mle-workflow

mle-workflow is a skill for Claude Code, Codex from JunMystery/Agent-Guidance-Python. It costs 44 tokens per session (4,633 once invoked), scanned A, a copy of mle-workflow, MIT.

A workflow for turning machine-learning experiments into repeatable production systems, including training, evaluation, deployment, monitoring, and rollback.

In plain words
What is it for?
Use it to plan or review model pipelines, set quality gates, track experiments, deploy models, monitor them, and recover from bad releases.
Why use it?
It addresses failures that appear when notebook code becomes a live system, such as data drift, mismatched artifacts, label leakage, or differences between training and serving.

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/junmystery/agent-guidance-python/mle-workflow
Any agent
npx skills add JunMystery/Agent-Guidance-Python --skill mle-workflow
Clone the repo
git clone --depth 1 https://github.com/JunMystery/Agent-Guidance-Python

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 mle-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/mle-workflow.svg)](https://agentmods.dev/skills/junmystery/agent-guidance-python/mle-workflow)
Your own site
<a href="https://agentmods.dev/skills/junmystery/agent-guidance-python/mle-workflow"><img src="https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/mle-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00044 $0.04633
Opus 5 $0.00022 $0.02316
Sonnet 5 $0.00009 $0.00927
Haiku 4.5 $0.00004 $0.00463

Measured yesterday against content hash 80f288f44f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mle-workflow 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.

Origin

This is a copy

98% identical to mle-workflow — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/mle-workflow/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Machine Learning Engineering Workflow

Use this skill to turn model work into a production ML system with clear data contracts, repeatable training, measurable quality gates, deployable artifacts, and operational monitoring.

When to Activate

  • Planning or reviewing a production ML feature, model refresh, ranking system, recommender, classifier, embedding workflow, or forecasting pipeline
  • Converting notebook code into a reusable training, evaluation, batch inference, or online inference pipeline
  • Designing model promotion criteria, offline/online evals, experiment tracking, or rollback paths
  • Debugging failures caused by data drift, label leakage, stale features, artifact mismatch, or inconsistent training and serving logic
  • Adding model monitoring, canary rollout, shadow traffic, or post-deploy quality checks

Scope Calibration

Use only the lanes that fit the system in front of you. This skill is useful for ranking, search, recommendations, classifiers, forecasting, embeddings, LLM workflows, anomaly detection, and batch analytics, but it should not force one architecture onto all of them.

  • Do not assume every model has supervised labels, online serving, a feature store, PyTorch, GPUs, human review, A/B tests, or real-time feedback.
  • Do not add heavyweight MLOps machinery when a data contract, baseline, eval script, and rollback note would make the change reviewable.
  • Do make assumptions explicit when the project lacks labels, delayed outcomes, slice definitions, production traffic, or monitoring ownership.
  • Treat examples as interchangeable scaffolds. Replace metrics, serving mode, data stores, and rollout mechanics with the project-native equivalents.
  • python-patterns and python-testing for Python implementation and pytest coverage
  • pytorch-patterns for deep learning models, data loaders, device handling, and training loops
  • eval-harness and ai-regression-testing for promotion gates and agent-assisted regression checks
  • database-migrations, postgres-patterns, and clickhouse-io for data storage and analytics surfaces
  • deployment-patterns, docker-patterns, and security-review for serving, secrets, containers, and production hardening

Read the full file on GitHub · 347 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 · 347 lines · 44 tokens per session scan A 80f288f44f02

Subscribe to this mod's changes

mle-workflow is a skill published in the GitHub repository JunMystery/Agent-Guidance-Python (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 4,633 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to mle-workflow, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

debug-evals

Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…

ggozad/haiku.rag · 103 tokens

blockrun

Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…

BlockRunAI/blockrun-mcp · 246 tokens

solr-semantic-search

To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.

griddynamics/rosetta · 24 tokens

td-api-reference

MUST READ before writing TD Python via executepython, setdatcontent, or editdatcontent, and before any heavy build. Parameters, storage, operators, referencing, threading, cook model, heavy-build safety caps.

dylanroscover/Embody · 48 tokens

manage-annotations

MUST READ before creating, modifying, or querying annotations. Contains parameter names, coordinate model, and API quirks.

dylanroscover/Embody · 28 tokens

aba-precision-protocol

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

dcostenco/prism-coder · 48 tokens