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 vidhunnan/agentic-skills --skill design-languagegit clone --depth 1 https://github.com/vidhunnan/agentic-skillsWrote 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/vidhunnan/agentic-skills/design-language)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-language"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-language/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/vidhunnan/agentic-skills/design-language"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-language.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 | $0.00150 | $0.03764 |
| Opus 5 | $0.00075 | $0.01882 |
| Sonnet 5 | $0.00030 | $0.00753 |
| Haiku 4.5 | $0.00015 | $0.00376 |
Grade A, and why
design-language 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 10d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-language
Writes the other half of the brief. design-brief captures what problem you're
solving and for whom; it never asks what the thing should look like — brand appears
there as one row of a constraints table. This skill captures the visual intent: the
surface, the references, the rules, the words.
It exists because of a specific failure. Asked to design something with no stated visual intent, a model produces the median of everything it has seen — competent, plausible, and indistinguishable from every other generated interface. The fix is not a better prompt. It is having written down, before anything is generated, what you are aiming at and what you are aiming away from.
This doc is also the gate on design-explore. Under
ADR 0022,
a generating skill may not run without a written visual intent — which means the
quality of this document sets the ceiling on everything generated from it.
Three rules govern this skill:
- Ask, never propose. The user's taste is the input. The moment you supply the aesthetic — even as "a starting point to react to" — the document records your median instead of their intent, and everything downstream is judged against it. Offering one example to show the register is fine; drafting the direction and taking a "yeah, that" is not.
- The negative does half the work. "Dark, editorial, designer-tool energy — similar to Linear, Vercel, Raycast. Not startup cliché." Strip the "not" and the references become decoration. Always get the anti-reference.
- A constraint you can't break isn't a constraint. "Clean and modern" cannot be
violated, so it cannot guide anything. "Exactly one accent colour" and "content
never touches the edges — 14% horizontal, 5% vertical" can be violated, which is
precisely what makes them useful to
design-exploreand checkable bydesign-critique.
Instructions
Step 0 — Detect your surface
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.
- 10d ago First seen · 301 lines · 150 tokens per session scan A 073ea9ae316f
design-language is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 150 tokens to every session and 3,764 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
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.