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 5.5 | $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 1mo 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.
- 1mo 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 (143 stars, last pushed 4d ago), 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.
Ollama-design-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Ollama-design-analysisskillmds/skillmd | Skill | 143 | 4d ago | MIT | C | 168 | Claude Code |
| frontendcode-yeongyu/lazycodex | Skill | 3.9k | yesterday | MIT | A | 79 | Codex |
| designlang-tokensManavarya09/design-extract | Skill | 4.8k | 2d ago | MIT | A | 30 | Claude Code |
| cli-anything-photoshopyb2460/harness-anything | Skill | 3.0k | 29d ago | MIT | A | 43 | Claude Code, Codex |
| app-screenshot-debugtermio-sh/termio | Skill | 785 | 5d ago | MIT | A | 161 | Claude Code, Codex |
| user-research-cookiycookiy-ai/user-research-skill | Skill | 1.6k | 5d ago | MIT | A | 154 | Claude Code, Codex |
| write-zot-themespatriceckhart/zot | Skill | 360 | yesterday | MIT | A | 23 | Claude Code, Codex |