What is airflow-unfactor CLAUDE.md?

Project instructions for airflow-unfactor, an MCP server that helps convert Apache Airflow workflows, called DAGs, into Prefect workflows, called flows. It supplies source code and translation guidance for a language model to generate the new code.

Use them when developing or operating airflow-unfactor, especially its source-reading, concept-lookup, and Airflow-to-Prefect conversion process.

Converting workflow code with fixed templates can miss project-specific details. These instructions describe the server’s build-time knowledge and runtime steps for helping the model perform the conversion.

How gabcoyne/airflow-unfactor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gabcoyne/airflow-unfactor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gabcoyne/airflow-unfactor/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gabcoyne/airflow-unfactor

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gabcoyne/airflow-unfactor/claude-md/github.svg)](https://agentmods.dev/instructions/gabcoyne/airflow-unfactor/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gabcoyne/airflow-unfactor/claude-md"><img src="https://agentmods.dev/badge/instructions/gabcoyne/airflow-unfactor/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gabcoyne/airflow-unfactor/claude-md"><img src="https://agentmods.dev/badge/instructions/gabcoyne/airflow-unfactor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,029 This file is loaded in full into every session.

When invoked 1,029 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01029	$0.01029
Opus 5.5	$0.00412	$0.00412
Sonnet 5.5	$0.00206	$0.00206
Haiku 4.5	$0.00103	$0.00103

Measured 2mo ago against content hash bfa5fd8bb19c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

airflow-unfactor CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — airflow-unfactor

Project Overview

An MCP server for LLM-assisted conversion of Apache Airflow DAGs to Prefect flows. The LLM reads raw DAG source code directly and generates complete Prefect flows using pre-compiled translation knowledge.

Key Insight: Deterministic code templating is brittle for DAG conversion. Instead, we provide raw source code + translation knowledge compiled from live sources, and the LLM generates the code.

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        Build Time (Colin)                        │
│  colin/models/*.md  →  colin run  →  colin/output/*.json        │
│  (GitHub source, Prefect MCP docs, LLM summarization)           │
└─────────────────────────────┬───────────────────────────────────┘
                              │ compiled JSON
┌─────────────────────────────▼───────────────────────────────────┐
│                     MCP Server (Runtime)                         │
│                                                                  │
│  1. read_dag         → Raw DAG source code for LLM to read      │
│  2. lookup_concept   → Translation rules from Colin output       │
│  3. search_prefect_docs → Live Prefect docs for gaps            │
│  4. LLM generates complete Prefect flow code                    │
│  5. validate         → Syntax check + both sources for review   │
│  6. scaffold         → Project directory structure               │
└─────────────────────────────────────────────────────────────────┘

We provide raw code, translation knowledge, and validation. The LLM generates the code.

MCP Tools

Tool	Purpose
`read_dag`	Read a DAG file, return raw source + metadata (path, size, line count)
`lookup_concept`	Query Airflow→Prefect translation knowledge (operators, patterns, connections)
`search_prefect_docs`	Search live Prefect documentation via Prefect MCP server
`validate`	Return both sources + syntax check for LLM comparison
`scaffold`	Generate Prefect project directory structure (not code)

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 116 lines · 1,029 tokens per session scan A bfa5fd8bb19c

Subscribe to this mod's changes

airflow-unfactor CLAUDE.md is an instructions file published in the GitHub repository gabcoyne/airflow-unfactor (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,029 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LLM Orchestration airflow mcp migration prefect

airflow-unfactor CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
airflow-unfactor CLAUDE.mdgabcoyne/airflow-unfactor	Instructions file	9	5mo ago	MIT	A	1,029	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

airflow-unfactor: Instructions file for Claude Code