anthropic-brand-colors

anthropic-brand-colors is a skill for Claude Code, Codex from cxcscmu/SkillLearnBench. It costs 25 tokens per session (935 once invoked), scanned A, original, MIT.

A reference for Anthropic’s brand colors, design tokens, and typography rules. It lists exact color values and describes where colors should be used in designs such as posters and documents.

In plain words
What is it for?
Use it when creating Anthropic-branded graphics, documents, posters, or interfaces. It provides colors for backgrounds, dark structural elements, accents, and supporting annotations.
Why use it?
It helps keep visual materials consistent with Anthropic’s stated design standards. Exact color values reduce uncertainty when matching backgrounds, text, accents, and annotations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating Anthropic-branded graphics, documents, posters, or interfaces. It provides colors for backgrounds, dark structural elements, accents, and supporting annotations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cxcscmu/skilllearnbench/anthropic-brand-colors
Install

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.

Any agent
npx skills add cxcscmu/SkillLearnBench --skill anthropic-brand-colors
Clone the repo
git clone --depth 1 https://github.com/cxcscmu/SkillLearnBench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for anthropic-brand-colors

README.md
[![agentmods](https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/anthropic-brand-colors/github.svg)](https://agentmods.dev/skills/cxcscmu/skilllearnbench/anthropic-brand-colors)
Your own site
<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/anthropic-brand-colors"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/anthropic-brand-colors/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.

agentmods 80×15 button for anthropic-brand-colors

Your own site · 80×15
<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/anthropic-brand-colors"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/anthropic-brand-colors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 935 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00935
Opus 5 $0.00013 $0.00467
Sonnet 5 $0.00005 $0.00187
Haiku 4.5 $0.00003 $0.00093

Measured 10d ago against content hash 234f7b48fe33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

anthropic-brand-colors 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 10d 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.

skills/b1-one-shot-claude-haiku-4-5/anthropic-poster-design/anthropic-brand-colors/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anthropic Brand Colors & Design Standards

Official Brand Color Palette

Primary Colors

  • Anthropic Identity Light (Background): #F5F5F5

    • Primary background for posters and documents
    • Off-white, neutral, professional
    • High contrast with text elements
  • Anthropic Corporate Dark (Casing/Primary Dark): #1A1A1A

    • Deep charcoal, nearly black
    • Used for primary structural elements
    • Professional, premium appearance

Brand Accents

  • Primary Brand Accent (Interaction/Highlights): #6366F1

    • Indigo blue, modern and focused
    • Used for primary UI elements, connectors, key interaction points
    • Maintains good contrast on light backgrounds
  • Secondary Brand Accent (Thermal/Systems): #8B5CF6

    • Purple accent, warm and complementary
    • Used for secondary systems and thermal elements
    • Distinguishes subsystems from primary accents
  • Tertiary Brand Accent (PCB/Electronics): #3B82F6

    • Bright blue, digital/technical feel
    • Used for circuit boards and electrical components
    • Conveys technology and precision

Supporting Colors

  • Muted Mid Gray (Annotations/Leader Lines): #9CA3AF
    • Medium gray, subtle and non-intrusive
    • Used for annotation lines, borders, supporting text
    • Low contrast to maintain minimalism

Typography Standards

Primary Heading Font

Font Family: Inter

  • Weight: Bold (700)
  • Size: 64-72px for primary titles
  • Letter Spacing: -0.02em (tight tracking)
  • Color: Anthropic Corporate Dark (#1A1A1A)

Secondary/Annotation Font

Font Family: Inter or System Sans-serif

  • Weight: Regular (400) to Medium (500)
  • Size: 12-18px for annotations
  • Color: Muted Mid Gray for non-critical labels
  • Color: Corporate Dark for critical labels

Fallback Fonts (if Inter unavailable)

  • DejaVuSans
  • Arial
  • Helvetica
  • System sans-serif

Design Principles

Minimalism

  • Low saturation across all colors
  • Avoid neon or high-intensity gradients
  • Use color strategically for hierarchy and function
  • Ample whitespace and breathing room

Read the full file on GitHub · 118 lines

Changes

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.

  1. 10d ago First seen · 118 lines · 25 tokens per session scan A 234f7b48fe33

Subscribe to this mod's changes

anthropic-brand-colors is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 935 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 2026-08-30.