# On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces

arXiv: https://arxiv.org/abs/2608.28497 · HTML: https://mlsanity.com/paper/2608.28497/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 16 of 16)

- [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [An Empirical Comparison of Dependency Network Evolution in Seven Software Packaging Ecosystems](https://mlsanity.com/paper/1710.04936/) (2017)
- [Agentic Refactoring: An Empirical Study of AI Coding Agents](https://mlsanity.com/paper/2511.04824/) (2025)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study](https://mlsanity.com/paper/2402.16480/) (2024)
- [On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code](https://mlsanity.com/paper/2509.14744/) (2025)
- [Exploring ChatGPT App Ecosystem: Distribution, Deployment and Security](https://mlsanity.com/paper/2408.14357/) (2024)
- [Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity](https://mlsanity.com/paper/2601.18345/) (2026)
- [Understanding Prompt Management in GitHub Repositories: A Call for Best Practices](https://mlsanity.com/paper/2509.12421/) (2025)
- [Extension Decisions in Open Source Software Ecosystem](https://mlsanity.com/paper/2507.23168/) (2025)
- [Do AI Coding Agents Log Like Humans? An Empirical Study](https://mlsanity.com/paper/2604.09409/) (2026)
- [Bridging the Language Gap: An Empirical Study of Bindings for Open Source Machine Learning Libraries Across Software Package Ecosystems](https://mlsanity.com/paper/2201.07201/) (2022)
- [Using Source Code Density to Improve the Accuracy of Automatic Commit Classification into Maintenance Activities](https://mlsanity.com/paper/2005.13904/) (2020)
- [Are We Speeding Up or Slowing Down? On Temporal Aspects of Code Velocity](https://mlsanity.com/paper/2303.04293/) (2023)
- [CommitSuite: A Comprehensive Benchmark for Commit Classification and Message Generation](https://mlsanity.com/paper/2605.02256/) (2026)

## Abstract (arXiv)

AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly extended through plugin marketplaces, yet the structure, maintenance, and co-evolution dynamics of these emerging repositories remain empirically unexplored. Unlike traditional software packages that deliver functionality through source code, agent plugins deliver functionality through a combination of natural-language instruction files, scripts, and configuration files, raising the question of whether these plugins are maintained artifacts that co-evolve across components, or one-off artifacts that developers write once and do not need to revisit. To study the maintenance and co-evolution of agent plugins, we conduct an empirical study of 1,926 repositories hosting Claude Code plugin marketplaces, analyzing 8,351 plugins and 77,773 commits across 2,018 marketplaces. We find that the marketplace is expanding rapidly, plugin-touching commit activity growing 8.8x over six months after the October 2025 launch, and plugins targeting Software Engineering tasks accounting for 61.3% of all plugins. Plugin development is predominantly feature-driven, with feature commits occurring at more than twice the rate of conventional open-source software (OSS) (39.6% vs. 17.2%). Claude co-authors 34.9% of all commits, and four commit types (docs, perf, style, and refactor) carry substantially different meanings in plugin repositories than in traditional software. Most component types evolve independently, but within skills directories, natural-language instruction files and implementation scripts co-evolve at above-chance rates, with 78% of co-changes being functionally coupled, representing a new class of maintenance dependency not observed in traditional software engineering.