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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chatlatanagulchai, Worawalan, Thonglek, Kundjanasith, Reid, Brittany, Kashiwa, Yutaro, Leelaprute, Pattara, Rungsawang, Arnon, Manaskasemsak, Bundit, Iida, Hajimu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917171172474880
author Chatlatanagulchai, Worawalan
Thonglek, Kundjanasith
Reid, Brittany
Kashiwa, Yutaro
Leelaprute, Pattara
Rungsawang, Arnon
Manaskasemsak, Bundit
Iida, Hajimu
author_facet Chatlatanagulchai, Worawalan
Thonglek, Kundjanasith
Reid, Brittany
Kashiwa, Yutaro
Leelaprute, Pattara
Rungsawang, Arnon
Manaskasemsak, Bundit
Iida, Hajimu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14744
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
Chatlatanagulchai, Worawalan
Thonglek, Kundjanasith
Reid, Brittany
Kashiwa, Yutaro
Leelaprute, Pattara
Rungsawang, Arnon
Manaskasemsak, Bundit
Iida, Hajimu
Software Engineering
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.
title On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
topic Software Engineering
url https://arxiv.org/abs/2509.14744