compose_skill

A package of AI-agent tools for Android Jetpack Compose development, Kotlin's toolkit for building app screens in code. It includes a coding assistant and a separate audit tool.

In plain words
What is it for?
Use it when developing Compose applications and when you also want an audit of performance, state, effects, animations, paging, tests, focus, or launch resources.
Why use it?
It brings Compose-specific guidance and repository review into one installable package, covering both implementation and checking work.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add hamen/compose_skill
agentmods
npx agentmods add plugins/hamen/compose_skill/marketplace
Clone the repo
git clone --depth 1 https://github.com/hamen/compose_skill

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

compose_skill 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.

.claude-plugin/marketplace.json · 35 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "compose_skill",
  "description": "Agent skills for Jetpack Compose development — coding assistant + audit tool",
  "owner": {
    "name": "Ivan Morgillo"
  },
  "plugins": [
    {
      "name": "compose-agent",
      "description": "Agent skill that helps AI coding assistants write modern Jetpack Compose: correct state, effects, animation APIs, Paging 3 in Compose, performance-aware modifiers, Navigation 3, coroutines on lifecycle, UI tests, focus/keyboard navigation, Compose Multiplatform boundaries, Android launch resources, and idiomatic Kotlin.",
      "author": { "name": "Ivan Morgillo" },
      "category": "development",
      "source": {
        "source": "git-subdir",
        "url": "https://github.com/hamen/compose_skill.git",
        "path": "skills/compose-agent"
      },
      "tags": ["android", "jetpack-compose", "kotlin", "animation", "paging", "ui-testing", "focus", "kotlin-multiplatform", "splash-screen", "agent-skill"]
    },
    {
      "name": "jetpack-compose-audit",
      "description": "Strict, evidence-based audit for Android Jetpack Compose repositories. Produces a 0-100 score with every deduction cited against developer.android.com and coverage notes for animation performance, Paging 3 list/load-state correctness, UI tests, focus/keyboard, Compose Multiplatform, and Android launch UX surfaces.",
      "author": { "name": "Ivan Morgillo" },
      "category": "development",
      "source": {
        "source": "git-subdir",
        "url": "https://github.com/hamen/compose_skill.git",
        "path": "skills/jetpack-compose-audit"
      },
      "tags": ["android", "jetpack-compose", "audit", "performance", "animation", "paging", "ui-testing", "focus", "kotlin-multiplatform", "splash-screen"]
    }
  ]
}
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 · 35 lines scan A d8bf06f7d482

Subscribe to this mod's changes

compose_skill is a plugin published in the GitHub repository hamen/compose_skill (367 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.