What is skills AGENTS.md?

Repository instructions for maintaining a ZenML skills marketplace, including its folder structure, validation commands, naming rules, and testing guidance. A skills marketplace is a collection of reusable add-ons for coding agents.

Use it when adding or updating ZenML skills, checking marketplace or plugin JSON files, reviewing file organization, or following the project’s documentation and testing conventions.

It tells contributors how to inspect and validate the repository even though it has no application runtime or build system. This reduces mistakes in plugin manifests, file locations, and skill documentation.

skills AGENTS.md — Instructions file for Codex and OpenCode by zenml-io: Repository instructions for maintaining a ZenML skills marketplace,

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/zenml-io/skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/zenml-io/skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zenml-io/skills/agents-md.svg)](https://agentmods.dev/instructions/zenml-io/skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zenml-io/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,617 This file is loaded in full into every session.

When invoked 2,617 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.02617	$0.02617
Opus 5	$0.01308	$0.01308
Sonnet 5	$0.00523	$0.00523
Haiku 4.5	$0.00262	$0.00262

Measured 5d ago against content hash d6ee6f8911ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 5d 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

This repository is a skills marketplace, not an application codebase.

.claude-plugin/marketplace.json: top-level marketplace manifest listing all plugins.
skills/<plugin>/plugin.json: plugin metadata and the relative skills path ("./skills/").
skills/<plugin>/skills/<skill-name>/SKILL.md: primary skill instructions (Markdown with YAML frontmatter).
Supporting docs may live beside each skill (for example references/*.md or agents/*.md).
design/ is for local design artifacts and should not be committed.

Build, Test, and Development Commands

There is no build pipeline or runtime service in this repo. Use validation and inspection commands instead:

jq . .claude-plugin/marketplace.json: validate marketplace JSON syntax.
jq . skills/<plugin>/plugin.json: validate a plugin manifest.
rg --files skills: list skill files and confirm expected paths.
git status: verify only intended files are staged/modified.

Coding Style & Naming Conventions

Use clear, instructional Markdown in SKILL.md files with frontmatter.
Set name to a kebab-case identifier.
Write description as concise purpose plus “Use when …” guidance.
Keep plugin and skill folder names kebab-case (for example zenml-pipeline-authoring).
Follow existing JSON style: 2-space indentation, double-quoted keys/strings.
Prefer concrete, actionable steps over abstract guidance.
Keep ZenML doc links current (https://docs.zenml.io/...).

Testing Guidelines

No automated test framework is configured here. Treat structure validation as required:

Confirm skill file location: skills/<plugin>/skills/<skill>/SKILL.md.
Confirm plugin.json includes "skills": "./skills/".
Confirm plugin registration in .claude-plugin/marketplace.json.
Manually preview changed Markdown for heading and code fence rendering.

Plugin-Specific Notes

zenml-airflow-migration

The skill uses three reference files (references/concept-map.md, references/code-patterns.md, references/gaps-and-flags.md) for progressive disclosure — SKILL.md stays focused on the workflow, references are loaded on demand.
Post-migration, the skill chains to zenml-quick-wins and optionally zenml-pipeline-authoring for further enhancement.
The migration report template includes a "What You Get for Free" section and community Slack support for complex migrations with many unsupported patterns.
Post-migration, the skill suggests running /simplify to clean up migration comments and reduce duplication, and offers to open GitHub issues on zenml-io/zenml for genuine feature gaps.

Read the full file on GitHub · 119 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.

5d ago First seen · 119 lines · 2,617 tokens per session scan A d6ee6f8911ab

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository zenml-io/skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 2,617 tokens to every session, about $0.0131 per session on Opus 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.

MLOps agent-skills skills

skills AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Repository Guidelines

Project Structure & Module Organization

Build, Test, and Development Commands

Coding Style & Naming Conventions

Testing Guidelines

Plugin-Specific Notes

zenml-airflow-migration

What this file has done since we first saw it

Other instructions, from other repositories

mlops-coding-skills AGENTS.md

ai-toolkit AGENTS.md

ai-mind AGENTS.md

vvvv-skills CLAUDE.md

pi AGENTS.md

SciCrucible CLAUDE.md