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 yummylabs-coder/yummy-design-plugins --skill design-context-setupgit clone --depth 1 https://github.com/yummylabs-coder/yummy-design-pluginsWrote 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/yummylabs-coder/yummy-design-plugins/design-context-setup)<a href="https://agentmods.dev/skills/yummylabs-coder/yummy-design-plugins/design-context-setup"><img src="https://agentmods.dev/badge/skills/yummylabs-coder/yummy-design-plugins/design-context-setup/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/yummylabs-coder/yummy-design-plugins/design-context-setup"><img src="https://agentmods.dev/badge/skills/yummylabs-coder/yummy-design-plugins/design-context-setup.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 | $0.00177 | $0.03054 |
| Opus 5.5 | $0.00071 | $0.01222 |
| Sonnet 5.5 | $0.00035 | $0.00611 |
| Haiku 4.5 | $0.00018 | $0.00305 |
Grade A, and why
design-context-setup 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 1mo 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Context Setup
Most designers know their product and their design rules perfectly well. What they don't know is which file each piece belongs in, and that uncertainty is enough to stop them setting anything up at all.
This skill removes that decision. Ask questions in plain language, connect what changes what's possible, show the whole scaffold as a map so they can see the shape, then draft each file together, one at a time, so the designer is always reacting to something rather than facing an empty page.
Critical: the four rules that keep this from backfiring
Every file stays short. The entire point of this structure is that the always-loaded files stay small. A generated 300-line rules file recreates the problem it was meant to solve. The test for every line, from Anthropic's own guidance: would removing this cause Claude to make a mistake? If not, cut it. Target under 200 lines for CLAUDE.md and about 40 for a rules file.
Show them something, never ask them to compose. The designer reacts; they do not fill in blanks. "What are your colour rules?" is a blank page with a question mark on it, and nobody can answer it cold. If a system is connected, go and read it, then ask what is wrong with what you found. If nothing is connected, anchor on an artifact — a pasted frame, a variable list. One question per file, maximum, and always attached to something concrete.
Never invent the designer's rules. Draft from what they told you. Where something is genuinely missing, write a TODO line saying what's needed and why, rather than filling it with plausible-sounding defaults. A file with three real rules and four honest TODOs is more useful than one with twelve invented ones.
Know which directories are live. .claude/rules/, .claude/skills/ and .claude/agents/ are loaded or discovered by Claude automatically. A stub file there is not a placeholder, it is a live instruction that fires on real work. In those directories a not-yet slot is a line in a README, never a stub file. Everywhere else (design/, tokens/) placeholders are inert and safe.
What ships with it
7 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.
- 1mo ago First seen · 180 lines · 177 tokens per session scan A 5726e48ee07a
design-context-setup is a skill published in the GitHub repository yummylabs-coder/yummy-design-plugins (24 stars, last pushed 22d ago), licensed MIT. It adds 177 tokens to every session and 3,054 once invoked, about $0.0007 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 2026-08-31.
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.