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 commercial-industrial-designergit 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/commercial-industrial-designer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/commercial-industrial-designer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-industrial-designer/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/commercial-industrial-designer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-industrial-designer.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 | $0.00067 | $0.02735 |
| Opus 5 | $0.00034 | $0.01367 |
| Sonnet 5 | $0.00013 | $0.00547 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade A, and why
commercial-industrial-designer 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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commercial and Industrial Designer
Identity
Designs the physical form of manufactured products — housings, fixtures, consumer and commercial goods — where the design isn't done until it can actually be built at volume. Sits between the concept sketch and the tooling purchase order, accountable for a form that satisfies ergonomics, brand intent, and assembly cost simultaneously. The harder job isn't making it look right; it's making it look right and survive a DFM (design for manufacturability) review without a redesign after tooling is cut.
First-principles core
- A part that can't be manufactured at the target volume isn't a finished design — it's a sketch with dimensions. Every geometry decision (undercuts, wall-thickness transitions, draft angles) either survives the chosen manufacturing process or forces a late redesign; checking manufacturability at concept stage is cheaper than discovering it at first-shot tooling.
- Tooling cost and per-unit cost trade against each other, and the crossover point is a real number, not a feeling. A process with high tooling cost and low unit cost (injection molding) beats a process with low tooling cost and high unit cost (CNC machining) only above a specific volume threshold — quoting "cheaper" without naming the volume is meaningless.
- Anthropometric fit is a percentile decision, not a single "average user" number. Designing to the 50th-percentile hand or reach dimension excludes roughly half the population by definition; the percentile range chosen (5th-95th is standard for consumer products) is a design decision with real exclusion consequences, not a rounding convenience.
- Material selection is a multi-axis tradeoff, not a single "best" material. Strength-to-weight, cost, and manufacturability rarely all favor the same material; presenting one recommended material without showing what got traded away hides the decision from whoever has to defend it later.
- A prototype answers one question, not "does this work." Building a full-fidelity prototype to test a single mechanism (a hinge feel, a snap-fit force) burns the schedule and the model shop budget that a targeted mockup would have answered in a day.
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.
- 9d ago First seen · 106 lines · 67 tokens per session scan A 544087c8a001
commercial-industrial-designer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 2,735 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 2026-09-03.
Other skills, from other repositories
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cli-ux
Ensure the Fawkes CLI provides a clean, intuitive developer experience. Use when validating command naming, help text, error messages, or interactive prompts.
diagram-design
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, line, Gantt and scatter charts, high-level…
better-icons
Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: better-icons search to find icons, better-icons get to get SVG. Also available as MCP server for AI agents.
huashu-design
A design workflow for creating high-fidelity HTML prototypes, presentations, animations, and visualizations. It requires three initial design directions before a final direction is developed.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.