zenml CLAUDE.md

zenml CLAUDE.md is an instructions file for coding agents from zenml-io/zenml. It costs 4,696 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for ZenML when using Claude Code, an AI coding assistant. They describe the project layout, coding standards, commenting policy, and a way to query ZenML’s documentation through an MCP connection.

In plain words
What is it for?
Use them when editing ZenML code, tests, docs, examples, or scripts, and when checking documented behavior through the configured documentation service.
Why use it?
They help the assistant follow ZenML’s conventions and consult current project documentation instead of relying only on assumptions.

Instructions file

About the project

ZenML is a Python framework for turning machine-learning and AI workflows into tracked pipelines that run on different infrastructure backends. It is for ML and AI engineers building applications such as model-training workflows, language-model systems, and agent loops in company environments.

zenml-io/zenml · 5,575 stars · on GitHub

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/zenml/claude-md
Clone the repo
git clone --depth 1 https://github.com/zenml-io/zenml

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 zenml CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zenml-io/zenml/claude-md.svg)](https://agentmods.dev/instructions/zenml-io/zenml/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zenml-io/zenml/claude-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/zenml/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,696 This file is loaded in full into every session.
When invoked 4,696 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.

ModelPer sessionOnce invoked
Fable 5 $0.04696 $0.04696
Opus 5 $0.02348 $0.02348
Sonnet 5 $0.00939 $0.00939
Haiku 4.5 $0.00470 $0.00470

Measured 5d ago against content hash f78240ad4eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zenml 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 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.

CLAUDE.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZenML Claude Code Guidelines

This document provides guidance for Claude Code when working with the ZenML codebase. ZenML is an extensible, open-source MLOps framework for creating production-ready ML pipelines.

Project Structure

  • /src/zenml/ - Core source code
  • /tests/ - Test suite (unit, integration)
  • /docs/ - Documentation
  • /examples/ - Example projects
  • /scripts/ - Development utilities

Use filesystem navigation tools to explore the codebase structure as needed.

Use ZenML Docs via MCP

Claude Code can query ZenML documentation via the built-in GitBook MCP server: https://docs.zenml.io/~gitbook/mcp. This enables real-time, source-of-truth lookups from the docs while you code, reducing hallucinations and speeding up feature discovery.

Quick setup (CLI):

claude mcp add zenmldocs --transport http https://docs.zenml.io/~gitbook/mcp

Note: The MCP server indexes the latest released docs, not the develop branch. For full setup details and editor alternatives, see docs/book/reference/llms-txt.md.

Code Style & Quality Standards

  • Use US English spelling in all code, comments, docstrings, and documentation (e.g., "initialize", "stabilize", "color"). The CI enforces this via typos (configured in .typos.toml).

Commenting policy — explain why, not what

  • Use comments to document intent, trade‑offs, constraints, invariants, and tricky edge cases—i.e., why the code is this way—rather than narrating changes. Prefer self‑explanatory code; add comments only where extra context is needed. Write for a reader 6+ months later.
  • Use for: complex logic/algorithms, non‑obvious design decisions, business rules/constraints, API purpose/contracts, edge cases.
  • Avoid: change‑tracking comments ("Updated from previous version", "New implementation", "Changed to use X instead of Y", "Refactored this section").
  • Avoid simple explanatory comments, where it is already clear from the code itself.
  • Avoid useless one-line comments interleaved with code that merely narrate the implementation. Favor expressive names and small, focused functions.

Read the full file on GitHub · 422 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.

  1. 5d ago First seen · 422 lines · 4,696 tokens per session scan A f78240ad4eaa

Subscribe to this mod's changes

zenml CLAUDE.md is an instructions file published in the GitHub repository zenml-io/zenml (5,575 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,696 tokens to every session, about $0.0235 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 2026-08-30.