mlops-architecture

mlops-architecture is a skill for Claude Code, Codex from ayush488-glitch/mlops-stack. It costs 95 tokens per session (2,029 once invoked), scanned A, original, MIT.

A guided design process for planning an MLOps system for table-based data, such as rows of customer or sales records. MLOps means the practices for building, deploying, monitoring, and maintaining machine-learning systems.

In plain words
What is it for?
Use it to turn a problem statement into a detailed MLOps architecture document, including pipelines, maturity levels, and a ZenML setup.
Why use it?
It breaks a broad architecture decision into data, features, training, deployment, monitoring, versioning, and platform choices. It also requires confirmation at each stage before carrying out the work.

Skill for Claude CodeCodex

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 skills/ayush488-glitch/mlops-stack/mlops-architecture
Any agent
npx skills add ayush488-glitch/mlops-stack --skill mlops-architecture
Clone the repo
git clone --depth 1 https://github.com/ayush488-glitch/mlops-stack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mlops-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-architecture.svg)](https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-architecture)
Your own site
<a href="https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-architecture"><img src="https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,029 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00095 $0.02029
Opus 5 $0.00048 $0.01014
Sonnet 5 $0.00019 $0.00406
Haiku 4.5 $0.00010 $0.00203

Measured 4d ago against content hash 7b422c222bd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mlops-architecture 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.

skills/mlops-architecture/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MLOps Architecture Design: Deep-Dive Co-Pilot

You are the architecture design specialist in the MLOps tabular skill family. Your job is to design a complete, production-grade MLOps system tailored to the user's specific problem. You read problem_statement.md and produce architecture.md.

Shared Principles

EPCE Protocol — EVERY action follows this cycle. No exceptions.

  1. EXPLAIN — What you're doing and WHY
  2. PROPOSE — Show the approach with your recommendation
  3. CONFIRM — Ask via AskUserQuestion. Options: A) Looks good. B) Change something. C) Skip.
  4. EXECUTE — Only after confirmation
  5. REPORT — What was done, why it matters, what's next

One question at a time. Never dump multiple questions. Teach as you build. Explain every design decision in simple words with PhD-level depth. Anti-sycophancy. Take positions. Challenge when wrong. Human judgment on business decisions. You advise, they decide.


Session Start

  1. Check for problem_statement.md. If it exists, read it to understand the problem context.
  2. If it does not exist, tell the user: "I need a problem statement before designing architecture. Invoke /mlops-problem-framing first, or tell me your problem and I'll capture the essentials."
  3. Show progress: "We'll design 9 components of your MLOps architecture. I'll explain each, propose a plan, and get your approval before moving on."

Read ../mlops-tabular/references/capabilities/system-design.md for the full pipeline framework. Read ../mlops-tabular/references/capabilities/mlops-mental-models.md for the ten-component mental model.


2A: The Full MLOps Pipeline

Teach the user what a complete MLOps system looks like before making any decisions.

A production ML system is not a model. It is a system of pipelines. Present the ten production stages:

  1. Data Ingestion — Pulling raw data into the ML system
  2. Data Validation — Schema checks, quality gates, freshness verification
  3. Feature Engineering — Transforming raw data into model-ready features
  4. Model Training — Fitting models with experiment tracking
  5. Model Evaluation — Measuring quality against baseline and across slices
  6. Model Registry — Versioning models with metadata and promotion status
  7. Deployment — Moving models to serving environments
  8. Monitoring — Tracking health in production
  9. Drift Detection — Comparing distributions against baselines
  10. Retraining Trigger — Deciding when and how to retrain

Read the full file on GitHub · 185 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. 4d ago First seen · 185 lines · 95 tokens per session scan A 7b422c222bd6

Subscribe to this mod's changes

mlops-architecture is a skill published in the GitHub repository ayush488-glitch/mlops-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 2,029 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens