mobile-tier

mobile-tier is a skill for Claude Code, Codex from hyperlogue/r3. It costs 0 tokens per session (1,533 once invoked), scanned A, original, MIT.

Design instructions for how the r3 interface should work on phones and small screens.

In plain words
What is it for?
Use them when changing mobile layouts or mobile review features such as reading code, switching versions, viewing feedback, replying, resolving, or submitting.
Why use it?
They define which activities must remain usable on mobile and how mobile code should stay separate from the desktop interface.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hyperlogue/r3/mobile-tier
Any agent
npx skills add hyperlogue/r3 --skill mobile-tier
Clone the repo
git clone --depth 1 https://github.com/hyperlogue/r3

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 mobile-tier

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyperlogue/r3/mobile-tier.svg)](https://agentmods.dev/skills/hyperlogue/r3/mobile-tier)
Your own site
<a href="https://agentmods.dev/skills/hyperlogue/r3/mobile-tier"><img src="https://agentmods.dev/badge/skills/hyperlogue/r3/mobile-tier.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01533
Opus 5 $0.00000 $0.00766
Sonnet 5 $0.00000 $0.00307
Haiku 4.5 $0.00000 $0.00153

Measured 5d ago against content hash 9fee77dc842a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 5d 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.

.claude/skills/mobile-tier/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 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.

Phones are not first-class: no productive authoring is expected. But reading code, switching rounds/snapshots, reading feedback, resolve/submit, replying, and adding feedback all work below md (768px). 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 is JumpToFile's inline matchMedia("(pointer: coarse)") probe, which suppresses autofocus on touch — it can't import usePointerCoarse without breaking the isolation rule.
  • The single mount point is ReviewView, which swaps the side dock for MobileReviewChrome. Panel and domain state never fork, and the same FeedbackPanel renders with the same props either way.

web/src/mobile/ holds containers only: useIsMobile + usePointerCoarse (both over useMediaQuery), MobileReviewChrome (bottom bar + the 3-state feedback sheet), and AddFeedbackPill (the touch selection-anchor pill).

Side-by-side diffs never render below md. Two code columns don't fit a phone pane, so ReviewView forces layout="unified" and PaneToolbar 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 sidebar hides. The pane toolbar wraps into stacked full-width rows — round/snapshot selector (full-bleed trigger, chevron far right) · the round summary · the buttons.

The whole header stack (review header, review summary, toolbar rows) mounts inside the scroll pane on mobile. The review header + summary scroll away with the code, while the toolbar sticks at the pane top and each file header pins just below it. The toolbar's live height rides on the pane as --pane-sticky-h, which FileCard's header top and the anchor-in-view test both read (unset = 0 on desktop). So the sticky stack is toolbar + file header, the code gets the full height between the navbar and the bottom bar, and the pane stays the one scroll container.

Read the full file on GitHub · 126 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. 5d ago First seen · 126 lines · 0 tokens per session scan A 9fee77dc842a

Subscribe to this mod's changes

mobile-tier is a skill published in the GitHub repository hyperlogue/r3 (25 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,533 tokens. 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.

Related

Other skills, from other repositories