What is cookiecutter-mlops-package AGENTS.md?

Repository instructions for an AI coding agent working on a Cookiecutter template that creates Python packages for machine-learning operations. They describe the project layout, setup commands, testing rules, and coding conventions.

Use them when changing the template, its tests, setup process, or shared configuration.

They give the agent the project context and the exact checks required for a change to be accepted. This helps avoid editing generated-template files incorrectly or skipping the repository’s standard checks.

cookiecutter-mlops-package AGENTS.md — Instructions file by fmind

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/fmind/cookiecutter-mlops-package/agents-md

Clone the repo

git clone --depth 1 https://github.com/fmind/cookiecutter-mlops-package

Made for: Codex, OpenCode.

Per session 1,296 This file is loaded in full into every session.

When invoked 1,296 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	$0.01296	$0.01296
Opus 5	$0.00648	$0.00648
Sonnet 5	$0.00259	$0.00259
Haiku 4.5	$0.00130	$0.00130

Measured 3d ago against content hash 6152d26cc44e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cookiecutter-mlops-package 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 3d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Context and rules for AI agents working in this repository. Humans should start with README.md.

Project overview

Name: cookiecutter-mlops-package — a Cookiecutter template that scaffolds MLOps Python packages.
Layout: {{cookiecutter.repository}}/ holds the template sources (raw Jinja); tests/test_cookiecutter.py bakes the template and runs the generated project's full toolchain.
Language: Python 3.14+ (pyproject.toml), managed with uv.
Reference: mlops-python-package is the reference implementation. Shared configuration files should differ from it only by cookiecutter variables; diff against it before changing the template.

Setup & core commands

All work goes through mise (see mise.toml); git hooks (lefthook.yml) and CI call the same tasks.

Everything: mise run all — format, check, test. This is the gate; CI runs this exact task and nothing else. There is no build step: [tool.uv] package = false, this repository is a test suite, not a distribution.
Install: mise install provisions the pinned toolchain (run_auto_install is off), then mise run install syncs the virtualenv (uv sync) and installs git hooks.
Format: mise run format — ruff (import sort + format, including Python inside Markdown) and dprint (JSON/Markdown/TOML/YAML).
Check: mise run check — ruff lint, ty types, pip-audit deps, dprint/validate-pyproject/uv lock format, gitleaks secrets, trivy filesystem scan, actionlint + zizmor workflows.
Test: mise run test — pytest bakes the template and runs mise trust/mise install/git init/mise run all/... inside the generated project. Needs docker running and takes several minutes.

Definition of done

A change is complete only when, locally, mise run all passes warning-free — which includes the bake test actually generating a project and passing that project's own gate. Fix root causes — never weaken an assertion, add a skip/xfail, loosen a type, or suppress a lint error to force a green result.

Read the full file on GitHub · 43 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.

3d ago First seen · 43 lines · 1,296 tokens per session scan A 6152d26cc44e

Subscribe to this mod's changes

cookiecutter-mlops-package AGENTS.md is an instructions file published in the GitHub repository fmind/cookiecutter-mlops-package (442 stars, last pushed 9d ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0065 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.

MLOps best-practices cookiecutter machine-learning template

cookiecutter-mlops-package AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Project overview

Setup & core commands

Definition of done

What this file has done since we first saw it

Other instructions, from other repositories

zenml CLAUDE.md

zenml AGENTS.md

mlops-python-package AGENTS.md

weightslab AGENTS.md

plexe AGENTS.md

zero-to-ai snyk_rules.instructions.md