mlops-python-package AGENTS.md

Project instructions for a Python package that predicts how many bikes are available, using machine-learning tools and data validation. They explain setup, project commands, testing, formatting, and the package's MLOps workflow.

In plain words
What is it for?
Setting up the project, running its complete validation task, formatting and checking Python code, testing changes, and maintaining its machine-learning tracking and deployment workflow.
Why use it?
They help coding agents follow the repository's required tools and checks instead of bypassing its shared commands or duplicating separately maintained skills.

Instructions file for CodexOpenCode

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/mlops-python-package/agents-md
Clone the repo
git clone --depth 1 https://github.com/fmind/mlops-python-package

Made for: Codex, OpenCode.

Per session 1,248 This file is loaded in full into every session.
When invoked 1,248 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 $0.01248 $0.01248
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured yesterday against content hash 3ee6e58ede2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mlops-python-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 yesterday.

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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 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: bikes — a production-shaped MLOps package that predicts the number of bikes available.
  • Description: reference implementation for the MLOps Coding Course, generated from cookiecutter-mlops-package.
  • Language: Python 3.14+ (pyproject.toml), managed with uv.
  • Stack: MLflow (tracking, registry, projects, evaluation), scikit-learn, pandas, Pydantic + Pandera validation, OmegaConf YAML configs, loguru.
  • Skills: the reusable practices behind this package are published as Agent Skills in mlops-coding-skills. Install them from there rather than vendoring a copy here — a copy drifts, and this repository already lost a month to proving it.

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, build. This is the gate; CI runs this exact task and nothing else.
  • Install: mise run install — sync the virtualenv (uv sync) and install git hooks.
  • Format: mise run formatruff (import sort + format, including Python inside Markdown) and dprint (JSON/Markdown/TOML/YAML).
  • Check: mise run checkruff lint, ty types, pip-audit deps, dprint/validate-pyproject/uv lock format, gitleaks secrets, trivy filesystem scan, hadolint Dockerfile, actionlint + zizmor workflows.
  • Test: mise run testpytest with coverage (fails under 100%); mise run test:parallel is a faster, coverage-free local loop.
  • Build: mise run builduv build (wheel + sdist); mise run build:image builds the Docker image.
  • Docs: mise run docspdoc API reference into docs/.
  • MLflow jobs: mise run project runs every job; mise run project:run <name> runs one (confs/<name>.yaml).

Read the full file on GitHub · 46 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. yesterday First seen · 46 lines · 1,248 tokens per session scan A 3ee6e58ede2b

Subscribe to this mod's changes

mlops-python-package AGENTS.md is an instructions file published in the GitHub repository fmind/mlops-python-package (1,416 stars, last pushed 8d ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0062 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.