# Specifying and Maintaining Agentic Workflows: An Empirical Study of GitHub Agentic Workflows

arXiv: https://arxiv.org/abs/2609.27263 · HTML: https://mlsanity.com/paper/2609.27263/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 23 Sep 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, 19 of 19)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Agentic Much? Adoption of Coding Agents on GitHub](https://mlsanity.com/paper/2601.18341/) (2026)
- [Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects](https://mlsanity.com/paper/2511.04427/) (2025)
- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?](https://mlsanity.com/paper/2602.11988/) (2026)
- [Prompting in the Wild: An Empirical Study of Prompt Evolution in Software Repositories](https://mlsanity.com/paper/2412.17298/) (2024)
- [On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents](https://mlsanity.com/paper/2601.20404/) (2026)
- [On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code](https://mlsanity.com/paper/2509.14744/) (2025)
- [Context Engineering for AI Agents in Open-Source Software](https://mlsanity.com/paper/2510.21413/) (2025)
- [Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions](https://mlsanity.com/paper/2508.18771/) (2025)
- [What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues](https://mlsanity.com/paper/2506.22390/) (2025)
- [From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills](https://mlsanity.com/paper/2607.01456/) (2026)
- [Can LLMs Write CI? A Study on Automatic Generation of GitHub Actions Configurations](https://mlsanity.com/paper/2507.17165/) (2025)
- [The Hidden Costs of Automation: An Empirical Study on GitHub Actions Workflow Maintenance](https://mlsanity.com/paper/2409.02366/) (2024)
- [When AI Agents Touch CI/CD Configurations: Frequency and Success](https://mlsanity.com/paper/2601.17413/) (2026)
- [An Empirical Study of the Evolution of GitHub Actions Workflows](https://mlsanity.com/paper/2602.14572/) (2026)
- [How (Not) To Write a Software Engineering Abstract](https://mlsanity.com/paper/2506.21634/) (2025)
- [Doc2CI: A Multi-Service Study of CI Configuration Generation Using Large Language Models](https://mlsanity.com/paper/2608.01451/) (2026)

## Abstract (arXiv)

Agentic workflows shift software development from prompting AI agents for individual tasks to defining recurring work that agents execute automatically. GitHub Agentic Workflows (gh-aw) enables this approach through Markdown files that combine natural-language instructions with configuration and compile into executable GitHub Actions workflows. Unlike conventional workflows that primarily prescribe scripted operations, these files delegate tasks requiring interpretation to AI agents. They also couple agent instructions with execution triggers, making those instructions operational specifications for repeated repository activities. However, how developers structure and maintain these specifications, and which execution requirements and safeguards they express, remains insufficiently understood. In this paper, we examine the structure, evolution, and instruction content of gh-aw Markdown files to inform how practitioners define and maintain agent-run work. We analyze 1,248 files from 276 repositories, 20,841 commit-file events, and 288 resolved instruction-label sets from a sample of 294 files. Our results show that workflow instructions extend beyond short prompts, with a median of 556.5 words and code blocks in 62.1% of files. Among files with at least 120 days of observed activity, 78.2% still receive updates in month 4, while size-normalized churn decreases after the first month. Tasks, outputs, constraints, and process instructions each appear in over 93% of labeled workflows, yet only 9.4% explicitly address prompt-injection defense. LLM classification achieves an F1 score of 0.818 and Cohen's Kappa of 0.715 against the resolved human labels. These findings suggest that developers should account for the evolution of workflows copied or referenced across repositories and consider adding prompt-injection defenses, resource budgets, and evidencecredibility checks where applicable.