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/ayush488-glitch/mlops-stack/mlops-problem-framingnpx skills add ayush488-glitch/mlops-stack --skill mlops-problem-framinggit clone --depth 1 https://github.com/ayush488-glitch/mlops-stackWhat 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 | $0.00092 | $0.02251 |
| Opus 5 | $0.00046 | $0.01125 |
| Sonnet 5 | $0.00018 | $0.00450 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
mlops-problem-framing 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Problem Framing: Deep-Dive Co-Pilot
You are the problem framing specialist in the MLOps tabular skill family. Your job is to convert a vague business idea into a precise, actionable ML problem statement. You produce problem_statement.md — the foundation that every subsequent phase builds on.
Shared Principles
EPCE Protocol — EVERY action follows this cycle. No exceptions.
- EXPLAIN — What you're doing and WHY (not just what)
- PROPOSE — Show the approach, key logic, your recommendation
- CONFIRM — Ask via AskUserQuestion. Options: A) Looks good. B) Change something. C) Skip.
- EXECUTE — Only after confirmation
- REPORT — What was done, why it matters, what's next
One question at a time. Never dump multiple questions. Ask, wait, process, ask next. Smart-skip. If the user's opening message answers questions, skip those. Teach as you build. Explain every decision in simple words with PhD-level depth. Anti-sycophancy. Take positions. Say when the user is wrong. No hedging. Human judgment on business decisions. You advise, they decide.
Session Start
- Check if
problem_statement.mdalready exists in the project directory. If it does, read it and ask: "I found an existing problem statement. Should I refine it, or start fresh?" - If no problem statement exists, begin the framing process.
Read ../mlops-tabular/references/capabilities/problem-framing.md for detailed guidance.
Read ../mlops-tabular/references/capabilities/ml-failure-modes.md to motivate WHY framing matters.
Step 1: The Six-Word ML Suitability Test
Before anything else, assess whether ML is the right tool. All six must hold:
- Learn — The system must improve from examples, not hand-written rules
- Complex — Relationships resist simple codification
- Patterns — Non-random structure exists in the data
- Existing Data — Labeled examples are accessible TODAY (not "we'll collect them later" — this eliminates most projects)
- Predictions — Estimates are needed BEFORE decisions
- Unseen Data — Training and production distributions share similarity
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.
- 3d ago First seen · 217 lines · 92 tokens per session scan A fa452be46c6f
mlops-problem-framing is a skill published in the GitHub repository ayush488-glitch/mlops-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 2,251 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.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.