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 eddie199/claude-design-md --skill claude-design-md-generatorgit clone --depth 1 https://github.com/eddie199/claude-design-mdWrote 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/eddie199/claude-design-md/claude-design-md-generator)<a href="https://agentmods.dev/skills/eddie199/claude-design-md/claude-design-md-generator"><img src="https://agentmods.dev/badge/skills/eddie199/claude-design-md/claude-design-md-generator/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/eddie199/claude-design-md/claude-design-md-generator"><img src="https://agentmods.dev/badge/skills/eddie199/claude-design-md/claude-design-md-generator.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 | $0.00138 | $0.01427 |
| Opus 5 | $0.00069 | $0.00714 |
| Sonnet 5 | $0.00028 | $0.00285 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
claude-design-md-generator 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 11d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Generator
For users designing UI screens in Claude Design — dashboards, apps, admin tools, SaaS products, internal tools, any product surface.
Produces a CLAUDE.md file, ~60–100 lines, that Claude Design auto-loads at the root of every chat in the project. Ask 5 questions, compose, present.
This skill is scoped to UI screen design. If the user is building something else (marketing sites, editorial/lifestyle brand sites, long-form content surfaces), still produce a CLAUDE.md — but flag that the shape is optimised for product UI and some rules may need adjusting.
The interview
Ask one question at a time, conversationally. Don't dump the full list. Adapt based on prior answers.
Q1. Name and one-sentence description. "What's the project called, and what is it in one sentence?"
Q2. Codebase and design system state. "Is there a linked codebase? A design system? Or is this design-only for now?" If linked, ask the stack in one line.
Q3. Aesthetic in one concrete sentence. "Describe the feel in one or two concrete sentences. Avoid adjectives like 'modern' or 'clean' — name measurable things (density, font treatment, surface style, palette direction)." If they only give adjectives, push back once: "Can you give me one concrete constraint? E.g., 'dense tables with tabular figures, 1px borders instead of fills' or 'lots of whitespace, one accent colour, 4pt grid'."
Q4. Tokens. Ask only if no linked design system. Request: background, foreground, one accent (with scope of use — e.g., "CTAs only"), headline font, body font. 5 values, not a full palette. For product UI, also ask if there's a mono font for numbers, IDs, and code.
Q5. Top three don'ts. "What are three things Claude Design should never do on this project?" If they don't know, suggest defaults and let them confirm or adjust. Product UI defaults:
- Never invent hex values outside the token set.
- Never use drop shadows (use 1px borders instead).
- Never Title Case button labels — sentence case only.
- Never use emoji in UI chrome.
- Never use more than 2 font weights on a single screen.
What ships with it
3 files 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.
- 11d ago First seen · 85 lines · 138 tokens per session scan A 557745243a4d
claude-design-md-generator is a skill published in the GitHub repository eddie199/claude-design-md (2 stars, last pushed 4mo ago), licensed MIT. It adds 138 tokens to every session and 1,427 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
hyperframes
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…
hatch-pet
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells…
od-contribute
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship…
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…