What is mlops-coding-skills AGENTS.md?

Contributor instructions for a collection of reusable MLOps skills, where MLOps means the practices used to build, deploy, and maintain machine-learning systems.

Use them when editing or verifying an MLOps skill, checking its guidance against the reference Python package, or running the project’s standard validation tasks.

They define the project’s purpose, reference technology versions, setup commands, and definition of done, while noting that the repository contains instructions rather than an application.

mlops-coding-skills AGENTS.md — Instructions file by MLOps-Courses

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/mlops-courses/mlops-coding-skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/MLOps-Courses/mlops-coding-skills

Made for: Codex, OpenCode.

Per session 1,092 This file is loaded in full into every session.

When invoked 1,092 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	$0.01092	$0.01092
Opus 5	$0.00546	$0.00546
Sonnet 5	$0.00218	$0.00218
Haiku 4.5	$0.00109	$0.00109

Measured 2d ago against content hash 2f9aa39c8507, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mlops-coding-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 2d 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 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: mlops-coding-skills — a collection of Anthropic-style Agent Skills for MLOps.
Purpose: package the methodology of the MLOps Coding Course as reusable skills that AI coding assistants (Antigravity, Gemini CLI, GitHub Copilot, Claude Code) can load on demand.
Content: each mlops-*/ folder holds one SKILL.md (YAML frontmatter + Markdown instructions). There is no application code to build and no test suite to run.
Reference: the skills describe the stack implemented in mlops-python-package — Python 3.14, uv, mise, Ruff 0.16, ty 0.0.69, pytest, MLflow 3.15 on a SQL tracking store (sqlite:///mlflow.db, not the deprecated file store). Verify an instruction against that package before writing 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, then check. This is the gate; CI runs this exact task and nothing else.
Install: mise install installs the pinned tools; mise run install installs the git hooks (lefthook).
Format: mise run format — dprint formats JSON, Markdown, TOML, and YAML, including the seven SKILL.md deliverables.
Check: mise run check — dprint check (format), actionlint + zizmor (workflows), gitleaks (secrets in the last 100 commits), trivy (filesystem scan), check:frontmatter (name equals folder), and gh skill publish --dry-run (Agent Skills specification).
Tools are pinned in mise.toml and locked in mise.lock; run mise lock after changing a version.

Definition of done

A change is complete only when, locally, mise run all passes with no findings and the seven SKILL.md files still describe commands that exist in the reference package. Fix root causes — never weaken an assertion, exclude a file, or skip a check to force a green result.

Read the full file on GitHub · 41 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.

2d ago First seen · 41 lines · 1,092 tokens per session scan A 2f9aa39c8507

Subscribe to this mod's changes

mlops-coding-skills AGENTS.md is an instructions file published in the GitHub repository MLOps-Courses/mlops-coding-skills (22 stars, last pushed 23d ago), licensed MIT. It adds 1,092 tokens to every session, about $0.0055 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 agent-skills ai ai-coding generative-ai skills

mlops-coding-skills 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

superpowers-zh CLAUDE.md

superpowers-zh GEMINI.md

spec-superflow GEMINI.md

spec-superflow copilot-instructions.md

web-dev-skills AGENTS.md

claude-skills CLAUDE.md