# jujumilk3/leaked-system-prompts **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/jujumilk3-leaked-system-prompts).** 14,134 stars · 1,969 forks ## Links - GitHub: https://github.com/jujumilk3/leaked-system-prompts - awesome-repositories: https://awesome-repositories.com/repository/jujumilk3-leaked-system-prompts.md ## Topics `ai` `document` `llm` `prompt` ## Description This project is a research-oriented repository that serves as a centralized database for system-level prompts and internal behavioral instructions extracted from various large language models. Its primary purpose is to provide a transparent, accessible reference for researchers and developers to study how artificial intelligence models are configured, constrained, and governed. The repository distinguishes itself by cataloging the hidden directives and operational guidelines that define model personas and safety boundaries. By archiving these instruction sets, it enables comparative analysis of how different models maintain their internal logic and respond to user interactions. The project functions as a resource for investigating the transparency of AI systems, offering a structured collection of data that helps clarify the underlying mechanisms of model behavior. It supports the broader goal of understanding the configuration and constraints inherent in modern language models. ## Tags ### Artificial Intelligence & ML - [System Prompt Archives](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-models/system-prompt-archives.md) — Providing a reference collection of extracted system instructions to improve understanding of how different artificial intelligence models are governed. - [Prompt Engineering Archives](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering-archives.md) — Archives internal behavioral directives and system-level instructions to enable comparative analysis of how different models maintain their internal logic. - [System Prompt Collections](https://awesome-repositories.com/f/artificial-intelligence-ml/system-prompt-collections.md) — Maintains a centralized collection of extracted system prompts from various models. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-opus-4_20250805.md)) - [Agent Persona Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/configuration-and-specifications/agent-persona-definitions.md) — Defines system prompts and behavioral constraints to govern AI persona and interaction style. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/discord-clyde_20230716-2.md)) - [Instruction Databases](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-models/instruction-databases.md) — Maintains a structured collection of internal model instructions to facilitate the study of AI configuration and governance. - [Model Behavioral Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/model-behavioral-analysis.md) — Preserves internal model instructions to facilitate behavioral analysis. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-sonnet-3.5_20241022.md)) - [System Prompts](https://awesome-repositories.com/f/artificial-intelligence-ml/system-prompts.md) — Catalogs and archives system-level prompt configurations used to define model personas and operational boundaries. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/claude-code-output-style-default_20251007.md)) - [AI Assistant Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-assistant-configurations.md) — Configures AI assistants to adopt specialized roles and prioritize specific knowledge sources. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md)) - [Research Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-optimization-and-tuning/large-language-model-configurations/research-tools.md) — Offers a research-oriented resource for developers to inspect and compare the hidden persona definitions and operational guidelines of AI models. - [Large Language Model Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-optimization-and-tuning/large-language-model-configurations.md) — Provides access to internal configuration and behavioral directives for comparative analysis of language models. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude_2.0_20240306.md)) - [AI Ethics and Fairness](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-ethics-and-fairness.md) — Evaluates and documents the ethical implications of model constraints and safety boundaries. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/microsoft-copilot_20260328.md)) ### DevOps & Infrastructure - [AI System Instructions](https://awesome-repositories.com/f/devops-infrastructure/configuration-management/application-settings-management/application-behavior-configurations/ai-system-instructions.md) — Archives system-level prompts and behavioral instructions for AI research. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-opus-4_20250731.md)) ### Education & Learning Resources - [Instructional](https://awesome-repositories.com/f/education-learning-resources/developer-documentation-references/knowledge-bases/instructional.md) — Provides a centralized archive of internal system instructions and behavioral guidelines for large language models. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/canva-code_20250519.md)) - [Instructional Reference Materials](https://awesome-repositories.com/f/education-learning-resources/instructional-reference-materials.md) — Provides comprehensive reference materials for researchers studying model instructions. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-sonnet-4.5_20260128.md)) ### Software Engineering & Architecture - [Prompt Submission Workflows](https://awesome-repositories.com/f/software-engineering-architecture/development-methodologies/engineering-best-practices/open-source-collaboration/community-contribution-models/prompt-submission-workflows.md) — Accepts community submissions of instructions through pull requests with verifiable examples. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/README.md)) - [Contextual Metadata Injection](https://awesome-repositories.com/f/software-engineering-architecture/contextual-data-injection/contextual-metadata-injection.md) — Injects real-time information about participants and environment variables to personalize AI responses. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/discord-clyde_20230716-2.md)) ### Security & Cryptography - [Model Safety Filters](https://awesome-repositories.com/f/security-cryptography/model-safety-filters.md) — Archives validation layers and safety policies used by various language models. ([source](https://github.com/jujumilk3/leaked-system-prompts/blob/main/microsoft-copilot_20240310.md))