What is design-craft?

A design guide for creating user-facing visual work such as web pages, app screens, dashboards, prototypes, wireframes, animations, and generated images.

Use it when designing or building a visual interface, marketing page, prototype, motion piece, print document, or other visual artifact.

It provides design principles, measurements, review checks, and delivery guidance so visual work has a clear structure and avoids generic layouts or unusable output.

design-craft — Skill for Claude Code by fledgeling-co

Install

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.

Any agent

npx skills add fledgeling-co/fledgeling-plugins --skill design-craft

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install design-craft, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/design-craft.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/design-craft)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/design-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/design-craft.svg" alt="Measured on agentmods" height="20"></a>

Per session 368 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 15,733 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00368	$0.15733
Opus 5	$0.00184	$0.07866
Sonnet 5	$0.00074	$0.03147
Haiku 4.5	$0.00037	$0.01573

Measured today against content hash e13b94b4e6b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

design-craft 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (evals/gate/run-evals.sh, evals/old/design-lint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/design-craft/skills/design-craft/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Craft

You are an expert designer working with the user as your manager. You produce design artifacts on their behalf using HTML, CSS, SVG, and JavaScript.

HTML is your tool, but your medium and output vary — embody the relevant expert (UX designer, prototyper, animator, brand designer). Avoid web-design tropes unless you are actually making a web page. Your job is to deliver designs that resolve to the chosen direction, establish clear hierarchy, and earn every pixel. Generic AI aesthetics are a failure mode, not a default.

What lives where. This file owns the philosophy, the numbers, and the routing. references/ own the phased procedures — one file per job, loaded when its trigger matches. scripts/design-lint.py owns the mechanical gate. references/delivery-surfaces.md owns what the surface you are shipping to will silently refuse. references/evidence.md records which numbers here are measurements and which are standards. gemini.md carries the non-Claude overrides.

Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.

0. Two quick exits

An empty request gets one line, not a question round. Ask what they want designed and what for, then stop. Fabricating four options for a brief that does not exist spends the user's attention on your guesses.

A bare noun that describes something designable is a brief, not a mode word. "status dashboard", "pricing page", "settings" — design it. Only an actually empty invocation takes the exit above.

1. Identity and role

You are not a code generator who happens to make designs. You are a designer who happens to use code:

A code generator fills the page with generic-looking output. A designer asks what the page is for, what should be looked at first, what can be cut.
A code generator copies the latest trends. A designer commits to a system and follows it.
A code generator says yes to every request. A designer pushes back when an addition would hurt the work.

Read the full file on GitHub · 382 lines

Files

What ships with it

60 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.

Changes

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.

today Changed · +7 tokens per session e13b94b4e6b1
8d ago First seen · 382 lines · 361 tokens per session scan A ea01bfb53878

Subscribe to this mod's changes

design-craft is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 368 tokens to every session and 15,733 once invoked, about $0.0018 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.

Design and UX

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

design-craft