mlops-deploy-monitor

mlops-deploy-monitor is a skill for Claude Code from ayush488-glitch/mlops-stack. It costs 89 tokens per session (2,653 once invoked), scanned A, original, MIT.

A guide for putting machine-learning models that use table-based data into production and watching how they perform. It covers model changes, data changes, monitoring, and incident response.

In plain words
What is it for?
Use it to plan deployment methods such as canary or blue-green releases, set drift thresholds, monitor production behavior, and prepare response procedures.
Why use it?
It helps teams detect when predictions become unreliable and respond when a deployed model or its data stops behaving as expected.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it to plan deployment methods such as canary or blue-green releases, set drift thresholds, monitor production behavior, and prepare response procedures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor
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.

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

Made for: Claude Code.

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-deploy-monitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor/github.svg)](https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor)
Your own site
<a href="https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor"><img src="https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mlops-deploy-monitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor"><img src="https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-deploy-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00089 $0.02653
Opus 5 $0.00044 $0.01326
Sonnet 5 $0.00018 $0.00531
Haiku 4.5 $0.00009 $0.00265

Measured 11d ago against content hash ada7843d9ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mlops-deploy-monitor 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 11d 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-deploy-monitor/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MLOps Deploy & Monitor: Deep-Dive Co-Pilot

You are the deployment and monitoring specialist in the MLOps tabular skill family. Your job is to deploy the model safely, set up production monitoring, build incident response capability, and harden the system for production. You are building Steps 7-10 plus the Ship phase.

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 monitoring decision, every deployment strategy, every threshold choice. Build incrementally. One step, verify, next. Anti-sycophancy. Take positions. Challenge when wrong. Fetch Before Generate. Check installed versions before writing framework code.


Session Start

  1. Check for existing project, architecture.md, trained model in registry.
  2. Read architecture to understand deployment and monitoring plans.
  3. If prerequisites are missing, tell the user what to complete first.
  4. Show progress: "We'll build 4 steps: Drift Detection → Deployment → Monitoring → Production Hardening, then Ship."

Read relevant references:

  • ../mlops-tabular/references/capabilities/drift-detection.md
  • ../mlops-tabular/references/capabilities/deployment-strategies.md
  • ../mlops-tabular/references/capabilities/model-monitoring.md
  • ../mlops-tabular/references/capabilities/incident-response.md
  • ../mlops-tabular/references/capabilities/model-registry.md
  • ../mlops-tabular/references/capabilities/production-readiness.md

Step 7: Drift Detection

Two Types of Drift

Teach the distinction — it determines the response:

Data Drift (Covariate Shift) — Input feature distributions shift, but the relationship between features and target stays the same. P(X) changes, P(Y|X) stays.

Example: "A marketing campaign reaches a new income segment. Your model sees borrowers with different income distributions, but the relationship between income and default hasn't changed. The model may still be correct in principle, but it's operating in a region where it has little training data."

Read the full file on GitHub · 267 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. 11d ago First seen · 267 lines · 89 tokens per session scan A ada7843d9ffd

Subscribe to this mod's changes

mlops-deploy-monitor is a skill published in the GitHub repository ayush488-glitch/mlops-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 2,653 once invoked, about $0.0004 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

tensorrt-llm

High-throughput LLM inference on NVIDIA GPUs.

NousResearch/hermes-agent · 18 tokens

google-cloud-solution-guided-gke-ai-migration

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…

google/skills · 157 tokens

agent-platform-tuning

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).

google/skills · 64 tokens

gke-inference

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).

google/skills · 74 tokens

agent-platform-endpoint-management

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…

google/skills · 64 tokens

modal

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

K-Dense-AI/scientific-agent-skills · 65 tokens