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 cxcscmu/SkillLearnBench --skill anthropic-brand-tokensgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/anthropic-brand-tokens)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/anthropic-brand-tokens"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/anthropic-brand-tokens/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/cxcscmu/skilllearnbench/anthropic-brand-tokens"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/anthropic-brand-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00721 |
| Opus 5 | $0.00012 | $0.00360 |
| Sonnet 5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
anthropic-brand-tokens 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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anthropic Brand Tokens
Color Palette
Core Identity Colors
| Token | Name | HEX | Usage |
|---|---|---|---|
--color-bg-light |
Identity Light | #F5F0E8 |
Primary background, light surfaces |
--color-corporate-dark |
Corporate Dark | #1A1A1A |
Primary text, outer casing, headings |
--color-mid-gray |
Muted Mid Gray | #8C8C8C |
Annotation lines, secondary text |
Brand Accent Colors
| Token | Name | HEX | Usage |
|---|---|---|---|
--color-accent-primary |
Primary Brand Accent | #C96442 |
CTAs, interaction highlights, connectors |
--color-accent-secondary |
Secondary Brand Accent | #8B9E8E |
Thermal/secondary hardware, calm areas |
--color-accent-tertiary |
Tertiary Brand Accent | #6B7FA3 |
PCB substrate, informational elements |
Supporting Tones
| Token | Name | HEX |
|---|---|---|
| Warm Off-White | Surface / Card | #FAF8F3 |
| Soft Divider | Rule / Border | #DDD8CE |
| Deep Charcoal | Dark Variant | #2D2D2D |
Design Principles
- Low-saturation: Desaturated, muted tones. No neon, no AI-gradient blues/purples.
- Minimalist: Generous whitespace, clean geometry.
- Warm Neutral Base: Cream/off-white background (Identity Light) as the canvas.
- Monochromatic Accents: Accents are desaturated earth/slate tones, not vivid.
Typography
Primary Font Stack
- Heading / Display:
Styrene A(Anthropic proprietary) → fallback"GT Walsheim"→"Inter"→"Liberation Sans" - Body / Label: Same stack at smaller sizes
- Monospace / Technical:
"IBM Plex Mono"→"Courier New"
Font Weights
- Display title: Bold / 700
- Section labels: SemiBold / 600
- Body / annotations: Regular / 400
System Font Fallbacks (Linux)
When proprietary fonts are unavailable, use:
HEADING_FONT_NAME = "DejaVu Sans" # or "Liberation Sans"
font_paths = {
"bold": "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf",
"regular": "/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
}
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.
- 9d ago First seen · 66 lines · 24 tokens per session scan A a269f0202250
anthropic-brand-tokens is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 721 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
geometric-layout-repair
Use when producing a minimally changed repaired 2D layout in JSON from extracted architectural geometry and rule-based clearance constraints.
ada-plan-view-accessibility
Use when checking simplified ADA-derived plan-view bathroom accessibility constraints such as turning space, door clear width, toilet centerline, grab bars, and lavatory knee/toe clearance.
web-interface-guidelines
Vercel's comprehensive UI guidelines for building accessible, performant web interfaces. Use this skill when reviewing or building UI components for compliance with best practices around accessibility, performance, animations, and visual stability.
Visual Regression Review
Compare browser-rendered UI state against expected layout, content, and responsive behavior.
Popular Web Designs
Design contemporary web layouts, visual systems, and polished interface patterns.
baoyu-infographic
A tool for creating infographics, which are visual layouts that explain information or data.