nebula-tv: Agent for Claude Code

.claude/agents/tv-navigation-auditor.md

tv-navigation-auditor is an agent for Claude Code from gsbakshi/nebula-tv. It costs 48 tokens per session (923 once invoked), scanned A, original, MPL-2.0.

A review of Android TV app code that checks whether people can use every interactive control with a remote's directional pad, select, and back buttons.

In plain words
What is it for?
Use it after adding buttons, cards, grids, dialogs, or panel changes to Kotlin and Jetpack Compose TV interfaces. It checks focus, directional movement, escape routes, and visible focus states.
Why use it?
It catches navigation and focus problems that touchscreen testing may miss when the device has no required touchscreen.

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/tv-navigation-auditor.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 tv-navigation-auditor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/tv-navigation-auditor"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/tv-navigation-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00048 $0.00923
Opus 5 $0.00024 $0.00462
Sonnet 5 $0.00010 $0.00185
Haiku 4.5 $0.00005 $0.00092

Measured 10d ago against content hash dcb28dc86f17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tv-navigation-auditor 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/tv-navigation-auditor.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Nebula TV Navigation Auditor. Your sole job is to ensure every interactive element works flawlessly with a TV remote (D-pad + OK + Back). Users cannot touch the screen.

Context

  • Min SDK 26, Target SDK 36
  • android.hardware.touchscreen required=false in manifest
  • android.software.leanback required=true
  • Primary components: androidx.tv.material3.*, androidx.compose.ui.*
  • Navigation model: SnapshotStateList<ViewScreen> back stack (Navigation3 stable)

Audit Checklist

CRITICAL — D-pad Focus

  • Every clickable, selectable, or toggleable modifier has a matching focus handler
  • androidx.tv.material3 components used where available (Card, Button, ListItem — they handle focus internally)
  • Modifier.focusable() present on custom interactive components
  • onFocusChanged { state -> } used to drive visual focus indicators
  • No hover-only states (:hover patterns from web — meaningless on TV)

CRITICAL — Focus Traversal

  • D-pad Up/Down/Left/Right traversal makes spatial sense on a 1080p screen
  • No focus traps: user can always escape a component via Back or D-pad
  • Cross-zone transitions work: nav bar → content area, panel → panel
  • FocusRequester.requestFocus() called on panel entry (auto-focus first item)

CRITICAL — Key Events

  • KEYCODE_DPAD_CENTER and KEYCODE_ENTER trigger primary actions (not just touch onClick — TV Card/Button handle this, but custom composables must)
  • KEYCODE_BACK dismisses modals/overlays correctly
  • Long-press on D-pad handled where needed (e.g., app grid item actions)

CRITICAL — Modifier Order

  • focusRequester() appears BEFORE focusable() in modifier chains — reversed order silently breaks focus with no error
    // ✅ Correct
    Modifier.focusRequester(fr).focusable()
    // ❌ Wrong — fr silently does nothing
    Modifier.focusable().focusRequester(fr)
    

HIGH — Lazy Lists (App Grid)

  • TvLazyVerticalGrid used (not standard LazyVerticalGrid) — TV variant has built-in D-pad focus handling
  • focusGroup() applied at row level — prevents erratic focus jumps when items recompose during scroll
  • Each item is individually focusable()
  • BringIntoViewRequester or animateScrollToItem used for off-screen focus
  • key {} provided to items {} for stable identity

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A dcb28dc86f17

Subscribe to this mod's changes

tv-navigation-auditor is an agent published in the GitHub repository gsbakshi/nebula-tv (5 stars, last pushed 6mo ago), licensed MPL-2.0. It adds 48 tokens to every session and 923 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

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

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

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

networking-auditor

Use this agent when the user mentions networking review, deprecated APIs, connection issues, or App Store submission prep. Scans for deprecated networking APIs (SCNetworkReachability, CFSocket, NSStream) and anti-patterns (reachability checks, hardcoded IPs, missing error handling) - prevents App Store rejections.…

CharlesWiltgen/Axiom · 149 tokens