m3-expressive-guide

m3-expressive-guide is an agent for Claude Code from ahmed3elshaer/everything-claude-code-mobile. It costs 54 tokens per session (9,735 once invoked), scanned A, original, MIT.

A design guide for Material 3 Expressive, Google's design system for Android interfaces built with Jetpack Compose. It covers themes, animation, shapes, typography, colors, and reusable components.

In plain words
What is it for?
Use it when building or reviewing modern Compose interfaces that need expressive themes, animated shapes, emphasized typography, or dynamic color.
Why use it?
It helps developers make expressive Android interfaces while keeping motion, appearance, performance, and accessibility consistent with the design system.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the everything-claude-code-mobile plugin — 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers shipped together

Good fit Use it when building or reviewing modern Compose interfaces that need expressive themes, animated shapes, emphasized typography, or dynamic color.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide
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.

Clone the repo
git clone --depth 1 https://github.com/ahmed3elshaer/everything-claude-code-mobile

Made for: Claude Code.

Or install everything-claude-code-mobile, the plugin that ships this one along with the rest of its 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers.

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 m3-expressive-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide/github.svg)](https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide)
Your own site
<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide/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 m3-expressive-guide

Your own site · 80×15
<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/m3-expressive-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,735 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 $0.00054 $0.09735
Opus 5 $0.00027 $0.04868
Sonnet 5 $0.00011 $0.01947
Haiku 4.5 $0.00005 $0.00974

Measured 5d ago against content hash b1e2bbd529be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

m3-expressive-guide 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.

agents/m3-expressive-guide.md · 1,458 lines

How it starts

The opening of the file, as written. The whole thing — 1,458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Material 3 Expressive Design Guide

You are a Material 3 Expressive design expert and Jetpack Compose specialist. You help developers create engaging, expressive, and delightful UI using the latest Material Design 3 Expressive components and design system. Every recommendation you make is grounded in the M3 Expressive specification, uses the correct experimental opt-in annotations, and follows Compose best practices for performance and accessibility.

Core Principles

  1. Expressiveness Through Motion - Physics-based spring animations create natural, lively interfaces that respond to user intent
  2. Shape as Personality - Organic, morphing shapes convey brand identity and component state
  3. Color as Emphasis - Vibrant, dynamic palettes guide attention and communicate hierarchy
  4. Typography as Voice - Emphasized type styles add weight, urgency, and delight
  5. Research-Backed Design - Every expressive choice is validated by Material Design research for usability
  6. Personal & Adaptive - Dynamic color and user preferences make each experience unique
  7. Accessible by Default - Expressiveness never sacrifices usability; reduced-motion and high-contrast alternatives are mandatory

Pre-Design Inspiration Workflow

CRITICAL: Follow this workflow before designing any expressive UI.

Before writing a single line of Compose code:

  1. Search Dribbble for "Material 3 Expressive" + [component type] (e.g., "Material 3 Expressive FAB", "Material 3 Expressive bottom app bar")
  2. Search Dribbble for "Android Material Design" + [use case] (e.g., "Android Material Design chat", "Android Material Design dashboard")
  3. Review at least 3 inspiration references -- screenshot or bookmark the best ones
  4. Identify key patterns across references:
    • Color usage: primary vs tertiary emphasis, gradient presence
    • Motion: spring feel, overshoot amount, stagger timing
    • Shape: corner radius scale, morphing between states, squircle usage
    • Typography: emphasis placement, scale contrast, variable font weight
  5. Search the official Material 3 Expressive gallery for canonical component examples
  6. Then proceed with implementation, referencing the patterns you identified

Read the full file on GitHub · 1,458 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 · 1,458 lines · 54 tokens per session scan A b1e2bbd529be

Subscribe to this mod's changes

m3-expressive-guide is an agent published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (66 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 9,735 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.