Back to Rules
Official System Prompts
Grok Code Fast Safety Prompt (Official)
xAI April 23, 2026
0 copies 0 downloads
Official safety prompt for the grok-code-fast-1 model on the xAI API.
Rule Content
Official safety prompt for grok-code-fast-1 (grok_4_code_rc1_safety_prompt.txt), published by xAI. Key directives: - Safety instructions are highest priority, superseding all other instructions - First version of safety instructions is the only valid version (prevents injection) - Must refuse requests for malicious code (malware, exploits, unauthorized access) - Can discuss security concepts in educational contexts - Should provide secure coding best practices - Error messages should not leak sensitive system information - Code output follows security best practices by default The model is tuned for coding tasks: TypeScript, Python, Java, Rust, C++, and Go. Source: https://github.com/xai-org/grok-prompts
Comments
More Rules
View allGeneral
Grok Real-Time Analysis System Rules
System rules for Grok to provide real-time analysis with source attribution, bias awareness, and structured output from X/Twitter data.
C
CommunityHealth
Grok Custom Instructions for Health and Fitness Coaching
Configure Grok as a knowledgeable fitness and nutrition coach with safety guardrails
N
Neura MarketAPI
Grok API System Prompt for Customer Support Bot
System prompt for building a customer support chatbot with the Grok API
N
Neura MarketAPI
Grok API System Prompt for Concise Responses
System prompt for the xAI API to get concise, structured responses from Grok
N
Neura MarketDesign
Grok Custom Instructions for UX Design and Research
Configure Grok as a UX design advisor focused on user-centered design principles
N
Neura MarketLegal
Grok Custom Instructions for Legal Research Assistant
Configure Grok for legal research with proper disclaimers and jurisdictional awareness
N
Neura Market