Borrowing it
Nothing to install: this file belongs to hyperlogue/r3. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hyperlogue/r3/main/.claude/skills/mobile-tier/SKILL.mdgit clone --depth 1 https://github.com/hyperlogue/r3Wrote 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/hyperlogue/r3/mobile-tier)<a href="https://agentmods.dev/skills/hyperlogue/r3/mobile-tier"><img src="https://agentmods.dev/badge/skills/hyperlogue/r3/mobile-tier/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/hyperlogue/r3/mobile-tier"><img src="https://agentmods.dev/badge/skills/hyperlogue/r3/mobile-tier.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 | $0.00121 | $0.02012 |
| Opus 5.5 | $0.00048 | $0.00805 |
| Sonnet 5.5 | $0.00024 | $0.00402 |
| Haiku 4.5 | $0.00012 | $0.00201 |
Grade A, and why
mobile-tier 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 3d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The phone tier
This file is the design source of truth for r3 below Tailwind md — update it
here when the mobile design changes.
The phone tier supports reading, version switching, threads, comments, resolution,
and Submit below md (768px). Artifact authoring stays with the publisher.
Portrait tablets keep the desktop layout.
The prime rule: isolate, don't interleave
Mobile must not add complexity to desktop code.
- All mobile UI lives in
web/src/mobile/, and desktop components never import from it. - Existing components get only inert
max-md:/pointer-coarse:class tweaks. The one exception isJumpToFile's inlinematchMedia("(pointer: coarse)")probe, which suppresses autofocus on touch — it can't importusePointerCoarsewithout breaking the isolation rule. - The single mount point is
ArtifactPageinweb/src/artifact-page.tsx, which swaps the side dock forMobileReviewChrome. Panel and domain state never fork, and the sameArtifactThreadsrenders with the same props either way.
web/src/mobile/ holds containers only: useIsMobile + usePointerCoarse
(both over useMediaQuery), MobileReviewChrome (bottom bar + the 3-state
discussion sheet), and AddCommentPill (the touch selection-anchor pill).
Side-by-side diffs never render below md. Two code columns don't fit a phone
pane, so ArtifactPage forces layout="unified" and the workspace toolbar hides the toggle
(max-md:hidden, an inert class — desktop components still don't import from
mobile/). The override deliberately does not write the persisted preference,
so a split-preferring reader gets split back on a wide viewport.
Layout
The file sidebar hides; HTML artifacts have no sidebar at any width. The shared
workspace toolbar retains its file controls below md. The version selector moves
from the top navigation into the three-dot details popover, where its choices
expand inline and selecting one closes the popover. An older selected version has
a Go to the latest version button in that version section; it also closes the
popover when selected. The artifact title and actions occupy the shared top navigation,
outside the scrolling pane;
the content toolbar sticks. The title truncates to preserve space for compact
controls, with metadata and the selected version's description in the details popover.
File headers prioritize filenames: source/rendered uses labeled icons, and Viewed
keeps its checkbox with a screen-reader label. These controls retain the compact
header height.
--pane-sticky-h records its measured height so file headers and Locate geometry
use the same offset. The pane stays the one source/diff scroll container.
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.
- 3d ago Changed efb173cf7674
- 4d ago Changed · +4 lines 5fcd6363bb67
- 8d ago Changed · +3 lines · +121 tokens per session f4d7c8802bc2
- 11d ago Changed 0d65244d6cc0
- 13d ago Changed · +13 lines 3ea7fc040b96
- 15d ago Changed · +9 lines 59da49864012
- 29d ago Changed b12271e91012
- 1mo ago Changed · +9 lines 925f847e4eaa
- 1mo ago First seen · 126 lines · 0 tokens per session scan A 9fee77dc842a
mobile-tier is a skill published in the GitHub repository hyperlogue/r3 (45 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 2,012 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
eval-skills
Audit a project or library of skills for metadata, trigger boundaries, workflow completion criteria, local resource closure, instruction economy, tool scope, effort, and routing evidence. Use before shipping skills, after importing a skill collection, or when a skill triggers too often or not at all.
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
design-patterns
Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
eval-rules
Audit Claude Code instruction rules in .claude/rules/ and /.claude/rules/: frontmatter, paths glob validity against real files, symlink load status, and day-to-day usefulness, then update rules with the user. Use for first-time rules setup, rules that apply too often or never, or periodic rules hygiene. Not for Codex…
review-pr
Perform a comprehensive code review of a pull request.