mlops

mlops is a skill for Claude Code, Codex from arbazkhan971/godmode. It costs 10 tokens per session (1,136 once invoked), scanned A, original, MIT.

A guide to putting trained machine-learning models into production so applications can send them data and receive predictions. It covers model readiness, serving choices, and inference optimisation.

In plain words
What is it for?
Use it to choose a serving system, prepare deployment artifacts, measure prediction performance, and consider quantisation or other size and speed improvements.
Why use it?
It provides checks for evaluation, fairness, saved model files, input and output formats, response time, and model size before deployment.

Skill for Claude CodeCodex

Part of the godmode plugin — 133 skills, 1 command, 9 agents, 3 MCP servers shipped together

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/arbazkhan971/godmode/mlops
Any agent
npx skills add arbazkhan971/godmode --skill mlops
Clone the repo
git clone --depth 1 https://github.com/arbazkhan971/godmode

Made for: Claude Code, Codex.

Or install godmode, the plugin that ships this one along with the rest of its 133 skills, 1 command, 9 agents, 3 MCP servers.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/arbazkhan971/godmode/mlops.svg)](https://agentmods.dev/skills/arbazkhan971/godmode/mlops)
Your own site
<a href="https://agentmods.dev/skills/arbazkhan971/godmode/mlops"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/mlops.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 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 $0.00010 $0.01136
Opus 5 $0.00005 $0.00568
Sonnet 5 $0.00002 $0.00227
Haiku 4.5 $0.00001 $0.00114

Measured yesterday against content hash d46bdea5e69f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mlops 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.

skills/mlops/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate When

  • /godmode:mlops, "deploy model", "model serving"
  • "model drift", "retrain", "A/B test models"
  • Trained model ready for production deployment

Workflow

1. Model Readiness

Model: <name and version>
Source: EXP-<ID>
Checklist:
  [ ] Evaluation complete (test metrics documented)
  [ ] Bias/fairness check passed
  [ ] Artifacts saved (weights, config, preprocessor)
  [ ] Input/output schema documented
  [ ] Latency benchmarked (< target p99 ms)
  [ ] Size acceptable (< N MB)

IF latency p99 > 100ms: apply optimization. IF model size > 500MB: consider distillation/pruning.

2. Serving Infrastructure

Options:
  TF Serving: TensorFlow models, gRPC/REST
  Triton: multi-framework, ONNX/TensorRT
  SageMaker: managed AWS, auto-scaling
  FastAPI/Ray Serve: custom, flexible
# Check for serving frameworks
pip list | grep -iE "fastapi|ray|triton|sagemaker"
ls model_repository/ serve/ 2>/dev/null

3. Inference Optimization

| Optimization | Latency | Size | Accuracy |
| Baseline FP32 | <ms> | <MB> | <val> |
| FP16 quant | <ms> | <MB> | <val> |
| INT8 quant | <ms> | <MB> | <val> |
| ONNX | <ms> | <MB> | <val> |
| Distillation | <ms> | <MB> | <val> |

IF accuracy drop > 1% from quantization: use FP16 only. IF latency target not met: try TensorRT or distillation.

Batching: static (fixed workload), dynamic (variable traffic, max_queue_delay_ms), adaptive (auto-tune).

4. Model Versioning

| Version | Metric | Status | Traffic |
| v3.1 | F1=0.891 | CHAMPION | 90% |
| v3.2 | F1=0.903 | CANARY | 10% |
| v3.0 | F1=0.879 | ARCHIVED | 0% |
Lifecycle: STAGED->CANARY->CHAMPION->ARCHIVED

5. A/B Testing

Champion: v<N>  Challenger: v<N>
Split: <champion%>/<challenger%>
Routing: random|user-hash|feature-flag
Duration: <minimum days>
Sample size: <minimum per variant>
Success: primary metric >= <threshold> improvement
Guardrails: latency p99, error rate, business KPIs

IF p-value > 0.05 after min samples: no winner. IF guardrail regresses > 2%: stop test, revert.

Read the full file on GitHub · 150 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 · 150 lines · 10 tokens per session scan A d46bdea5e69f

Subscribe to this mod's changes

mlops is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 1,136 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

jobs-to-be-done

Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…

wondelai/skills · 137 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…

zjunlp/SkillNet · 71 tokens

ralph-specum-requirements

This skill should be used only when the user explicitly asks to use $ralph-specum-requirements, or explicitly asks Ralph Specum in Codex to run the requirements phase.

tzachbon/smart-ralph · 45 tokens

biome

Repository guidance for using Biome as the formatter, linter, and code quality tool within the hr-skills monorepo.

tuanductran/hr-skills · 29 tokens

dashboard-builder

Build and manage recurring dashboard views of key metrics — set up daily/weekly monitoring with saved metrics and segments. Use when the user wants to create a recurring dashboard, set up KPI monitoring, or establish a baseline.

reatlat/fullstory-claude-plugin · 46 tokens