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 skills add zorost/AI-Engineering-Lab --skill using-zorost-skillsgit clone --depth 1 https://github.com/zorost/AI-Engineering-LabWrote 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/zorost/ai-engineering-lab/using-zorost-skills)<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/using-zorost-skills"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/using-zorost-skills/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.
<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/using-zorost-skills"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/using-zorost-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00043 | $0.00849 |
| Opus 5 | $0.00022 | $0.00425 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
using-zorost-skills 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Zorost Skills
1 · Purpose
Make the agent choose the right skill for the task at hand, run it to its verification gate, and report honestly when no skill fits.
2 · When to use
- At the start of any non-trivial AI engineering task when this catalog is installed.
- When the agent is improvising a workflow that a catalog skill already covers.
Do not use this meta-skill for trivial one-line questions or file lookups. Answer those directly.
3 · Inputs
- The user's request, verbatim.
- The catalog table in
reference/skills/agent-skills/README.md(names + descriptions).
4 · Procedure
- Restate the task in one sentence, starting with a verb: "Build…", "Fix…", "Decide…", "Deploy…".
- Scan the catalog descriptions. Match on the task's stage, not its nouns:
deciding whether to fine-tune is
fine-tune-readiness, notlocal-model-fit. - If exactly one skill matches, load its full
SKILL.mdand follow its procedure. - If two skills match, run them in lifecycle order: Define before Build, Build before Verify, Verify before Ship.
- If no skill matches, say so in one line, "No catalog skill covers X; proceeding ad hoc", then proceed. Do not force a near-match.
- While running a skill, obey its STOP conditions. A stopped skill is a success state with a report, not a failure to hide.
- After the skill exits, state which skill ran and what its Verify section produced.
- If the skill's steps proved wrong or stale, open an issue or amend the skill file. A wrong skill that stays wrong teaches the next run to be wrong.
5 · Anti-rationalization
| Excuse | Answer |
|---|---|
| "Loading the skill wastes tokens." | One SKILL.md body is cheaper than one wrong approach. |
| "I already know how to do this." | The skill encodes the gates you skip when you improvise. Run it. |
| "Two skills half-match; I'll blend them." | Run the earlier-stage skill first. Blending skips gates. |
| "The task is small, skip the skill." | Small tasks are where bad habits form. If it matters, run the skill. If it does not, say so and answer directly. |
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.
- 11d ago First seen · 82 lines · 43 tokens per session scan A 0384bfa8cefb
using-zorost-skills is a skill published in the GitHub repository zorost/AI-Engineering-Lab (303 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 849 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
fine-tuning-os
Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…