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 agentmods add skills/jangles-byte/atelier/typography-and-layoutnpx skills add jangles-byte/atelier --skill typography-and-layoutgit clone --depth 1 https://github.com/jangles-byte/atelierWrote 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/jangles-byte/atelier/typography-and-layout)<a href="https://agentmods.dev/skills/jangles-byte/atelier/typography-and-layout"><img src="https://agentmods.dev/badge/skills/jangles-byte/atelier/typography-and-layout.svg" alt="Measured on agentmods" 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 | $0.00129 | $0.00585 |
| Opus 5 | $0.00064 | $0.00293 |
| Sonnet 5 | $0.00026 | $0.00117 |
| Haiku 4.5 | $0.00013 | $0.00059 |
Grade A, and why
typography-and-layout 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 4d 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.
What it actually says
Typography & Layout
Typography is most of design: get type and spacing right and a screen looks designed before it has any color or decoration. The failure mode is timidity — small scale jumps, default tracking, uniform spacing — not bad taste.
Workflow
- Read the design philosophy (
design-direction); the type voice comes from there. - Choose faces and pairings with references/type-pairing.md — contrast on exactly one axis, two families maximum.
- Build a modular scale and spacing system with references/scale-and-space.md — sizes, line heights, measure, and the spacing ladder, as tokens.
- Compose with references/composition.md — grid, hierarchy channels, negative space, and the sanctioned ways to break the grid.
- Render at real size and run the
critiqueskill. Type that looks right in code is routinely wrong on screen.
Which reference to load
| Situation | Load |
|---|---|
| Picking fonts, pairing display + text faces, font features | references/type-pairing.md |
| Setting sizes, line-height, measure, spacing ladder | references/scale-and-space.md |
| Arranging a page/screen/slide, hierarchy problems, grids | references/composition.md |
Non-negotiables
- Two font families maximum (a third only for code/data, and it counts if decorative).
- A real scale ratio, and at least one jump ≥ 3× body size somewhere in display contexts (heroes, slides, posters); interfaces cap lower but still need contrast.
- Body measure 45–75 characters; line-height inversely proportional to size.
- Spacing from a ladder (4/8-based), applied asymmetrically: space groups, not elements — more space between sections than inside them, always.
- Tabular numerals (
font-variant-numeric: tabular-numsor a mono) for any column of numbers that can change.
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.
- 4d ago First seen · 44 lines · 0 tokens per session scan A 1b74c2564157
typography-and-layout is a skill published in the GitHub repository jangles-byte/atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 585 once invoked, about $0.0006 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
sheleg-design
Use when deciding how something LOOKS or MOVES — cinematic landing pages and hero sections, particle/WebGL, scrubbed motion, drift, dashboards, admin or internal tools, mobile screens, chat or agent interfaces, tokens, palettes, typography and the Figma border. Triggers - "design a landing" / "дизайн лендинга", "build…
html-ppt-zhangzara-biennale-yellow
A curatorial deck for a contemporary art biennale — the thesis, the rooms, the works, and the visitor journey. Built as a decision-grade design craft deck for museum board, curators.
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-pink-script
A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.
figma
Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link…