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 ollama-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/ollama-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/ollama-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ollama-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/ollama-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/ollama-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 | $0.00168 | $0.08336 |
| Opus 5.5 | $0.00067 | $0.03334 |
| Sonnet 5 | $0.00034 | $0.01667 |
| Haiku 4.5 | $0.00017 | $0.00834 |
Grade C, and why
Ollama-design-analysis scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Contains the literal `curl -fsSL https://ollama.com/install.sh | sh` install command with a small copy-icon at the right edge. Sits directly below the hero headline as the page's most prominent "CTA." Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Ollama's site is the most aggressively under-designed marketing surface in the AI tooling space, and that is the entire point. The home page reads like a Markdown README rendered with care: a 36px center-aligned heading How it starts
The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Ollama's site is the most aggressively under-designed marketing surface in the AI tooling space, and that is the entire point. The home page reads like a Markdown README rendered with care: a 36px center-aligned heading sits above an inline curl install snippet inside a soft-gray pill, a single black "Download" CTA, and a hand-drawn llama mascot as the only ornament. Everything else — automate-your-work block, "Start local. Scale cloud." pricing pair, "Your data stays yours" guarantee strip, FAQ wall on /pricing — sits on the same paper-white canvas ({colors.canvas}) with quiet {colors.body} neutrals carrying the prose. The system is the documentation, and the documentation is the system.
The design philosophy is geometric: every interactive element collapses to {rounded.full} (9999px) — buttons, search pills, install-snippet pills, text inputs, and the terminal-traffic-light dots. There are no decorative drop shadows, no gradients, no hero illustrations beyond the llama. Cards (the rare ones, on /pricing) use a soft {rounded.lg} (12px) and a 1px hairline. The single inverted moment in the entire system is the dark "Max" pricing tier — {colors.surface-dark} with white text — which acts as the only attention-grabbing surface in an otherwise studiously flat layout.
Typography pairs SF Pro Rounded (display headings, weight 500–600) with the operating system's default sans (ui-sans-serif) for body and ui-monospace for code. The roundness of the heading face is the only "personality" the chrome carries — it gently echoes the {rounded.full} button geometry without being decorative about it.
Key Characteristics:
- Paper-white
{colors.canvas}end-to-end with no surface alternation — the whole page is one continuous sheet - Center-aligned hero with
{typography.display-xl}SF Pro Rounded headline, no eyebrow, no subhead beyond a small "Power OpenClaw with Ollama" line under the llama - Pill geometry everywhere: every button and pill input is
{rounded.full}; cards use{rounded.lg}; nothing is sharp-cornered except section dividers - Single-color CTA system: pure black
{colors.primary}pills carry every action; "Get Pro" / "Get Max" inside pricing cards are the only variations - Inline
curlinstall snippet rendered as a pill with{typography.code-md}— the most signature element, sitting directly under the hero headline - Terminal-mockup card with macOS traffic-light dots and inline
ollama launch openclawexample — the home page's only "product preview" - Inverted dark
{component.pricing-card-dark}for the highest-tier "Max" plan, breaking the flat-white rhythm exactly once per page
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 · 540 lines · 168 tokens per session scan C 702aa6668e0f
Ollama-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 8,336 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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'…