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 devanshuDesai/agent-skills --skill expo-liquid-glassgit clone --depth 1 https://github.com/devanshuDesai/agent-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/devanshudesai/agent-skills/expo-liquid-glass)<a href="https://agentmods.dev/skills/devanshudesai/agent-skills/expo-liquid-glass"><img src="https://agentmods.dev/badge/skills/devanshudesai/agent-skills/expo-liquid-glass/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/devanshudesai/agent-skills/expo-liquid-glass"><img src="https://agentmods.dev/badge/skills/devanshudesai/agent-skills/expo-liquid-glass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00165 | $0.01856 |
| Opus 5.5 | $0.00066 | $0.00742 |
| Sonnet 5.5 | $0.00033 | $0.00371 |
| Haiku 4.5 | $0.00016 | $0.00186 |
Grade A, and why
expo-liquid-glass 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 2mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo Liquid Glass
Ship Liquid Glass UI that feels native, stays legible, and degrades safely across iOS/Android.
Execution Order
- Confirm platform/runtime constraints.
- Check design alignment against HIG buckets (recommended for design-heavy tasks).
- Pick one primary implementation path (add a second path only if needed).
- Apply Apple-aligned visual rules before writing code.
- Implement guarded glass components with explicit fallbacks.
- Run accessibility and visual QA in both light/dark and clear/tinted appearances.
1) Preflight Constraints
- Use Liquid Glass only for controls/navigation chrome, not primary content surfaces.
- Treat these APIs as fast-moving: check current Expo SDK docs before finalizing syntax.
- Expect a development build for advanced iOS-native features:
expo-glass-effectand@expo/uiare not reliable in Expo Go on iOS. - Keep scope on Liquid Glass in Expo: use HIG rules to guide implementation, not to redesign unrelated product behavior.
2) Design Alignment (Recommended for design-heavy tasks)
For tasks that involve significant visual design decisions, evaluate against these HIG buckets:
- Foundations Check materials, color, layout, motion, and accessibility implications.
- Patterns Check navigation/search/flow behavior for consistency with system expectations.
- Components Check bars, buttons, menus, fields, sidebars, and overlays used by the screen.
- Inputs Check touch, gesture, keyboard, and pointer behavior for parity and discoverability.
See references/apple-liquid-glass-design.md for practical design guidance.
If a proposed style conflicts with HIG intent, prefer the HIG-consistent option.
3) Choose the Primary Path
| Path | Use It For | Tradeoffs |
|---|---|---|
expo-glass-effect |
Most RN screens that need glass chips, floating buttons, toolbars, grouped controls | Best default in Expo; must guard runtime availability |
@expo/ui (Host + SwiftUI modifiers) |
Native SwiftUI composition, advanced glass transitions, coordinated IDs/namespaces | iOS-family only, dev-build workflow, SwiftUI mental model |
expo-router/unstable-native-tabs |
System-native Liquid Glass tab bars and iOS 26 nav behavior | Unstable API; syntax differs between SDK 54 and 55 |
@callstack/liquid-glass |
Non-Expo RN or teams standardizing on Callstack package | iOS/tvOS focus; also requires fallbacks and runtime checks |
What ships with it
5 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.
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.
- 2mo ago First seen · 199 lines · 165 tokens per session scan A 730c87099f9a
expo-liquid-glass is a skill published in the GitHub repository devanshuDesai/agent-skills (12 stars, last pushed 9mo ago), licensed MIT. It adds 165 tokens to every session and 1,856 once invoked, about $0.0007 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 2026-08-31.
expo-liquid-glass compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| expo-liquid-glassdevanshuDesai/agent-skills | Skill | 12 | 9mo ago | MIT | A | 165 | Claude Code, Codex |
| display-glasses-with-jetpack-compose-glimmerandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 112 | Claude Code |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| expo-design-systemexpo/skills | Skill | 4.1k | yesterday | MIT | A | 197 | Claude Code, Codex |
| flutter-build-responsive-layoutflutter/agent-plugins | Skill | 3.2k | 2d ago | BSD-3-Clause | A | 51 | Claude Code |
| omh-apple-designrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 83 | Claude Code, Codex |
| axiom-audit-liquid-glassCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 32 | Codex |