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 Dragoon0x/canon --skill canon-typographygit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/dragoon0x/canon/canon-typography)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-typography"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-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/dragoon0x/canon/canon-typography"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-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 | $0.00082 | $0.02185 |
| Opus 5.5 | $0.00033 | $0.00874 |
| Sonnet 5.5 | $0.00016 | $0.00437 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
canon-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 2mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Typography
Typography is the single highest-leverage design decision in any interface. Most AI-generated UIs converge on the same wrong defaults. This skill prevents that.
Quantified Rules
Font Size
| Context | Range | Default | Source |
|---|---|---|---|
| Body text (desktop) | 16–18px | 16px | Material 3, Apple HIG |
| Body text (mobile) | 16–17px | 16px | iOS HIG (16px prevents zoom-on-focus) |
| Long-form reading | 18–20px | 18px | Refactoring UI, Practical Typography |
| Caption / metadata | 12–14px | 13px | Material 3 |
| Legal / footnote | 11–12px | 12px | Never below 11px |
| H1 (marketing) | 48–96px | 64px | Modular scale 1.25–1.333 |
| H1 (app) | 28–36px | 32px | Modular scale 1.2 |
| Button label | 14–16px | 15px | 44px touch target dictates min |
Hard floor: never use font-size below 12px on any visible text. Never below 14px on any tappable target on mobile.
Line Height
| Context | Ratio | Source |
|---|---|---|
| Display / large headings (>40px) | 1.0–1.1 | Tighter as size grows |
| Subheadings (24–40px) | 1.15–1.25 | Material 3 |
| Body text | 1.5–1.7 | WCAG 1.4.12 requires ≥1.5 |
| Dense UI (tables, lists) | 1.3–1.4 | Acceptable for short strings |
| Long-form prose | 1.6–1.75 | Practical Typography |
Rule: line-height decreases as font-size increases. Inverse relationship is non-negotiable.
Line Length (measure)
- Optimal: 50–75 characters per line
- Maximum: 90 characters
- Minimum: 45 characters
- Source: Robert Bringhurst's The Elements of Typographic Style
Use max-width: 65ch on prose containers. Use max-width: 75ch for marketing copy. Anything wider hurts comprehension.
Letter Spacing (tracking)
| Context | Value |
|---|---|
| Body text | 0 (default) |
| Large headings (>40px) | -0.01em to -0.03em |
| Small caps / all-caps labels | +0.05em to +0.1em |
| Buttons / nav (uppercase) | +0.025em to +0.05em |
Rule: tracking decreases as size increases. Tighten large type, loosen all-caps and small text.
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.
- 2mo ago First seen · 190 lines · 82 tokens per session scan A ecbfb29dddae
canon-typography is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 82 tokens to every session and 2,185 once invoked, about $0.0003 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 2026-09-03.
canon-typography compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-typographyDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 82 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| color-contrast-auditorcuriositech/windags-skills | Skill | 18 | 6d ago | none | A | 117 | Claude Code |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| lagannOldiiik/Design-Lagann | Skill | 2 | 18d ago | none | A | 0 | Claude Code, Codex |
| scroll-craftnateherkai/scroll-craft | Skill | 4.7k | 1mo ago | MIT | A | 177 | Claude Code |
| image-to-codeplugin87/ux-ui-agent-skills | Skill | 3.1k | 10d ago | MIT | A | 77 | Claude Code |