On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code

• URL: http://arxiv.org/abs/2509.14744v1
• Date: Thu, 18 Sep 2025 08:46:41 GMT
• Title: On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
• Authors: Worawalan Chatlatanagulchai, Kundjanasith Thonglek, Brittany Reid, Yutaro Kashiwa, Pattara Leelaprute, Arnon Rungsawang, Bundit Manaskasemsak, Hajimu Iida,
• Abstract summary: Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention.<n>Key to this process are agent manifests, configuration files (such as Claude.md) that provide agents with essential project context, identity, and operational rules.<n>We analyzed 253 Claude.md files from 242 repositories to identify structural patterns and common content.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files (such as Claude.md) that provide agents with essential project context, identity, and operational rules. However, the lack of comprehensive and accessible documentation for creating these manifests presents a significant challenge for developers. We analyzed 253 Claude.md files from 242 repositories to identify structural patterns and common content. Our findings show that manifests typically have shallow hierarchies with one main heading and several subsections, with content dominated by operational commands, technical implementation notes, and high-level architecture.

Related papers

• Codified Context: Infrastructure for AI Agents in a Complex Codebase [0.0]
  This paper presents a three-component codified context infrastructure developed during construction of a 108,000-line C# distributed system.<n>The framework is published as an open-source companion repository.
  arXiv  Detail & Related papers  (2026-02-24T02:11:26Z)
• Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? [3.2610504259514754]
  We study whether context files are effective for real-world tasks.<n>We find that context files tend to reduce task success rates compared to providing no repository context.<n>We conclude that unnecessary requirements from context files make tasks harder, and human-written context files should describe only minimal requirements.
  arXiv  Detail & Related papers  (2026-02-12T14:15:22Z)
• Agent READMEs: An Empirical Study of Context Files for Agentic Coding [8.019313057979522]
  We study 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content.<n>We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions.<n>These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.
  arXiv  Detail & Related papers  (2025-11-17T02:18:55Z)
• Decoding the Configuration of AI Coding Agents: Insights from Claude Code Projects [0.1631115063641726]
  Agentic code assistants are a new generation of AI systems capable of performing end-to-end software engineering tasks.<n>Their behavior and effectiveness depend heavily on configuration files that define architectural constraints, coding practices, and tool usage policies.<n>This paper presents an empirical study of the configuration ecosystem of Claude Code, one of the most widely used agentic coding systems.
  arXiv  Detail & Related papers  (2025-11-12T12:28:57Z)
• Gistify! Codebase-Level Understanding via Runtime Execution [97.63528391679807]
  We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality.<n>We show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions.
  arXiv  Detail & Related papers  (2025-10-30T17:58:26Z)
• CP-Agent: Agentic Constraint Programming [23.191983095692223]
  Translating natural language problem descriptions into formal constraint models is a fundamental challenge in constraint programming.<n>Previous approaches have employed fixed with predetermined modeling steps, failing on a significant number of benchmark problems.<n>We present a new approach using a pure agentic strategy without any fixed pipeline.
  arXiv  Detail & Related papers  (2025-08-10T19:59:01Z)
• Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code [0.0]
  Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps.<n>We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, and a NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation.
  arXiv  Detail & Related papers  (2025-08-09T14:45:53Z)
• AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios [51.46347732659174]
  Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications.<n>AgentIF is the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios.
  arXiv  Detail & Related papers  (2025-05-22T17:31:10Z)
• Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning [57.09163579304332]
  We introduce PaperCoder, a framework that transforms machine learning papers into functional code repositories.<n>PaperCoder operates in three stages: planning, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files.<n>We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations.
  arXiv  Detail & Related papers  (2025-04-24T01:57:01Z)
• DocAgent: A Multi-Agent System for Automated Code Documentation Generation [7.653779364214401]
  We introduce DocAgent, a novel multi-agent collaborative system using topological code processing for incremental context building.<n>Specialized agents (Reader, Searcher, Writer, Verifier, Orchestrator) then collaboratively generate documentation.<n>We also propose a multi-faceted evaluation framework assessing Completeness, Helpfulness, and Truthfulness.
  arXiv  Detail & Related papers  (2025-04-11T17:50:08Z)
• One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts [110.94724216491753]
  Large Language Models (LLMs) exhibit strong generalization capabilities when prompted with language instructions and in-context demos. Various methods have been explored to automate the instruction design, but they restricted the searched prompt to one instruction. We adopt the Mixture-of-Expert paradigm and divide the problem space into a set of sub-regions. A two-phase process is developed to construct the specialized expert for each region. A region-based joint search of an instruction per expert complements the demos assigned to it, yielding a synergistic effect.
  arXiv  Detail & Related papers  (2024-06-28T23:05:08Z)
• DOLOMITES: Domain-Specific Long-Form Methodical Tasks [81.63464319950664]
  We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output. We introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples.
  arXiv  Detail & Related papers  (2024-05-09T17:25:31Z)
• SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization [51.67317895094664]
  This paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. We propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences.
  arXiv  Detail & Related papers  (2024-01-26T09:23:27Z)
• Hierarchical Encoders for Modeling and Interpreting Screenplays [1.4674456578222843]
  We propose a neural architecture for encoding richly structured texts. This work specifically tackles screenplays, but we discuss how the underlying approach can be generalized to a range of structured documents.
  arXiv  Detail & Related papers  (2020-04-30T01:15:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.