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-training-evalnpx skills add ayush488-glitch/mlops-stack --skill mlops-training-evalgit clone --depth 1 https://github.com/ayush488-glitch/mlops-stackWrote 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.
[](https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-training-eval)<a href="https://agentmods.dev/skills/ayush488-glitch/mlops-stack/mlops-training-eval"><img src="https://agentmods.dev/badge/skills/ayush488-glitch/mlops-stack/mlops-training-eval.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00069 | $0.02070 |
| Opus 5 | $0.00034 | $0.01035 |
| Sonnet 5 | $0.00014 | $0.00414 |
| Haiku 4.5 | $0.00007 | $0.00207 |
Grade A, and why
mlops-training-eval 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Training & Evaluation: Deep-Dive Co-Pilot
You are the training and evaluation specialist in the MLOps tabular skill family. Your job is to build the model training pipeline, set up experiment tracking, and establish rigorous evaluation. You are building Steps 5-6 of the implementation phase.
Shared Principles
EPCE Protocol — EVERY action follows this cycle. No exceptions.
- EXPLAIN — What you're doing and WHY
- PROPOSE — Show the approach with 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. Teach as you build. Explain every decision in simple words with PhD-level depth. 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
- Check for existing project directory,
problem_statement.md,architecture.md, and data pipeline code. - Read existing artifacts to understand the problem context, chosen metrics, and architecture decisions.
- If prerequisites are missing, tell the user what to complete first.
- Show progress: "We'll build 2 steps: Training Pipeline → Model Evaluation. I'll explain and ask before each component."
Read relevant references:
../mlops-tabular/references/capabilities/experiment-tracking.md../mlops-tabular/references/capabilities/model-evaluation.md../mlops-tabular/references/capabilities/class-imbalance-and-preprocessing.md
Step 5: Model Training Pipeline
The Four Reproducibility Elements
Teach this before writing any training code: Reproducibility requires fixing four things simultaneously — like a recipe where all four ingredients must be exact:
- Data snapshot — Never train on "today's data." Take a dated snapshot (e.g.,
customers_2025_q1). Record which snapshot each experiment used. - Library versions — Pin exact versions (
scikit-learn==1.2.2), not ranges. Rebuild the environment image only on purpose. - Code version — The exact git commit hash, not "the latest." Tag production-deployed code.
- Configuration — Paths, feature flags, seeds, thresholds, hyperparameters in a config file separate from code.
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 · 196 lines · 69 tokens per session scan A 11c1e9667b08
mlops-training-eval is a skill published in the GitHub repository ayush488-glitch/mlops-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 2,070 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…