axiom-hig-ref

axiom-hig-ref is a skill for Claude Code, Codex from ComeOnOliver/skillshub. It costs 64 tokens per session (8,381 once invoked), scanned A, original, MIT.

A guide to Apple’s Human Interface Guidelines, the rules and recommendations for designing clear, consistent, and accessible interfaces on Apple devices. It covers typography, colours, backgrounds, symbols, Dark Mode, and accessibility.

In plain words
What is it for?
Use it when choosing UI styles, reviewing an app design, or explaining why a particular Apple interface pattern should be used.
Why use it?
It helps resolve design decisions and catch interfaces that do not follow familiar Apple patterns or work well for different users.

Skill for Claude CodeCodex

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

Good fit Use it when choosing UI styles, reviewing an app design, or explaining why a particular Apple interface pattern should be used.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/comeonoliver/skillshub/axiom-hig-ref
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 ComeOnOliver/skillshub --skill axiom-hig-ref
Clone the repo
git clone --depth 1 https://github.com/ComeOnOliver/skillshub

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 axiom-hig-ref

README.md
[![agentmods](https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-hig-ref/github.svg)](https://agentmods.dev/skills/comeonoliver/skillshub/axiom-hig-ref)
Your own site
<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-hig-ref"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-hig-ref/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 axiom-hig-ref

Your own site · 80×15
<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-hig-ref"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-hig-ref.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,381 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.
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 $0.00064 $0.08381
Opus 5 $0.00032 $0.04190
Sonnet 5 $0.00013 $0.01676
Haiku 4.5 $0.00006 $0.00838

Measured 9d ago against content hash 065e7709f26d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

axiom-hig-ref 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.

skills/CharlesWiltgen/Axiom/axiom-hig-ref/SKILL.md · 1,238 lines

How it starts

The opening of the file, as written. The whole thing — 1,238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple Human Interface Guidelines — Comprehensive Reference

Overview

The Human Interface Guidelines (HIG) define Apple's design philosophy and provide concrete guidance for creating intuitive, accessible, platform-appropriate experiences across all Apple devices.

Three Core Principles

Every design decision should support these principles:

1. Clarity Content is paramount. Interface elements should defer to content, not compete with it. Every element has a purpose, unnecessary complexity is eliminated, and users should immediately know what they can do without extensive instructions.

2. Consistency Apps use standard UI elements and familiar patterns. Navigation follows platform conventions, gestures work as expected, and components appear in expected locations. This familiarity reduces cognitive load.

3. Deference The UI should not distract from essential content. Use subtle backgrounds, receding navigation when not needed, restrained branding, and let content be the hero.

From Apple HIG: "Deference makes an app beautiful by ensuring the content stands out while the surrounding visual elements do not compete with it."

Design System Philosophy

From WWDC25: "A systematic approach means designing with intention at every level, ensuring that all elements, from the tiniest control to the largest surface, are considered in relation to the whole."

Related Skills
  • Use axiom-hig for quick decisions and checklists
  • Use axiom-liquid-glass for iOS 26 material implementation
  • Use axiom-liquid-glass-ref for iOS 26 app-wide adoption
  • Use axiom-accessibility-diag for accessibility troubleshooting

Color System

Semantic Colors Explained

Instead of hardcoded color values, use semantic colors that describe the purpose of a color rather than its appearance. Semantic colors automatically adapt to light/dark mode and accessibility settings.

Key insight from WWDC19: "Think of Dark Mode as having the lights dimmed rather than everything being flipped inside out." Colors are NOT simply inverted—table row backgrounds are lighter in both modes.

Read the full file on GitHub · 1,238 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. 9d ago First seen · 1,238 lines · 64 tokens per session scan A 065e7709f26d

Subscribe to this mod's changes

axiom-hig-ref is a skill published in the GitHub repository ComeOnOliver/skillshub (63 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 8,381 once invoked, about $0.0003 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.