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 ibm-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/ibm-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/ibm-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ibm-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/ibm-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ibm-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 | $0.00135 | $0.06896 |
| Opus 5.5 | $0.00054 | $0.02758 |
| Sonnet 5 | $0.00027 | $0.01379 |
| Haiku 4.5 | $0.00014 | $0.00690 |
Grade A, and why
IBM-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 — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
IBM's marketing system is a faithful application of Carbon Design System — IBM's open-source enterprise design system. The dominant surface is {colors.canvas} pure white with {colors.surface-1} light gray for elevation, charcoal {colors.ink} (#161616) for text, and IBM Blue {colors.primary} (#0f62fe) as the single brand accent.
The defining choice is flat geometry: every CTA, every card, every input, every container uses square corners ({rounded.none} 0px) with thin 1px borders. There are no rounded pills, no soft shadows, no atmospheric gradients. The system is engineered, not stylized.
IBM Plex Sans carries the entire type hierarchy. Display sizes (76 / 60 / 42px) run at weight 300 — IBM's signature light display treatment that makes 76px feel calmer than competing brands' 700-weight display. Body type sits at weight 400 with letter-spacing: 0.16px (a Carbon precision detail) and line-height 1.50. The voice reads as careful, technical, and trustworthy.
The system reaches for color rarely — IBM Blue marks links, primary CTAs, and the rare full-bleed CTA banner. Charcoal carries every other surface that isn't white. The result is enterprise gravitas without the enterprise stiffness: rigorous, light-weighted, and intentionally restrained.
Key Characteristics:
- Carbon Design System — IBM's marketing chrome IS Carbon. Buttons are square, inputs are square-with-bottom-rule, corners stay at 0px.
- Light-weight display type: Plex Sans at weight 300 for 42–76px headlines is the brand's typographic signature.
- One accent color:
{colors.primary}IBM Blue carries every link, primary CTA, and CTA banner. There is no second brand color. - White canvas + light gray (
{colors.surface-1}) + charcoal ({colors.ink}) cover 95% of surfaces. - Footer inverts to charcoal (
{colors.inverse-canvas}#161616) — the only dark surface above the page break. - Card hierarchy is carried by 1px hairlines and surface change, never by drop shadow.
letter-spacing: 0.16pxon body is a Carbon precision detail — the small positive tracking is part of the brand voice.- Page rhythm: utility bar → top nav → hero with light-weight headline → feature card grid → customer logo marquee → enterprise feature row → training section → newsletter / sign-in CTA → dark footer.
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 · 551 lines · 135 tokens per session scan A f6846fc9d5aa
IBM-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 6,896 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'…