whatisgithub

What is agent-workflows?

franklioxygen/agent-workflows — explained in plain English

Analysis updated 2026-05-18

55PythonAudience · developerComplexity · 2/5Setup · easy

In one sentence

A library of Markdown workflow guides that AI coding assistants and engineers follow for tasks like starting a project, fixing a bug, or reviewing code.

Mindmap

A visual breakdown will appear here once this repo is fully enriched.

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Point an AI coding assistant at a specific workflow file, such as bug-fixing or code review, before starting a task.

USE CASE 2

Use the bundled workflow-automation skill so the assistant picks the right workflow file automatically.

USE CASE 3

Install skills for Codex covering security review, migration planning, or release preparation.

USE CASE 4

Compare workflow-guided runs against unguided runs using the included pass-rate study.

What is it built with?

MarkdownPython

How does it compare?

franklioxygen/agent-workflowsbhartiyashesh/purelymailcalendarbiao994/docpaws
Stars555555
LanguagePythonPythonPython
Setup difficultyeasymoderatemoderate
Complexity2/54/53/5
Audiencedevelopergeneraldeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 30min
No license is stated in the provided text.

So what is it?

Agent Workflows is a library of structured step-by-step guides for AI coding tools and human engineers to follow when working on software projects. Instead of giving an AI assistant a single open-ended instruction and hoping it does the right thing, this library provides separate workflow documents for specific situations: starting a new project, adding a feature, fixing a bug, reviewing code, responding to a production incident, refactoring, and cleaning up technical debt. The core idea is that following a defined process with checkpoints produces better and more consistent results than ad hoc prompting. The README describes this as helping absorb "silent base-model quality drift" meaning that even if the underlying AI model becomes less reliable over time without an obvious announcement, the structured steps still catch mistakes before they slip through. The repository includes a small study using metrics like task pass rate, regression-free rate, and no-rework rate, comparing workflow-guided runs against unguided runs across six test tasks. Each workflow is a Markdown file that an AI coding assistant can read directly. Users either point the assistant to the relevant file manually, or use a bundled skill called workflow-automation that reads a task description and picks the right workflow file automatically. The library also includes shared files covering safety rules, preflight checks, and common conventions that all workflows reference, so each individual workflow document stays focused. Beyond the workflow documents, the repository ships several installable skills for tools like Codex: security review, test strategy design, migration planning, performance review, documentation maintenance, and release preparation. Each skill folder contains a metadata file and instructions, and is designed to be copied into a Codex skills directory and then invoked with a task description. The README notes the library is available in English and Simplified Chinese, and points new users to a separate getting-started guide included in the repository.

Copy-paste prompts

Prompt 1
Which workflow file in this library should I follow to respond to a production incident?
Prompt 2
Explain the pass rate, regression-free rate, and no-rework rate metrics used in this repo's study.
Prompt 3
How do I install and invoke the workflow-automation skill for Codex?
Prompt 4
Show me the shared safety rules file that all the workflows in this library reference.

Frequently asked questions

What is agent-workflows?

A library of Markdown workflow guides that AI coding assistants and engineers follow for tasks like starting a project, fixing a bug, or reviewing code.

What language is agent-workflows written in?

Mainly Python. The stack also includes Markdown, Python.

What license does agent-workflows use?

No license is stated in the provided text.

How hard is agent-workflows to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is agent-workflows for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.