Auto-Approve
Auto-approve configurations accelerate your development workflow by eliminating repetitive confirmation prompts, but they substantially increase security exposure.
⚠️ SECURITY WARNING: Auto-approve configurations bypass confirmation prompts, granting Gamecraft Agent direct system access. This can result in data loss, file corruption, or more severe consequences. Command line access poses particular risks, as it can potentially execute harmful operations that could damage your system or compromise security. Only enable auto-approval for actions you completely trust.
Quick Setup Guide
Navigate to the Auto-Approve tab in the Gamecraft Agent settings
Select which actions Gamecraft Agent can perform without requesting permission
Available Permission Types
Read files and directories
Enables Gamecraft Agent to access files without confirmation
Medium
Edit files
Allows Gamecraft Agent to modify files without approval
High
Execute approved commands
Runs whitelisted terminal commands automatically
High
Use MCP servers
Enables Gamecraft Agent to use configured MCP services
Medium-High
Switch modes
Changes between Gamecraft Agent modes automatically
Low
Create & complete subtasks
Manages subtasks without confirmation
Low
Retry failed requests
Automatically retries failed API requests
Low
Answer follow-up questions
Selects default answer for follow-up questions
Low
Advanced Configuration Panel
The configuration panel provides comprehensive control with essential security context:
Allow Gamecraft Agent to automatically perform operations without requiring approval. Enable these configurations only if you completely trust the AI and understand the associated security implications.
To access these configurations:
Click ⚙️ in the top-right corner
Navigate to Auto-Approve Settings
Read Operations
Read Operations Setting: "Always approve read-only operations"
Description: "When enabled, Gamecraft Agent will automatically view directory contents and read files without requiring you to click the Approve button."
Risk level: Medium
While this configuration only permits file reading (not modification), it could potentially expose sensitive data. Still recommended as an initial setting for most users, but remain mindful of what files Gamecraft Agent can access.
Write Operations
Write Operations Setting: "Always approve write operations"
Description: "Automatically create and edit files without requiring approval"
Delay slider: "Delay after writes to allow diagnostics to detect potential problems" (Default: 1000ms)
Risk level: High
This configuration allows Gamecraft Agent to modify your files without confirmation. The delay timer is essential:
Higher values (2000ms+): Recommended for complex projects where diagnostics require more time
Default (1000ms): Suitable for most development projects
Lower values: Use only when speed is critical and you're operating in a controlled environment
Zero: No delay for diagnostics (not recommended for critical code)
Write Delay & Problems Pane Integration
Gamecraft Problems pane that Gamecraft Agent checks during the write delay
When you enable auto-approval for file writing, the delay timer integrates with Gamecraft's Problems pane:
Gamecraft Agent makes a change to your file
Gamecraft's diagnostic tools analyze the modification
The Problems pane updates with any errors or warnings
Gamecraft Agent identifies these issues before proceeding
This functions like a human developer pausing to check for errors after modifying code. You can adjust the delay time based on:
Project complexity
Language server performance
How critical error detection is for your workflow
Retry
API Requests Setting: "Always retry failed API requests"
Description: "Automatically retry failed API requests when server returns an error response"
Delay slider: "Delay before retrying the request" (Default: 5s)
Risk level: Low
This configuration automatically retries API calls when they fail. The delay controls how long Gamecraft Agent waits before attempting again:
Longer delays are gentler on API rate limits
Shorter delays provide faster recovery from transient errors
MCP Tools
MCP Tools Setting: "Always approve MCP tools"
Description: "Enable auto-approval of individual MCP tools in the MCP Servers view (requires both this setting and the tool's individual 'Always allow' checkbox)"
Risk level: Medium-High (depends on configured MCP tools)
This configuration works in conjunction with individual tool permissions in the MCP Servers view. Both this global setting and the tool-specific permission must be enabled for auto-approval.
Mode Switching
Mode Switching Setting: "Always approve mode switching"
Description: "Automatically switch between different modes without requiring approval"
Risk level: Low
Allows Gamecraft Agent to change between different internal modes (Code, Architect, Debug, etc.) without requesting permission. This primarily affects the AI's behavior rather than system access.
Subtasks
Subtasks Setting: "Always approve creation & completion of subtasks"
Description: "Allow creation and completion of subtasks without requiring approval"
Risk level: Low
Enables Gamecraft Agent to create and complete subtasks automatically. This relates to workflow organization rather than system access.
Command Execution
Command Execution Setting: "Always approve allowed execute operations"
Description: "Automatically execute allowed terminal commands without requiring approval"
Command management: "Command prefixes that can be auto-executed when 'Always approve execute operations' is enabled. Add * to allow all commands (use with caution)."
Risk level: High
This configuration allows terminal command execution with controls. While risky, the whitelist feature limits what commands can run. Important security features:
Whitelist specific command prefixes (recommended)
Never use * wildcard in production or with sensitive data
Consider security implications of each allowed command
Always verify commands that interact with external systems
Interface elements:
Text field to enter command prefixes (e.g., 'git')
"Add" button to add new prefixes
Clickable command buttons with X to remove them
Follow-Up Questions
Follow-Up Questions Setting: Always default answer for follow-up questions
Description: Automatically selects the first AI-suggested answer for a follow-up question after a configurable timeout. This accelerates your workflow by allowing Gamecraft Agent to proceed without manual intervention. A visual countdown appears on the first suggestion.
Timeout slider: Use the slider to set the wait time from 1 to 300 seconds (Default: 60s).
Note: You can override the timer at any point by clicking a different suggestion, editing a suggestion, or typing a response.
Risk level: Low
Last updated