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.
npx agentmods add instructions/zenml-io/zenml/agents-mdgit clone --depth 1 https://github.com/zenml-io/zenmlWrote 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.
[](https://agentmods.dev/instructions/zenml-io/zenml/agents-md)<a href="https://agentmods.dev/instructions/zenml-io/zenml/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/zenml/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01575 | $0.01575 |
| Opus 5 | $0.00788 | $0.00788 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
zenml 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZenML Codex Agent Guidelines
ZenML is an extensible open-source MLOps framework for creating production-ready
ML pipelines. This root guide contains rules that must be loaded for every
Codex session in this repository. For detailed workflows, examples, and
subsystem recipes, use .agents/skills/zenml-repo-workflows/SKILL.md.
Project Structure
src/zenml/- Core source code.tests/- Unit and integration tests.docs/book/- Source documentation.examples/- Example projects.scripts/- Development utilities.
Always-Loaded Rules
- Use US English spelling in code, comments, docstrings, and documentation.
- Use Python 3.10+ compatible code.
- Type hint function parameters and return values.
- Follow Google Python style for docstrings. Include
Args,Returns,Yields, andRaisessections whenever the function contract requires them; do not use a summary-only docstring to omit applicable sections. - Prefer clear names and small functions over explanatory comments.
- Comments should explain intent, trade-offs, constraints, invariants, and tricky edge cases. Avoid comments that restate obvious code.
- Do not use multi-line banner comments to group classes or functions.
- Prefer typed contracts over
getattr/hasattrcapability checks when static typing can express the requirement. - Private methods and functions with a leading underscore should not be called outside their class or module.
- Integrations should avoid using ZenML private methods because externalized integrations will not be protected by in-repo type checks.
Common Commands
- Format before committing:
bash scripts/format.sh. - Check quality:
bash scripts/lint.sh. - Run targeted tests only:
pytest tests/unit/path/to/test_file.pyorpytest tests/unit/path/to/test_file.py::test_specific_function. - Do NOT run the entire local test suite by default; many tests need special environments.
- If you make changes after running tests, rerun the relevant tests.
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.
- 4d ago First seen · 149 lines · 1,575 tokens per session scan A 63f45f69cffe
zenml AGENTS.md is an instructions file published in the GitHub repository zenml-io/zenml (5,572 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,575 tokens to every session, about $0.0079 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.
Other instructions, from other repositories
mlops-python-package AGENTS.md
AGENTS.md instructions for fmind/mlops-python-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
AzureML_industry_labs AGENTS.md
Instructions for Azure-Samples/AzureML_industry_labs, covering agents.md, directory structure, root, lab structure (standard template) and existing labs.
opsml CLAUDE.md
Claude Code instructions for demml/opsml, covering claude.md and claude code notes.
opsml AGENTS.md
AGENTS.md instructions for demml/opsml, covering agents.md, what opsml is, common commands, task runner and rust.
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
streamlit agents.instructions.md
Instructions for streamlit/streamlit, covering agent definitions, file format, best practices, cross-platform compatibility and slash command support.