extended reasoning time
- Deeper analysis of multiple solution approaches
- Better handling of complex logic, edge cases, architectural decisions
- Higher credit cost per request
When to Use
| Use Think Hard Mode For | Don’t Use For |
|---|---|
| Complex architectural decisions with multiple trade-offs | Simple, straightforward tasks |
| Sophisticated debugging with multiple potential causes | Time-sensitive requests |
| Algorithm design requiring optimization analysis | Limited credit budget |
| Critical business logic where correctness is paramount | When standard mode is adequate |
| Performance optimization of complex bottlenecks |
Activation
- Natural Language (Claude)
Use the UI button for per-request activation:Works with all AI providers. Not persistent - must activate each time for requests requiring deep reasoning.
1
Enable Think Hard
Click “Think Hard” button/toggle in Input Box
2
Submit Your Prompt
Type and submit your request
3
Single Request Only
Applies to that specific request only - not persistent
Mode Comparison
| Mode | Control | Speed | Best For | Avoid When |
|---|---|---|---|---|
| Manual Accept | Maximum | Slowest | Learning, unfamiliar code, critical changes | Trusted projects, rapid iteration |
| Auto-Run | Moderate | Fast | Trusted codebases, prototyping, multi-file work | Unfamiliar code, no version control |
| Skip Permission | None | Fastest | CI/CD, disposable containers, sandboxes | Production, important code |
| Plan Mode | Review-First | N/A | Complex changes, architectural decisions | Simple tasks |
| Think Hard | Per-Request | Slower | Complex reasoning, algorithms, critical logic | Simple tasks, time-sensitive |
When to Use Each Mode
| Scenario | Manual Accept | Auto-Run | Skip Permission | Plan Mode |
|---|---|---|---|---|
| Learning Verdent | ✓ | |||
| Unfamiliar codebase | ✓ | ✓ | ||
| Trusted codebase with Git | ✓ | |||
| Critical/production code | ✓ | ✓ | ||
| Rapid prototyping | ✓ | |||
| Multi-file refactoring | ✓ | |||
| Complex architectural planning | ✓ | |||
| CI/CD pipelines (isolated) | ✓ | |||
| Disposable containers | ✓ | |||
| Compliance requirements | ✓ |
Safety Best Practices
Safety Hierarchy (Most to Least Safe)
Safety Hierarchy (Most to Least Safe)
Understanding the safety ranking of each mode helps you choose appropriately for different risk levels.
- Plan Mode - Read-only until approved. Zero execution risk during planning.
- Manual Accept Mode - Per-operation control with first-use approval per tool type.
- Auto-Run Mode - File autonomy with command approval. Git safety net required.
- Skip Permission Mode - Full autonomy. Isolated environments only.
General Best Practices
General Best Practices
Essential practices that apply regardless of which execution mode you’re using.For All Modes:
- Use Version Control - Initialize Git before using permissive modes, commit frequently, review diffs before committing
- Write Clear Prompts - Be specific about scope, specify file boundaries explicitly, use @-mentions for context
- Review Before Committing - Check Source Control panel after completions, review all diffs carefully, test changes
- Start Fresh Sessions - Clear context between major tasks, reset tool approvals for sensitive work, avoid context contamination
- Match Mode to Risk - Critical code → Manual Accept or Plan Mode, trusted code → Auto-Run, experiments → Auto-Run with Git, disposable → Skip Permission only
- Never commit sensitive files (.env, credentials)
- Configure .gitignore before using Auto-Run
- Review command permissions carefully
- Use Plan Mode for changes affecting security
- Fresh sessions reset tool approvals in Manual Accept
Progressive Permission Model
Progressive Permission Model
Understanding how Verdent’s permission system works helps you use it effectively.How it works:
- First use - System requests permission when you first use each tool type (file edits, command executions, tool usage)
- Subsequent uses - After initial approval, that tool type proceeds without prompts for the rest of the session
- New session - Starting a new session resets all approvals, allowing you to start fresh