nebula-tv: Agent for Claude Code

.claude/agents/compose-performance-reviewer.md

compose-performance-reviewer is an agent for Claude Code from gsbakshi/nebula-tv. It costs 40 tokens per session (811 once invoked), scanned A, original, MPL-2.0.

A reviewer for Jetpack Compose code, Google's Kotlin toolkit for building Android user interfaces, with attention to unnecessary screen updates and memory use.

In plain words
What is it for?
Use it when building app grids, widgets, animated backgrounds, or refresh loops in the Nebula launcher.
Why use it?
It helps find performance problems that can make data-heavy or animated Android TV screens slow or waste resources.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is gsbakshi/nebula-tv's own configuration. It tells Claude Code how to work on nebula-tv itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nebula-tv configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gsbakshi/nebula-tv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gsbakshi/nebula-tv/main/.claude/agents/compose-performance-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/gsbakshi/nebula-tv

Made for: Claude Code.

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 compose-performance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/compose-performance-reviewer/github.svg)](https://agentmods.dev/agents/gsbakshi/nebula-tv/compose-performance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/compose-performance-reviewer"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/compose-performance-reviewer/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 compose-performance-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/compose-performance-reviewer"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/compose-performance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 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 $0.00040 $0.00811
Opus 5 $0.00020 $0.00405
Sonnet 5 $0.00008 $0.00162
Haiku 4.5 $0.00004 $0.00081

Measured 10d ago against content hash 814cf0ce60b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compose-performance-reviewer 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 10d 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/agents/compose-performance-reviewer.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Nebula Compose Performance Reviewer. Nebula runs on Android TV hardware ranging from budget boxes (1GB RAM, weak CPU) to Nvidia Shield. The launcher is always resident in memory — performance regressions are permanent.

Context

  • Compose BOM 2025.07.00 / Kotlin 2.2.0
  • Multiple data streams: app grid, NASA/RSS/weather widgets, live backgrounds
  • collectAsStateWithLifecycle() available (lifecycle-runtime-compose)
  • Coroutines 1.10.2

Performance Audit Checklist

Recomposition Scope

  • State reads scoped to smallest composable that needs them (avoid reading state high up then passing to deep children when only deep child recomposes)
  • remember {} used for expensive operations: icon loading, string formatting, regex
  • rememberUpdatedState() used when passing callbacks into LaunchedEffect / coroutines
  • Data classes passed as params are @Stable or @Immutable (or are primitive/String)
  • Lambdas are not created inline where they cause recomposition (extract to val or use rememberUpdatedState)

State Management

  • derivedStateOf {} used for computed values that depend on other state
  • MutableStateFlow not converted to State unnecessarily mid-composition
  • collectAsStateWithLifecycle() used — NOT collectAsState() (stops collection when backgrounded)
  • State not duplicated (one source of truth per data type)

Lazy Lists — App Grid (Critical Path)

  • key { packageName } in items {} for the app grid
  • App icon Drawable → Bitmap → ImageBitmap conversion happens off-composition (in ViewModel or background thread)
  • AsyncImage (Coil) or equivalent used — NOT synchronous bitmap.asImageBitmap() on main thread
  • contentPadding set correctly to avoid remeasure on scroll

Background Animation (NASA / Cosmic Backgrounds)

  • Animation does NOT cause recomposition of static panels (state isolated in background composable)
  • AnimatedContent or Crossfade used for image transitions (not manual alpha animations that trigger full recompose)
  • Image preloading: next background loaded while current is displayed
  • Background composable uses rememberInfiniteTransition only for continuous effects

Read the full file on GitHub · 60 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. 10d ago First seen · 60 lines · 40 tokens per session scan A 814cf0ce60b0

Subscribe to this mod's changes

compose-performance-reviewer is an agent published in the GitHub repository gsbakshi/nebula-tv (5 stars, last pushed 6mo ago), licensed MPL-2.0. It adds 40 tokens to every session and 811 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

flutter-reviewer

Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.

affaan-m/ECC · 50 tokens

harmonyos-app-resolver

HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.

affaan-m/ECC · 49 tokens

textkit-auditor

Use this agent when the user mentions TextKit review, text layout issues, Writing Tools integration, or UITextView/NSTextView code review. Automatically scans for TextKit 1 fallback triggers, deprecated glyph APIs, and missing TextKit 2 features - prevents loss of Writing Tools support and ensures modern text handling…

CharlesWiltgen/Axiom · 245 tokens

resize-auditor

Use this agent when the user mentions window resizing support, resizable-window readiness, iPhone Mirroring compatibility, scene-lifecycle migration checking, or preparing an app for the 27-cycle resizing model. Automatically scans UIKit code, Info.plist, and the scene manifest for resize-readiness violations …

CharlesWiltgen/Axiom · 294 tokens

swiftdata-auditor

Use this agent when the user mentions SwiftData review, @Model issues, SwiftData migration safety, or SwiftData performance checking. Automatically scans SwiftData code for the 10 most critical violations - struct models, missing VersionedSchema models, relationship defaults, migration timing, background context…

CharlesWiltgen/Axiom · 250 tokens

energy-auditor

Use this agent when the user mentions battery drain, energy optimization, power consumption audit, or pre-release energy check. Automatically scans codebase for the 8 most common energy anti-patterns - timer abuse, polling instead of push, continuous location, animation leaks, background mode misuse, network…

CharlesWiltgen/Axiom · 149 tokens