# Beyond the Prompt: An Empirical Study of Cursor Rules

arXiv: https://arxiv.org/abs/2512.18925 · HTML: https://mlsanity.com/paper/2512.18925/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 74 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://mlsanity.com/paper/2304.06815/) (2023)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024)
- [Type-Constrained Code Generation with Language Models](https://mlsanity.com/paper/2504.09246/) (2025)
- [Test-Driven Development for Code Generation](https://mlsanity.com/paper/2402.13521/) (2024)
- [Aligning Language Models with Demonstrated Feedback](https://mlsanity.com/paper/2406.00888/) (2024)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks](https://mlsanity.com/paper/2401.15170/) (2024)
- [Categorizing the Content of GitHub README Files](https://mlsanity.com/paper/1802.06997/) (2018)
- [TypeT5: Seq2seq Type Inference using Static Analysis](https://mlsanity.com/paper/2303.09564/) (2023)
- [CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion](https://mlsanity.com/paper/2509.16112/) (2025)
- [Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context](https://mlsanity.com/paper/2402.03630/) (2024)
- [SemAgent: A Semantics Aware Program Repair Agent](https://mlsanity.com/paper/2506.16650/) (2025)
- [To Type or Not to Type? A Systematic Comparison of the Software Quality of JavaScript and TypeScript Applications on GitHub](https://mlsanity.com/paper/2203.11115/) (2022)

## Built on by (most cited first, 7 of 7)

- [Harness Engineering for Agentic AI Coding Tools: An Exploratory Study](https://mlsanity.com/paper/2602.14690/) (2026)
- [Codified Context: Infrastructure for AI Agents in a Complex Codebase](https://mlsanity.com/paper/2602.20478/) (2026)
- [A Dataset of Agentic AI Coding Tool Configurations](https://mlsanity.com/paper/2605.08435/) (2026)
- [Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories](https://mlsanity.com/paper/2606.13298/) (2026)
- [Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints](https://mlsanity.com/paper/2605.14362/) (2026)
- [Motif: Discovering and Automating Personal Web Workflows](https://mlsanity.com/paper/2607.10531/) (2026)
- [Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and Services](https://mlsanity.com/paper/2608.05159/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) have demonstrated remarkable capabilities, research shows that their effectiveness depends not only on explicit prompts but also on the broader context provided. This requirement is especially pronounced in software engineering, where the goals, architecture, and collaborative conventions of an existing project play critical roles in response quality. To support this, many AI coding assistants have introduced ways for developers to author persistent, machine-readable directives that encode a project's unique constraints. Although this practice is growing, the content of these directives remains unstudied. This paper presents a large-scale empirical study to characterize this emerging form of developer-provided context. Through a qualitative analysis of 401 open-source repositories containing cursor rules, we developed a comprehensive taxonomy of project context that developers consider essential, organized into five high-level themes: Conventions, Guidelines, Project Information, LLM Directives, and Examples. Our study also explores how this context varies across different project types and programming languages, offering implications for the next generation of context-aware AI developer tools.