system-prompts-and-models-of-ai-tools

Extracts, organizes, and catalogs system prompts from 25+ AI coding tools (Cursor, Windsurf, Claude Code, v0, Lovable, etc.) into a structured repository with version tracking and architectural pattern identification. Uses community-driven collection to reverse-engineer tool behavior, enabling developers to understand how different AI systems are instructed to behave, what tool ecosystems they expose, and how they prioritize task execution across parallel vs. sequential workflows.

Maps and categorizes the tool ecosystems exposed by agentic IDEs (Qoder, Windsurf, Claude Code, VSCode Agent) into 8-30+ discrete tool categories including code search, file operations, command execution, browser interaction, and memory systems. Analyzes how tools are organized hierarchically, whether they execute in parallel or sequential chains, and how validation pipelines (e.g., linter checks via get_problems) constrain tool output before user presentation.

Catalogs how AI tools implement multi-model support and LLM configuration: model selection strategies, fallback mechanisms, cost optimization, and performance tuning. Analyzes how tools choose between models (GPT-4, Claude, Llama) based on task complexity, latency requirements, or cost constraints. Captures configuration patterns like temperature settings, token limits, and how tools adapt prompts for different model families and their specific capabilities/limitations.

Catalogs architectural patterns from specialized AI systems: Trae's agentic IDE design, Perplexity's web search and browser integration, Proton's multi-model routing and ecosystem integration, and Lumo's specialized capabilities. Analyzes how these systems differentiate through unique tool ecosystems, specialized prompts, and domain-specific optimizations. Captures cross-cutting patterns like communication protocols, user interaction models, and how systems adapt to different use cases (coding vs. research vs. productivity).

Identifies and compares cross-cutting architectural patterns that appear across multiple agentic IDEs and AI systems: tool system design patterns, file editing strategies, validation pipelines, memory architectures, and communication protocols. Analyzes how different tools solve similar problems (e.g., context window management, tool orchestration, error handling) with different approaches. Provides pattern language and taxonomy for describing AI system architectures.

Extracts and compares file editing approaches used across AI tools: line-replace strategies (Lovable), ReplacementChunks (Windsurf), Quick Edit Comments (v0), and full-file rewrites. Analyzes how each tool handles edit validation, linter feedback integration, and conflict resolution when multiple edits target the same file region. Captures constraints like maximum edit chunk sizes and how tools preserve code structure during modifications.

Documents how different agentic IDEs implement code search and context gathering: semantic search (embeddings-based), keyword search, AST-based navigation, and codebase indexing strategies. Analyzes how tools prioritize context selection (recent files, related modules, search results ranking) and how search results are incorporated into LLM context windows. Captures constraints like maximum search result count and context window allocation strategies.

Catalogs memory systems used by agentic IDEs: Knowledge Items (KI) architecture (Qoder), conversation logs with persistent context, workflow systems with turbo annotations, and state management patterns. Analyzes how tools maintain long-term context across conversations, handle memory eviction when context windows fill, and integrate external knowledge bases or documentation. Captures memory lifecycle: creation, retrieval, update, and deletion strategies.

Extracts web development patterns from AI tools specialized in web building (v0, Lovable, Same.dev): Next.js/React integration, Tailwind CSS design system adherence, shadcn/ui component usage, design aesthetics requirements, and SEO standards. Analyzes how tools handle component generation, styling constraints, and integration with external services (Stripe, analytics). Captures tool-specific conventions like Quick Edit Comments (v0) and design system customization approaches.

Documents how agentic IDEs decompose user requests into executable tasks: task planning algorithms, complexity assessment heuristics, and tool selection strategies. Analyzes how tools decide between parallel vs. sequential execution, when to delegate to sub-agents, and how to break down complex requests into manageable steps. Captures decision criteria like estimated token cost, execution time, and success probability.

Catalogs how agentic IDEs integrate command execution and terminal access: shell command execution strategies, background process management, script execution and debugging systems, and output capture/parsing. Analyzes constraints like command timeout policies, output size limits, and security restrictions (e.g., no destructive commands). Captures how tools handle command failures, stderr/stdout parsing, and integration with linters and build systems.

Catalogs browser interaction capabilities in web-focused AI tools (Windsurf, Comet, Lovable): page interaction (clicking, typing, scrolling), screenshot capture, DOM inspection, and browser preview systems. Analyzes how tools handle dynamic content, JavaScript execution, and real-time page state tracking. Captures constraints like screenshot resolution, interaction latency, and how browser state is communicated back to the AI agent for decision-making.

Catalogs security and access control mechanisms in agentic IDEs: workspace isolation, file access restrictions, secrets management, and security scanning pipelines. Analyzes how tools prevent unauthorized file access, detect and redact sensitive information (API keys, credentials), and implement audit logging. Captures constraints like read-only file restrictions and how tools handle sensitive operations like deployment or credential access.