agentmods.dev

mcp-airflow: Instructions file for Codex

AGENTS.md

mcp-airflow AGENTS.md is an instructions file for Codex, OpenCode from antonio-mello-ai/mcp-airflow. It costs 589 tokens per session, scanned A, original, MIT.

Project instructions for an MCP Airflow server, a program that exposes Apache Airflow's workflow-management API to other tools.

In plain words
What is it for?
They help contributors understand the project's Python and FastMCP stack, setup requirements, status, and Brazilian Portuguese language conventions.
Why use it?
They document required setup, including a Git hook that checks version changes before code is pushed.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

This is antonio-mello-ai/mcp-airflow's own configuration. It tells Codex and OpenCode how to work on mcp-airflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-airflow configures →

not rated 2repo changed 1mo ago A scan 589 tokens original MIT
View source ↗ antonio-mello-ai/mcp-airflow
Reuse

Borrowing it

Nothing to install: this file belongs to antonio-mello-ai/mcp-airflow. 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/antonio-mello-ai/mcp-airflow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/antonio-mello-ai/mcp-airflow

Made for: Codex, OpenCode.

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.

agentmods badge for mcp-airflow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/antonio-mello-ai/mcp-airflow/agents-md/github.svg)](https://agentmods.dev/instructions/antonio-mello-ai/mcp-airflow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/antonio-mello-ai/mcp-airflow/agents-md"><img src="https://agentmods.dev/badge/instructions/antonio-mello-ai/mcp-airflow/agents-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.

agentmods 80×15 button for mcp-airflow AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/antonio-mello-ai/mcp-airflow/agents-md"><img src="https://agentmods.dev/badge/instructions/antonio-mello-ai/mcp-airflow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 589 This file is loaded in full into every session.
When invoked 589 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00589 $0.00589
Opus 5.5 $0.00236 $0.00236
Sonnet 5.5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 1mo ago against content hash 3f224a7b16dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-airflow AGENTS.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 1mo 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.

AGENTS.md · 75 lines

What it actually says

AGENTS.md — MCP Airflow

Purpose

Public MCP server that exposes a bounded set of Apache Airflow REST API operations as tools. The repository is an open-source package, not the source of truth for any private Airflow deployment or credentials.

Repository rules

  • Keep examples generic and safe for a public repository.
  • Never commit Airflow credentials, tokens, private hostnames, customer names, or deployment-specific topology.
  • Preserve compatibility with the supported Airflow 2.x and 3.x API contracts.
  • Treat trigger_dag_run and any future mutating tool as an operational action; its name, arguments, and result must make the mutation explicit.
  • Do not silently broaden the MCP server's permissions or tool surface.
  • Roadmap, backlog, and priority live in GitHub Issues. Delivery evidence lives in closed Issues, pull requests, releases, and PyPI publication records.
  • Do not create roadmap.md, docs/backlog.md, or CHANGELOG.md.

Development

uv sync --group dev
uv run --all-extras --all-groups pytest
uvx ruff check src/ tests/
uvx ruff format --check src/ tests/

pyproject.toml is the single source of truth for the package version. The legacy VERSION file no longer exists. Until GitHub issue #9 is implemented, do not enable the stale .githooks/pre-push hook described in older clones.

Verification

  • Add tests for every behavior change.
  • Validate both the relevant Airflow API version and failure path.
  • Never log or assert plaintext passwords, bearer tokens, or full authenticated URLs.
  • Keep the package import and registered-tool smoke tests passing.

Active documentation

  • README.md: public overview and installation
  • docs/fluxos-negocio.md: supported operator flows
  • docs/arquitetura.md: components and API boundaries
  • docs/operacao.md: configuration, validation, and releases
  • docs/index.md: documentation index
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.

  1. 1mo ago Changed · +51 lines · +470 tokens per session 3f224a7b16dd
  2. 2mo ago First seen · 24 lines · 119 tokens per session scan A 159d548256b3

Subscribe to this mod's changes

mcp-airflow AGENTS.md is an instructions file published in the GitHub repository antonio-mello-ai/mcp-airflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 589 tokens to every session, about $0.0024 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.

felhenmcp-server
Related

mcp-airflow AGENTS.md compared with instructions from other repositories

mcp-airflow AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-airflow AGENTS.mdantonio-mello-ai/mcp-airflowInstructions file21mo agoMITA589Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot