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 HalidSaglam/saglitzdesign-mcp --skill saglitzdesigngit clone --depth 1 https://github.com/HalidSaglam/saglitzdesign-mcpWrote 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/halidsaglam/saglitzdesign-mcp/saglitzdesign)<a href="https://agentmods.dev/skills/halidsaglam/saglitzdesign-mcp/saglitzdesign"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/saglitzdesign/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/halidsaglam/saglitzdesign-mcp/saglitzdesign"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/saglitzdesign.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 | $0.00204 | $0.01125 |
| Opus 5 | $0.00102 | $0.00562 |
| Sonnet 5 | $0.00041 | $0.00225 |
| Haiku 4.5 | $0.00020 | $0.00112 |
Grade A, and why
saglitzdesign 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 5d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaglitzDesign
This is the door into a design system that can prove its claims: every recommendation downstream of it either comes generated, comes measured, or comes cited — not from taste alone.
Route to the right skill
The sign the work gives off, and which of the eight depth skills answers it. Read top to bottom; the first row that matches wins.
| The work is… | Route to |
|---|---|
| Native iOS, iPadOS, or macOS UI — HIG conventions, Liquid Glass, or porting a design onto an Apple platform | apple-platform-design |
| Native Android UI — Material 3, predictive back, edge-to-edge, or porting a design onto Android | android-platform-design |
| Auditing a whole project or repository — running every deterministic auditor over it, before it ships or to see what is wrong with it | ship-quality-gate |
| Critiquing one interface — a screenshot, a live page, or a screen's code — for what's wrong with it | design-review |
| Checking whether a codebase has a real design system, or migrating scattered values onto tokens | design-system-audit |
| Building or improving a landing page or marketing site so it converts | landing-page-conversion |
| Adding or fixing motion — transitions, hovers, presses, gestures, page transitions | motion-and-animation |
| Anything else — building or restyling a UI with no more specific match above | clean-interface-design |
The two audit-shaped rows overlap, and the order resolves it deliberately:
"audit this repo for what's wrong with it" is a whole-project run, so it goes
to ship-quality-gate — the deterministic gate — rather than to the taste
critique. Reach for design-review when the target really is one screen.
Four invariants, whichever skill you land in
- Generate the system before the pixels. A brand color and a vibe produce a whole foundation — palette, type scale, spacing, elevation, tokens — before any single screen gets built. Hand-picked one-off hex values and font sizes are the failure mode this prevents.
- Bind every value to a token. A color, radius, spacing step, or type size that isn't a token reference is a value the next screen will re-decide independently. That's how "feels inconsistent but I can't say why" happens.
- Run the deterministic auditors at the close. Taste closes the file; a lint pass, a contrast check, and a consistency score close the task. Read what each auditor discloses it could not see, not only what it found.
- Ground every number claimed in a measured output. A contrast ratio, a consistency score, a Lighthouse figure — state it because a tool produced it, not because it sounds plausible.
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.
- 5d ago First seen · 43 lines · 204 tokens per session scan A 04d7b3e41ac7
saglitzdesign is a skill published in the GitHub repository HalidSaglam/saglitzdesign-mcp (5 stars, last pushed 8d ago), licensed MIT. It adds 204 tokens to every session and 1,125 once invoked, about $0.0010 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 2026-09-04.
Other skills, from other repositories
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.
von-restorff-effect
Apply the Von Restorff Effect — the element that differs from its neighbours is the one remembered. Use when a single action must dominate. For overall ordering rather than single-element emphasis, use visual-hierarchy.
handoff-spec
Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use design-qa-checklist; for reusable library components use component-spec (design-systems).
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
color-system
Build a product colour system — tonal scales, semantic roles, and contrast compliance. Use when defining or rebuilding colour from scratch. For dark-mode adaptation use dark-mode-design; for chart palettes use data-visualization; for multi-brand token architecture use theming-system (design-systems).
dark-mode-design
Adapt an existing palette to dark mode — surface elevation, contrast rebalancing, and desaturation rules. Use when you already have a light palette to translate. For building the base palette first, use color-system.