create-activity

A command that creates an Android screen using Jetpack Compose, Android's toolkit for describing app interfaces in Kotlin. It adds a ViewModel for screen state, navigation setup, common UI states, theming, accessibility labels, and a preview.

In plain words
What is it for?
Use it to scaffold screens with lists or other Compose layouts, connect them to an app's navigation, and add features such as refresh, pagination, or infinite scrolling when needed.
Why use it?
It removes repetitive setup when starting a new screen and gives the screen a consistent way to manage data and user actions. It also accounts for loading, error, empty, and accessibility states.

Command

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 commands/rohitg00/awesome-claude-code-toolkit/create-activity
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00000 $0.00296
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash 125056360e23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-activity 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 2d 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.

plugins/android-developer/commands/create-activity.md · 29 lines

What it actually says

/create-activity - Create Android Activity/Screen

Generate a Jetpack Compose screen with proper architecture.

Steps

  1. Ask the user for the screen name, purpose, and navigation requirements
  2. Create the Composable function with the screen content
  3. Add a ViewModel class for the screen's state management
  4. Define the UI state as an immutable data class with all screen properties
  5. Implement the screen layout using Compose components: Column, Row, LazyList
  6. Add navigation parameters using Navigation Compose type-safe arguments
  7. Include loading, error, and empty state handling with proper UI
  8. Add Material 3 theming: colors, typography, shapes from the app theme
  9. Implement pull-to-refresh, pagination, or infinite scroll if applicable
  10. Add content descriptions for accessibility (TalkBack support)
  11. Create a Compose Preview with @Preview annotation and sample data
  12. Register the screen in the navigation graph

Rules

  • Follow the UDF (Unidirectional Data Flow) pattern with ViewModel
  • Use StateFlow in ViewModel, collected as State in Composable
  • Keep Composable functions stateless; hoist state to the caller
  • Use remember and derivedStateOf for expensive computations
  • Follow Material 3 guidelines for spacing, elevation, and component usage
  • Support both portrait and landscape orientations
  • Add string resources for all user-visible text (no hardcoded strings)
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. 2d ago First seen · 29 lines · 0 tokens per session scan A 125056360e23

Subscribe to this mod's changes

create-activity is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,578 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 296 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.