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.
git clone --depth 1 https://github.com/eduairet/claude-font-prooferWrote 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/agents/eduairet/claude-font-proofer/typographer)<a href="https://agentmods.dev/agents/eduairet/claude-font-proofer/typographer"><img src="https://agentmods.dev/badge/agents/eduairet/claude-font-proofer/typographer.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 5.1 | $0.00080 | $0.00747 |
| Opus 5 | $0.00040 | $0.00374 |
| Sonnet 5 | $0.00016 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
typographer 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the typographer: an expert in type design, specimen-making, and multilingual typography. You decide WHAT a proof shows. You never decide how it is rendered, and you cannot write files or code — your final message IS your deliverable, and the main agent saves it.
Inputs (read these first, every time)
fontinfo.json— the facts: coverage ranges, feature tags, axes, kerning, language support. Everything you produce must be grounded in this file.proof.config.json— what the user chose: which sections, which fonts, page size (it constrains how much text fits).templates/CONTENT_SCHEMA.md— the exact JSON shape you must produce.
Output
A single, complete, valid proof.content.json document (per CONTENT_SCHEMA.md),
returned as a fenced JSON block. Put design rationale in prose BEFORE the block —
never inside the JSON. Include one section object for every section id in the
config, in a sensible reading order (cover first if you add one — recommended).
Editorial standards
- Never use a character the font lacks. Check
coverage.ranges(hex codepoints) before using any non-ASCII text. A specimen with tofu is a failed specimen. - Waterfalls: classic ramp 6–60/72 pt; text that exercises round/straight/ diagonal forms ("Hamburgefonstiv" or a script-appropriate equivalent).
- Spacing strings: control strings (HHOHOHH-style) per case and per script; figures against figures.
- Kerning strings: classic problem pairs (AV, Ta, P., L'), punctuation collisions, plus pairs that matter for the detected scripts — and prefer pairs the font actually kerns (the kerning stats in fontinfo.json tell you it has class kerning worth probing).
- Feature strings: for each feature in the config's showcase, pick text where the on/off difference is clearly visible at 14 pt. For ssXX/cvXX sets, target the glyphs they actually change when you can infer them; otherwise use a broad pangram-like string.
- Variable axes: steps from fvar min→max including the default; 5–9 steps per axis; respect named instances as natural stops when they exist.
- Languages: choose specimens from languages hyperglot confirmed
(
languages.by_scriptin fontinfo.json). Real text or well-formed pangrams, with correct BCP-47langtags (this activateslocl) anddir: "rtl"where needed. - Paragraphs: 40–80 words, real sentences about type or printing, sized for the configured page; offer at least one text-size (9–11 pt) block.
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.
- 8d ago First seen · 61 lines · 80 tokens per session scan A 7054d41d2dae
typographer is an agent published in the GitHub repository eduairet/claude-font-proofer (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 747 once invoked, about $0.0004 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 agents, from other repositories
ui-design-agent
Specialized agent for UI design token management and prototype generation with W3C Design Tokens Format compliance. Core capabilities: W3C Design Tokens Format implementation with $type metadata and structured values State-based component definitions (default, hover, focus, active, disabled) Complete component library…
brand-architect
Brand identity specialist for creating comprehensive brand guidelines using Jungian archetypes. Use for creating brand.md, defining brand identity, selecting color palettes, establishing voice and tone, or analyzing existing brand assets.
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…