AAS Core is a local control plane for coding agents that lets them search a large catalogue of skills, choose a stack, validate it, and create a reproducible plan. It is used to assemble and review agent workflows through its CLI, local MCP server, catalogue, plugins, and Workbench. The catalogue add-ons provide the skills, plugins, bundles, and workflows that AAS Core helps agents select and validate.
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 sickn33/agentic-awesome-skills --skill hig-foundationsgit clone --depth 1 https://github.com/sickn33/agentic-awesome-skillsWrote 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/sickn33/agentic-awesome-skills/hig-foundations)<a href="https://agentmods.dev/skills/sickn33/agentic-awesome-skills/hig-foundations"><img src="https://agentmods.dev/badge/skills/sickn33/agentic-awesome-skills/hig-foundations/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/sickn33/agentic-awesome-skills/hig-foundations"><img src="https://agentmods.dev/badge/skills/sickn33/agentic-awesome-skills/hig-foundations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01661 |
| Opus 5.5 | $0.00005 | $0.00664 |
| Sonnet 5.5 | $0.00002 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
hig-foundations 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 yesterday.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple HIG: Design Foundations
Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
Key Principles
-
Prioritize content over chrome. Reduce visual clutter. Use system-provided materials and subtle separators rather than heavy borders and backgrounds.
-
Build in accessibility from the start. Design for VoiceOver, Dynamic Type, Reduce Motion, Increase Contrast, and Switch Control from day one. Every interactive element needs an accessible name; reuse the semantic control label and avoid redundant manual labels.
-
Use system colors and materials. System colors adapt to light/dark mode, increased contrast, and vibrancy. Prefer semantic colors (
label,secondaryLabel,systemBackground) over hard-coded values. -
Use platform fonts and icons. Use the platform system font via semantic text styles. SF Pro, SF Compact, SF Mono and New York are options with platform and licensing constraints; not all are the default on every platform. Follow the type hierarchy at recommended sizes. Use SF Symbols for iconography.
-
Match platform conventions. Align look and behavior with system standards. Provide direct, responsive manipulation and clear feedback for every action.
-
Respect privacy. Request permissions only when needed, explain why clearly, provide value before asking for data. Design for minimal data collection.
-
Support internationalization. Accommodate text expansion, right-to-left scripts, and varying date/number formats. Use Auto Layout for dynamic content sizing.
-
Use motion purposefully. Animation should communicate meaning and spatial relationships. Honor Reduce Motion using reduced or static alternatives appropriate to the setting; a crossfade is an option rather than a requirement for every animation.
Reference Index
| Reference | Topic | Key content |
|---|---|---|
| accessibility.md | Accessibility | VoiceOver, Dynamic Type, color contrast, motor accessibility, Switch Control, audio descriptions |
| app-icons.md | App Icons | Icon grid, platform-specific sizes, single focal point, opaque backgrounds and platform-specific foreground transparency |
| branding.md | Branding | Integrating brand identity within Apple's design language, subtle branding, custom tints |
| color.md | Color | System colors, Dynamic Colors, semantic colors, custom palettes, contrast ratios |
| dark-mode.md | Dark Mode | Elevated surfaces, semantic colors, adapted palettes, vibrancy, testing in both modes |
| icons.md | Icons | Glyph icons, SF Symbols integration, custom icon design, icon weights, optical alignment |
| images.md | Images | Image resolution, @2x/@3x assets, vector assets, image accessibility |
| immersive-experiences.md | Immersive Experiences | AR/VR design, spatial immersion, comfort zones, progressive immersion levels |
| inclusion.md | Inclusion | Diverse representation, non-gendered language, cultural sensitivity, inclusive defaults |
| layout.md | Layout | Margins, spacing, alignment, safe areas, adaptive layouts, readable content guides |
| materials.md | Materials | Vibrancy, blur, translucency, system materials, material thickness |
| motion.md | Motion | Animation curves, transitions, continuity, Reduce Motion support, physics-based motion |
| privacy.md | Privacy | Permission requests, usage descriptions, privacy nutrition labels, minimal data collection |
| right-to-left.md | Right-to-Left | RTL layout mirroring, bidirectional text, icons that flip, exceptions |
| sf-symbols.md | SF Symbols | Symbol categories, rendering modes, variable color, custom symbols, weight matching |
| spatial-layout.md | Spatial Layout | visionOS window placement, depth, ergonomic zones, Z-axis design |
| typography.md | Typography | SF Pro, Dynamic Type sizes, text styles, custom fonts, font weight hierarchy, line spacing |
| writing.md | Writing | UI copy guidelines, tone, capitalization rules, error messages, button labels, conciseness |
What ships with it
18 files 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.
- references/accessibility.md 29 KB
- references/app-icons.md 20 KB
- references/branding.md 4.6 KB
- references/color.md 45 KB
- references/dark-mode.md 14 KB
- references/icons.md 29 KB
- references/images.md 17 KB
- references/immersive-experiences.md 22 KB
- references/inclusion.md 19 KB
- references/layout.md 38 KB
- references/materials.md 24 KB
- references/motion.md 11 KB
- references/privacy.md 28 KB
- references/right-to-left.md 30 KB
- references/sf-symbols.md 35 KB
- references/spatial-layout.md 14 KB
- references/typography.md 50 KB
- references/writing.md 12 KB
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.
- yesterday First seen · 113 lines · 12 tokens per session scan A 0612ffddbd0e
hig-foundations is a skill published in the GitHub repository sickn33/agentic-awesome-skills (49,614 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,661 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-11-12.
hig-foundations compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hig-foundationssickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 12 | Claude Code |
| build-nitro-modulesMarshanda14816/agent-skills | Skill | 2 | 1mo ago | none | A | 84 | Claude Code, Codex |
| android-playstore-builderAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 38 | Claude Code, Codex |
| flutter-developerAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 33 | Claude Code, Codex |
| ios-appstore-builderAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 37 | Claude Code, Codex |
| mobile-ci-cdAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 34 | Claude Code, Codex |
| animation-engineerAtulPurohit/Antigravity-Awesome-Skills | Skill | 5 | 4mo ago | none | A | 21 | Claude Code, Codex |