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 skillmds/skillmd --skill bmw-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/bmw-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/bmw-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/bmw-design-analysis/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/skillmds/skillmd/bmw-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/bmw-design-analysis.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 | $0.00121 | $0.07414 |
| Opus 5.5 | $0.00048 | $0.02966 |
| Sonnet 5 | $0.00024 | $0.01483 |
| Haiku 4.5 | $0.00012 | $0.00741 |
Grade A, and why
BMW-design-analysis 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 4d 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 — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
BMW's corporate site carries a far more measured, corporate-automotive interface than its motorsport-bombastic cousin BMW M. The atmosphere is light: {colors.canvas} (#ffffff) is the base surface, {colors.surface-card} (#fafafa) carries the soft-grey card plates, and dark navy {colors.surface-dark} (#1a2129) appears only inside hero bands — one per page, framing the lead model render.
Type runs BMW's licensed BMW Type Next Latin at two weights: heavy 700 (display + button + nav) and Light 300 (body + secondary copy). That contrast — heavy display next to thin paragraph — is the editorial signature, channeling the brand's "European-engineered" voice. Weight 500 is deliberately absent; weight 400 only appears on caption and nav-link in neutral utility contexts.
The brand action color, BMW corporate blue ({colors.primary} — #1c69d4), works alone across every primary CTA — buttons are rectangular, 0px corner, with white type. The site rotates a blue-button + dark-navy-hero combination across page rhythm. The M tricolor stripe ({colors.m-blue-light} → {colors.m-blue-dark} → {colors.m-red}) only appears in motorsport contexts and as M-model badges/dividers — never in the corporate site's main language.
The configuration and reservation flows add a dealer-side inventory UI on top of the same system — filter chips, model cards, price tables — but typography and color stay identical; only density goes up.
Key Characteristics:
- Light
{colors.canvas}is the base surface; dark navy{colors.surface-dark}appears only inside hero bands — page rhythm relies on contrast. - BMW corporate blue (
{colors.primary}— #1c69d4) acts as the single primary action color. - BMW Type Next Latin: weight 700 display against weight 300 body is the signature.
- Buttons are rectangular, 0px radius — corporate dialect, distinct from M's sportier radii.
- Model cards run as 4-up or 5-up grids with no hairline border or only minimal border — just white plate + photo + title.
- Photography (model renders) sits in environment, no shadow — depth comes entirely from color-block contrast.
- M tricolor stripe appears only in M-model contexts — not part of the corporate language.
- Section rhythm holds at
{spacing.section}(80px) for every major band.
What ships with it
1 file 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.
- 4d ago First seen · 545 lines · 121 tokens per session scan A 6842a97731fc
BMW-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 7,414 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…