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 skills/mlops-courses/mlops-coding-skills/mlops-initializationnpx skills add MLOps-Courses/mlops-coding-skills --skill mlops-initializationgit clone --depth 1 https://github.com/MLOps-Courses/mlops-coding-skillsWhat 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 | $0.00050 | $0.02776 |
| Opus 5 | $0.00025 | $0.01388 |
| Sonnet 5 | $0.00010 | $0.00555 |
| Haiku 4.5 | $0.00005 | $0.00278 |
Grade C, and why
mlops-initialization scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- If missing, install it: `curl -LsSf https://astral.sh/uv/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If missing, install it: `curl -LsSf https://astral.sh/uv/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Initialization
Goal
To initialize a robust, production-ready MLOps project structure using the modern Python toolchain (uv), industry-standard version control (git), a shared task runner (mise), and a configured development environment (VS Code). This skill ensures reproducibility, collaboration, and high code quality from day one.
Prerequisites
- Language: Python 3.14 (latest stable)
- Manager:
uv(replaces pip, venv, poetry, pyenv) - Tasks:
mise(replaces make/just, and pins the toolchain) - VCS: Git
- IDE: VS Code (recommended)
Instructions
1. System & Toolchain Verification
Before modifying files, verify that the essential tools are available.
- Check
uv:- Ensure
uvis installed:uv --version - If missing, install it:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Ensure
- Check
git:- Ensure
gitis installed:git --version
- Ensure
- Check
mise:- Ensure
miseis installed:mise --version misepins every non-Python tool (dprint,gitleaks,trivy,actionlint, ...) so contributors and CI resolve identical binaries.
- Ensure
2. Project Initialization
Initialize the project structure using uv to ensure modern standards (pyproject.toml).
- Create Directory (if not already inside):
mkdir <project_name> && cd <project_name>
- Initialize Project:
- Run
uv init - This creates
pyproject.toml,.python-version, and a basichello.py.
- Run
- Configure
pyproject.toml:-
Update metadata:
name,version,description,authors,license. -
Set requires-python: Ensure it matches the project's target environment (e.g.,
>=3.14). -
Declare the license the PEP 639 way:
licenseis an SPDX expression (a plain string), and the file itself is listed inlicense-files. The oldlicense = { file = "LICENSE" }table form is deprecated and rejected by current build backends. -
Example Structure:
[project] name = "my-mlops-project" version = "0.1.0" description = "A robust MLOps project." readme = "README.md" requires-python = ">=3.14" license = "MIT" # SPDX expression (PEP 639) license-files = ["LICENSE.txt"] # the file(s) shipped in the distribution authors = [{ name = "Your Name", email = "[email protected]" }] dependencies = [ "loguru>=0.7.3", "mlflow>=3.15.1", # MLflow 3.15 still declares `pandas<3`, so the pandas 3.x line is unreachable # here; keep the floor permissive and let `uv.lock` pin the tested version. "pandas>=2.3.3", "pydantic>=2.13.4", "scikit-learn>=1.9.0", ] [project.urls] Repository = "https://github.com/username/my-mlops-project" Documentation = "https://username.github.io/my-mlops-project" # PEP 735 dependency groups (not shipped with the package). [dependency-groups] dev = [ "lefthook>=2.1.10", "pip-audit>=2.10.1", "pytest>=9.1.1", # Ruff 0.16 rewrote the default rule set and now formats Python inside Markdown: # an older Ruff disagrees with a 0.16-formatted repository, so floor it here. "ruff>=0.16.2", "ty>=0.0.69,<0.1", # pre-1.0: pin a compatible range ] [build-system] # Keep the upper bound at least one minor ahead of the pinned `uv`: without it # `uv build` warns, and a future breaking `uv_build` silently breaks the sdist. requires = ["uv_build>=0.9,<0.13"] build-backend = "uv_build"
-
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 · 212 lines · 50 tokens per session scan C 24f17b9b7010
mlops-initialization is a skill published in the GitHub repository MLOps-Courses/mlops-coding-skills (22 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 2,776 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.