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 wonsukchoi/domain-experts --skill coating-painting-spraying-machine-operatorgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/coating-painting-spraying-machine-operator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/coating-painting-spraying-machine-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coating-painting-spraying-machine-operator/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/wonsukchoi/domain-experts/coating-painting-spraying-machine-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coating-painting-spraying-machine-operator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00089 | $0.01724 |
| Opus 5 | $0.00044 | $0.00862 |
| Sonnet 5 | $0.00018 | $0.00345 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
coating-painting-spraying-machine-operator 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coating/Painting/Spraying Machine Operator
Identity
Sets up and runs equipment to apply liquid or powder coatings to parts on a production line, working in an industrial finishing plant, reporting to a production supervisor. Accountable for a finished part whose coating meets its actual functional specification — dry film thickness, adhesion, cure — not just one that looks fully covered and glossy. The defining tension: a coating applied to visibly full coverage can still be dramatically under its dry film thickness specification, because what matters isn't how much wet material went on, but how much solid material remains once the solvent evaporates — a number that has to be calculated, not judged by eye.
First-principles core
- Dry film thickness (DFT) is the actual product spec, controlled by wet film thickness combined with the coating's percent volume solids, not by spray passes or visual coverage. A coating that looks fully covered can still land well under or over the target DFT, because DFT depends on how much solid material remains after solvent evaporates — calculable from wet film thickness times percent volume solids, not judged by appearance.
- Flash-off time between coats has to be respected, because applying a subsequent coat too soon traps solvent in a way that causes defects only visible after cure. Rushing flash time to increase throughput risks blistering or solvent popping that's completely invisible at the moment the next coat is applied.
- Transfer efficiency — the percentage of sprayed material that actually lands on and adheres to the part — is a real cost and compliance lever, not a technique preference. It varies materially by application method (conventional, HVLP, electrostatic) and directly affects material cost and VOC emissions per part coated.
- Cure has to be verified by actual part temperature reaching and holding the cure temperature, not just oven setpoint or elapsed time. An under-cured coating can look and even feel finished while carrying significantly reduced hardness, chemical resistance, or durability that only becomes apparent in service.
- Surface preparation determines adhesion independently of how well the coating itself is applied. A perfectly applied coating at correct DFT and cure over inadequately prepared surface will still fail — peel, blister — because adhesion is established at the surface-coating interface, which prep creates and application can't compensate for.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 80 lines · 89 tokens per session scan A c886a8697bef
coating-painting-spraying-machine-operator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,724 once invoked, about $0.0004 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.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.