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 m3taz-ahmed/ai-globals --skill design-md-lordgit clone --depth 1 https://github.com/m3taz-ahmed/ai-globalsWrote 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/m3taz-ahmed/ai-globals/design-md-lord)<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/design-md-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/design-md-lord/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/m3taz-ahmed/ai-globals/design-md-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/design-md-lord.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 | $0.00062 | $0.00913 |
| Opus 5.5 | $0.00025 | $0.00365 |
| Sonnet 5.5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
design-md-lord 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 23d 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.
What it actually says
Design MD Lord
[OBJ] Apply real-world design references (DESIGN.md files — Refero catalog, brand systems) to UI work via aiZee's DesignLibrary. Extract tokens, typography, spacing, components, and Do/Don't rules from references — as inspiration, never verbatim copying.
[RULES]
- [CMD] For live evidence gathering (screens/flows/sections beyond the bundled catalog), use the
design-researchskill — Refero + Mobbin MCP. This skill applies the locked direction; that skill finds it. - [CMD] Browse the Refero catalog (styles.refero.design) for DESIGN.md references matching the project's vibe — 2000+ styles extracted from real sites.
- [CMD] With the Refero MCP server configured (
referoin.devin/mcp_config.json), search styles semantically instead of guessing. - [CMD] Import a reference into the local library:
DesignLibrary.import_brand(name, source)accepts aDESIGN.mdpath or raw markdown — lands indesign-library/<name>/DESIGN.mdand loads immediately. - [CMD] Load + mix references:
DesignLibrary.load("apple"),.mix(["stripe", "linear"])for cross-brand fusion,.suggest(project_type)for recommendations,.detect_project_type(dir)to auto-detect. - [REQ] Match reference to page type: landing/hero → bold brands (Linear, Vercel, Framer); dashboard/SaaS → density-first (Linear, Stripe, Sentry); pricing → conversion-focused (Stripe, Cal.com); docs → readability-first (Vercel, Notion); mobile → Apple/Google HIG.
- [REQ] Extract, don't copy: pull semantic tokens (
--color-*+ role), type scale, spacing rhythm, radii, shadows, component patterns, and the Do/Don't rules — then apply to THIS project's design system, not a clone. - [REQ] Token discipline: every color/spacing/type choice must trace to a token in the reference or the project's
@theme. NEVER invent ad-hoc values outside the token system. - [REQ] Honor the reference's Do/Don't section — it encodes what makes the style work (e.g., Apple's restraint, Linear's density, Stripe's elevation).
- [REQ] Mix at most 2-3 references: colors/components/elevation from one, typography/layout from another. More sources = incoherent slop.
- [PROHIBIT] Never copy brand names, logos, or trademarked assets — references guide style only.
- [REQ] After applying, run
DesignSlopVerifier— references prevent generic-AI output only if actually followed. - [REQ] RTL/Arabic projects: prefer references with clean geometric type; verify logical-property friendliness of spacing tokens.
[WORKFLOWS]
- New page design: detect project type →
suggest()or search Refero → pick 1-2 references →import_brand()→load()/mix()→ extract tokens → map to@theme/components → build →DesignSlopVerifier→ a11y pass. - Import a Refero style: find style on styles.refero.design (or MCP search) → copy
DESIGN.mdcontent →DesignLibrary.import_brand("<name>", <content>)→ use like any catalog brand. - Refresh a stale UI:
detect_project_type()→ suggest modern references → diff current tokens vs reference → update@theme→ verify components pick up tokens.
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.
- 23d ago Changed · +1 lines 8ae8e042802e
- 1mo ago First seen · 47 lines · 62 tokens per session scan A 994b363458ee
design-md-lord is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 913 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.