Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miikkij/aimeat-protocol/main/.claude/skills/aimeat-design-language/SKILL.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/miikkij/aimeat-protocol/aimeat-design-language)<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-design-language"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-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/miikkij/aimeat-protocol/aimeat-design-language"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-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 | $0.00143 | $0.09515 |
| Opus 5.5 | $0.00057 | $0.03806 |
| Sonnet 5.5 | $0.00029 | $0.01903 |
| Haiku 4.5 | $0.00014 | $0.00951 |
Grade A, and why
aimeat-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 5d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The AIMEAT design language
One product, two faces. The showroom is what a visitor sees before signing in: the front page,
how it works, for your business, help, members, the change log. The poster is what a person sees
once inside: the home, every profile tab, the chat, the sign-in dialog, the app catalog. They share
the type, the colours, the shapes and the rules; they differ in how loud they are. A third register,
the classic shell (rounded controls, cards), remains under the admin dashboard and the oldest
views and is not extended; it reads the same type tokens. Its rules (buttons, cards, badges, the
segmented control, the toast, the top bar) live in aimeat/public/css/components/, one sheet each.
That folder also holds the library parts Settings & Controls is drawn from (the page kit, the
listing, the facts, the fields, the timeline, and every part only one page draws), one sheet
each, each with its entry in the component catalogue (src/services/ui-library/entries-*.ts) and
a demo in the design lab; they read the shape values like poster.css does. Since 2026-09-27 a
Settings & Controls page writes no class at all: it calls the components (components/Action.js,
Mark.js, Note.js, List.js, Facts.js, Field.js, SettingsPage.js and the rest) with data,
and a component draws only its own class names and the poster.css shapes below. The admin pages
(since 2026-09-27) and appcat, the app catalogue rebuilt on the components at /v1/appcat, are
drawn the same way; where the old app catalogue drew a thing in its own way, that look is a named
option of the component reading the tokens (and poster.css holds its tones outside the
@app-catalog ranges, which the old catalogue's build copies), so a theme reaches it too.
Type and colour tokens live in aimeat/public/css/theme.css, and nothing else does:
pnpm check:theme-tokens refuses a rule there that is not a custom property. Font sizes and
weights are tokens too (--text-2xs … --text-xl, --weight-regular … --weight-heavy), so a
theme can change the type scale in one place. --text-2xs is 11px, the smallest text a page shows
(the Status and the time read it; Jouni, 2026-10-25): a size below it is a finding. The shared shapes live in
aimeat/public/css/poster.css. A view composes a shape by class and owns its layout. Change the
token or shape at its home; the maps below show which surfaces follow. Existing copies are
recorded migration debt, not examples for a new view.
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.
- 5d ago Changed · +1 lines 1483c4e09661
- 7d ago Changed · +1 lines 5c5e5effcea8
- 8d ago Changed e329ce397eae
- 13d ago Changed · +1 lines fa1fae814171
- 18d ago Changed · +14 lines 1309dcfe7a67
- 20d ago Changed · +1 lines · +34 tokens per session e913f2f91723
- 22d ago Changed bd49cd2dfbd0
- 23d ago Changed · +1 lines 0210aabe31ec
- 26d ago Changed · +17 lines cee17a44024a
- 27d ago First seen · 349 lines · 109 tokens per session scan A 024bd7feb16b
aimeat-design-language is a skill published in the GitHub repository miikkij/aimeat-protocol (10 stars, last pushed today), licensed MIT. It adds 143 tokens to every session and 9,515 once invoked, about $0.0006 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
architecture-diagram
This skill should be used when a system design needs a diagram — "draw the architecture", "diagram this system", "show the components", "make an architecture/infrastructure/topology diagram", or visualizing boxes-and-arrows, data flow, regions, or failure paths for a design. It generates a self-contained dark-theme…
design-expert
Expert-level system design, architecture patterns, scalability, and distributed systems. Use when the user mentions system design, architecture, scalability, distributed systems, or patterns, or when the task involves Architecture Patterns or Design Principles.
kernel-chat-web-design
Guides the design, layout, styling, and interactivity of kernel.chat editorial spreads and standalone artifact editions. Use this skill when editing or creating pages, React components, CSS files, or single-file HTML artifacts in the kernel.chat project to enforce the POPEYE-inspired bilingual design grammar and the…
kernel-chat-design-qa
Audits kernel.chat pages for responsive visual craft, accessibility, motion safety, interaction truth, runtime health, and production rendering. Use when reviewing an issue or artifact, checking whether a design is finished, comparing desktop and mobile, validating reduced motion or print, finding overflow and broken…
coordinate-agent-work
Coordinate independent coding or research agents across host sessions and linked Git worktrees through AgentTool Collab's local journal. Use when starting or resuming credential-bound coordination, splitting parallel work, claiming before overlapping edits, polling or acknowledging events, attaching evidence…
capability-conductor
A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.