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/trtmn/agent-plugins/font-extractornpx skills add trtmn/agent-plugins --skill font-extractorgit clone --depth 1 https://github.com/trtmn/agent-pluginsWhat 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 | $0.00089 | $0.00721 |
| Opus 5 | $0.00044 | $0.00360 |
| Sonnet 5 | $0.00018 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
font-extractor scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash(curl -L *:*) How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Font Extractor
Extract all fonts used on a website and save them locally, organized by font family.
Workflow
- Ask — confirm where to save fonts (default:
./fonts/) - Download — find and download all font files from the site
- Organize — run the bundled script to sort them into family subdirectories
The heavy lifting of family detection is done by reading each font file's internal name table — no need to parse CSS family names.
Step 0: Confirm output location
Before downloading, ask the user where they'd like the fonts saved. Default to ./fonts/ if they don't have a preference. Use their chosen path in place of ./fonts/ throughout the remaining steps.
Step 1: Download all font files
Fetch the page HTML and find font file URLs. Use whatever approach gets the job done fastest:
- Parse
<link rel="stylesheet">tags, fetch each CSS file, extracturl(...)values from@font-faceblocks - Check
<link rel="preload" as="font">tags - Search inline
<style>blocks - If nothing turns up in CSS, search the JS bundle(s) for font file URLs (SPAs often embed them there)
- If using Claude-in-Chrome (
mcp__claude-in-chrome__*),read_network_requestswill catch dynamically loaded fonts
Font file extensions to look for: .woff2, .woff, .ttf, .otf, .eot
Download every font file URL you find into ./fonts/ (flat). Use curl -L with a Referer header matching the page URL — many CDNs require it:
mkdir -p ./fonts
curl -L -H "Referer: <page-url>" -o "./fonts/<filename>" "<font-url>"
Download all unique URLs. Do not deduplicate — different URLs may be different versions or formats of the same font, and the user may want all of them.
Step 2: Organize by family
Run the bundled organize script. It reads each font file's internal metadata to determine its family name, then moves files into ./fonts/<family>/ subdirectories:
uv run "$CLAUDE_PLUGIN_ROOT/skills/font-extractor/scripts/organize_fonts.py" ./fonts
What ships with it
1 file 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.
- 2d ago First seen · 76 lines · 89 tokens per session scan A b013b3ab0fc9
font-extractor is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It adds 89 tokens to every session and 721 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-guide
Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design…
gstack-openclaw-office-hours
Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…