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 EthanYoQ/Skill-hub --skill typographygit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/typography)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/typography"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/typography/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/ethanyoq/skill-hub/typography"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/typography.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 | $0.00151 | $0.07112 |
| Opus 5.5 | $0.00060 | $0.02845 |
| Sonnet 5.5 | $0.00030 | $0.01422 |
| Haiku 4.5 | $0.00015 | $0.00711 |
Grade A, and why
typography 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 — 644 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography
Research-grounded decisions for every surface where humans read text. The philosophy: the browser renders semantic HTML correctly; every typographic decision on top of that is a bet. This skill records the bets worth making — each grounded in research — and the ones to skip.
The iA Writer principle applies: fewer decisions, made well, applied consistently.
Modes
Generative — New Project
When starting a new page, component, or document:
- Establish tokens first. Generate a typography token file (section 6) before writing any component CSS. Every size, color, and spacing value should reference a token.
- Detect language. If the project serves Japanese content, apply the Japanese overrides (section 3) from the start — not as a retrofit.
- Set the reading container. Every text-bearing surface gets a
max-widthconstraint. No exceptions. - Ship both color schemes. Default to
prefers-color-scheme. Never force one mode. - Verify mobile. Viewport meta tag, fluid font sizes via
clamp(), touch targets ≥ 44px. - Reader controls. For reading-focused interfaces, provide user-facing font size control (e.g., 3 steps: small/default/large via a
--fs-scaleCSS variable multiplier). For Japanese content, offer horizontal/vertical mode toggle with per-content persistence. - Write the project ledger. Create
TYPOGRAPHY.mdin the project root (see section 7).
Review — Existing Project
When auditing existing CSS, HTML, or rendered output:
- Line length — is body text constrained to 45–80 CPL (Latin) or 30–40 CPL (Japanese)?
- Font size — is body ≥ 16px on mobile, ≥ 18px on desktop?
- Line height — is body ≥ 1.5 (Latin) or ≥ 1.65 (Japanese)?
- Contrast — does body text meet 4.5:1 minimum? Compute from actual hex values.
- Dark mode — is
#000background or#ffftext present? Both are violations. - Japanese — is
lang="ja"declared? Isline-break: strictset? Isfont-style: italicabsent? - Type scale — are there more than 6 distinct sizes? Is the ratio consistent?
- Mobile — viewport meta present? Touch targets ≥ 44px?
- Prohibitions — scan for every item in section 4.
- Vertical text — if Japanese content uses
writing-mode: vertical-rl: istext-alignset tostart(notjustify)? Is column height capped (~22em)? Iswidth: max-contentset? Isoverflow-x: hiddenabsent from body? - Reader controls — for reading interfaces: is font size adjustable? For Japanese: is writing mode toggleable with persistence?
- Write the project ledger. Create or update
TYPOGRAPHY.mdin the project root (see section 7).
What ships with it
4 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 · 644 lines · 151 tokens per session scan A 5d35712221c0
typography is a skill published in the GitHub repository EthanYoQ/Skill-hub (11 stars, last pushed 3d ago), licensed MIT. It adds 151 tokens to every session and 7,112 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 2026-09-13.
typography compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| typographyEthanYoQ/Skill-hub | Skill | 11 | 3d ago | MIT | A | 151 | Claude Code, Codex |
| designSethGammon/Citadel | Skill | 927 | yesterday | MIT | A | 51 | Claude Code |
| ui-designernelson820125/iforgeai | Skill | 12 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| design-qacoo1white/cool-workflow | Skill | 2 | 2d ago | BSD-2-Clause | A | 61 | Claude Code, Codex |
| DesignSystemArchitectvignesh2027/Claude-Agentic-Skills2.0-version | Skill | 4 | 2mo ago | MIT | A | 36 | Claude Code, Codex |
| UserResearchOSvignesh2027/Claude-Agentic-Skills2.0-version | Skill | 4 | 2mo ago | MIT | A | 37 | Claude Code, Codex |
| onboarding-designervignesh2027/Claude-Agentic-Skills2.0-version | Skill | 4 | 2mo ago | MIT | A | 72 | Claude Code, Codex |