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 robcsaszar/scaffold --skill ai-design-dot-mdgit clone --depth 1 https://github.com/robcsaszar/scaffoldWrote 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/robcsaszar/scaffold/ai-design-dot-md)<a href="https://agentmods.dev/skills/robcsaszar/scaffold/ai-design-dot-md"><img src="https://agentmods.dev/badge/skills/robcsaszar/scaffold/ai-design-dot-md/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/robcsaszar/scaffold/ai-design-dot-md"><img src="https://agentmods.dev/badge/skills/robcsaszar/scaffold/ai-design-dot-md.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 | $0.00145 | $0.01621 |
| Opus 5 | $0.00072 | $0.00811 |
| Sonnet 5 | $0.00029 | $0.00324 |
| Haiku 4.5 | $0.00015 | $0.00162 |
Grade A, and why
ai-design-dot-md 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 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.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create / Extract DESIGN.md
DESIGN.md = YAML design tokens (machine-readable) + 8 ordered markdown sections (human-readable rationale). Two modes: extract from existing source code, create from design intent.
MANDATORY READ before any token work (Phase 3+): references/design-md-spec.md — Do NOT load during Phases 1 and 2.
Phase 1 — Detect Mode
Extract — frontend source exists. Signals: package.json, tailwind.config.js, CSS/SCSS files, component directories with repeated styles.
Create — no extractable source. User provides brand brief, palette, adjectives, or aesthetic description.
Ambiguous → ask: "Extract design tokens from existing source code, or create from a design brief?"
If an existing DESIGN.md is present → ask: "Update existing file or replace it?"
Exit criterion: mode is unambiguous and any existing file decision is made.
Phase 2 — Gather Inputs
Extract mode
Scan in order:
package.json→ detect framework (Svelte, React, Vue, Angular, Tailwind)- Framework config (
tailwind.config.js,svelte.config.js, theme files) - Global CSS/SCSS → custom properties, font-face declarations, spacing scales
- Component files → repeated class patterns, inline styles, token usage frequency
Consolidate near-duplicate colors (within ~10% perceptual distance). Use semantic keys in YAML (primary, secondary, accent) for cross-referencing. Use descriptive names ("Warm Amber") only in prose sections and as YAML value comments — never as token keys.
If no extractable tokens are found (minified CSS, no custom properties, framework-agnostic markup) → switch to Create mode and inform the user: "No design tokens found in source — I'll create DESIGN.md from a design brief instead."
Create mode
Elicit: brand name, 2–3 personality adjectives, primary color or hex, secondary/accent colors, preferred typeface (or "system" if unspecified), corner style (sharp / soft / pill), density (compact / comfortable / spacious).
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 Changed · +1 lines 345eb5bef576
- 8d ago First seen · 126 lines · 145 tokens per session scan A 1121ca6f792c
ai-design-dot-md is a skill published in the GitHub repository robcsaszar/scaffold (1 stars, last pushed 5d ago), licensed MIT. It adds 145 tokens to every session and 1,621 once invoked, about $0.0007 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
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
sdd
Implements the Spec-Driven Development lifecycle (Intent, Requirements, Design, Tasks, Build) for structured feature development. Use when the user wants to scaffold a new feature spec, generate EARS requirements, create a technical design, break work into tasks, or check spec status. Trigger on keywords: sdd…
apple-interface-writing
Draft, rewrite, or audit concise interface text using an independently expressed reference-only interpretation of Apple's Human Interface Guidelines for writing. Use for buttons, labels, settings, alerts, errors, onboarding, notifications, permissions, empty states, and multi-screen app flows where wording must make…
FAQ Generator
Generates a comprehensive FAQ section for any product, API, or documentation page.
sdd
Implements the Spec-Driven Development lifecycle (Intent, Requirements, Design, Tasks, Build) for structured feature development. Use when the user wants to scaffold a new feature spec, generate EARS requirements, create a technical design, break work into tasks, or check spec status. Trigger on keywords: sdd…
architecture-diagram
Generate or update a project architecture SVG diagram by scanning the live project structure. Use this skill whenever the user asks to regenerate, refresh, or update the architecture diagram, or when skills, agents, or commands have been added/removed and the diagram is stale — even if they just say "update the…