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 ship-quality-gategit 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/ship-quality-gate)<a href="https://agentmods.dev/skills/halidsaglam/saglitzdesign-mcp/ship-quality-gate"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/ship-quality-gate/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/ship-quality-gate"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzdesign-mcp/ship-quality-gate.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 | $0.00086 | $0.04047 |
| Opus 5 | $0.00043 | $0.02024 |
| Sonnet 5 | $0.00017 | $0.00809 |
| Haiku 4.5 | $0.00009 | $0.00405 |
Grade A, and why
ship-quality-gate 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Quality Gate
Design advice is cheap and unfalsifiable. The gate is the other half of the job: ten auditors that hand back findings with a rule id, a severity, the document the rule comes from, and — where the finding belongs to a place — a file and a line. Run them before anyone argues about anything.
Two qualifications on that sentence, because they change how you read the output. Seven of the ten read a real repository; design_lint, audit_ux_copy and audit_ethical_design read one snippet you paste in and have no notion of a project at all — the table below says so per tool. (Two separate corrections sit behind that sentence, and the first was not caused by the second: this file's opening once counted design_lint among the auditors that read a repository, which was fixed on the round that wrote up its snippet-only scope; audit_ux_copy joined the same camp later, on the round that gave it a notVisible list of its own. audit_android_ui later joined the directory-only camp beside audit_apple_ui. audit_ethical_design joined the snippet-only camp in 0.29.0.) And not every finding carries a file:line. design_lint, audit_ux_copy and audit_ethical_design findings carry a line and no file, because there is no file — audit_ux_copy's line marks a position in the pasted text, not a path. More importantly, an absence rule — no llms.txt, no sitemap referenced in robots.txt, no title, no canonical, no entitlements file among the surfaces read, no values-night/ beside a day theme — is a fact about a file that does not exist and so was never read; it names no file by construction. Some project-scope findings in audit_security, audit_apple_ui and audit_android_ui are the same shape.
The trade they make is the whole thing to understand. Each one reports what was authored, not what was measured. They load no page, render nothing, time nothing, and make no request to your site. Every finding is a fact about text — text that was read, or, for an absence rule, text that was looked for across the surfaces named in the finding and not found. That is why they are deterministic, offline and fast — and it is exactly what bounds them.
These ship in the SaglitzDesign MCP (
npx saglitzdesign-mcp). The rules behind them live in the base:get_design_doc("web-security-headers"),get_design_doc("frontend-attack-surface"),seo_geo_guide,get_design_doc("ai-default-aesthetic"),get_design_doc("ethical-design"),get_design_doc("apple-shipping-readiness"),get_design_doc("android-app-design"),get_design_doc("material-3"),get_design_doc("ux-writing"). For what these tools structurally cannot reach, pair them withmeasure_screenshot(the render),audit_accessibility(contrast ratios and target sizes) and the/saglitzdesign:design_reviewworkflow.
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 Changed · +6 lines · +2 tokens per session 16988e7e7126
- 9d ago First seen · 65 lines · 84 tokens per session scan A 66d886fd4d7a
ship-quality-gate is a skill published in the GitHub repository HalidSaglam/saglitzdesign-mcp (5 stars, last pushed 8d ago), licensed MIT. It adds 86 tokens to every session and 4,047 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
platform-conventions
Design to iOS and Android conventions — what each OS mandates, where they diverge, and when to unify. Use when shipping native apps. For breakpoint adaptation use responsive-design; for matching competitor patterns use jakobs-law (interaction-design).
logo-creator
Create logos using AI image generation. Discuss style/ratio, generate variations, iterate with user feedback, crop, remove background, and export as SVG. Use when user wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo.
omh-apple-design
This is a Hermes-native apple-design workflow skill.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.
design-system-governance
Define how the system evolves — contribution model, versioning, deprecation, and change management. Use when multiple teams contribute. For driving uptake use design-system-adoption (designer-toolkit); for design file history use version-control-strategy (design-ops).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).