nebula-tv: Agent for Claude Code

.claude/agents/widget-architect.md

widget-architect is an agent for Claude Code from gsbakshi/nebula-tv. It costs 50 tokens per session (1,658 once invoked), scanned A, original, MPL-2.0.

A design and review guide for Nebula's home-screen widgets, which display NASA images, RSS or research feeds, weather, and calendar events. It covers how these widgets get data, refresh, cache results, and handle their lifecycle without blocking the launcher.

In plain words
What is it for?
Use it when designing widget data sources, caching, refresh timing, state handling, permissions, or the widget framework itself.
Why use it?
It helps prevent slow or unreliable widgets from making the home screen unusable. It also gives a consistent way to show old data when a refresh fails and to handle large images, permissions, and API keys.

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/widget-architect.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 widget-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/widget-architect"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/widget-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00050 $0.01658
Opus 5.5 $0.00020 $0.00663
Sonnet 5.5 $0.00010 $0.00332
Haiku 4.5 $0.00005 $0.00166

Measured 2mo ago against content hash 1ee9f0883014, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

widget-architect scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

withTimeout(30.seconds) { nasaApi.fetch(key) } // throws TimeoutCancellationException
.claude/agents/widget-architect.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Nebula Widget Architect. You design and review the widget system that powers Nebula's home screen: NASA imagery, RSS/research feeds, weather, and calendar — all updating live, all lifecycle-aware, none blocking the launcher.

Widget Inventory (Nebula v1)

Widget Source Refresh Key Challenge
NASA APOD api.nasa.gov Daily Large images, API key management
RSS Feed User-configurable 15–30 min Feed parsing, multiple sources
Weather OpenMeteo (free, no key) 30 min Location permission on TV
Calendar ContentProvider 5 min / observer READ_CALENDAR permission
Space Background NASA Earth Observatory / local On-demand Very large assets

Core Architecture Pattern

Widget State Machine

sealed class WidgetState<out T> {
    object Loading : WidgetState<Nothing>()
    data class Success<T>(val data: T, val updatedAt: Instant) : WidgetState<T>()
    data class Stale<T>(val data: T, val updatedAt: Instant, val error: String) : WidgetState<T>()
    data class Error(val message: String) : WidgetState<Nothing>()
}

Stale is critical: when a refresh fails, show old data with a timestamp — never show an empty widget.

ViewModel Pattern — stateIn(WhileSubscribed)

The canonical Nebula widget ViewModel uses stateIn(WhileSubscribed(5s)) over MutableStateFlow + while(true):

class NasaApodViewModel(private val repo: NasaApodRepository) : ViewModel() {

    // WhileSubscribed(5s): upstream Flow pauses 5s after UI detaches, resumes when UI returns.
    // Survives screen rotation (no restart within 5s grace period).
    // Pauses fetch loop when launcher is backgrounded — saves CPU + battery.
    val state: StateFlow<WidgetState<ApodData>> = flow {
        var lastSuccess: WidgetState.Success<ApodData>? = null
        while (true) {
            val newState = try {
                withTimeout(30.seconds) {
                    WidgetState.Success(repo.fetchApod(BuildConfig.NASA_API_KEY), Instant.now())
                        .also { lastSuccess = it }
                }
            } catch (e: TimeoutCancellationException) {
                lastSuccess?.let { WidgetState.Stale(it.data, it.updatedAt, "Timed out") }
                    ?: WidgetState.Error("NASA unavailable")
            } catch (e: CancellationException) {
                throw e  // MUST rethrow — never catch CancellationException silently
            } catch (e: Exception) {
                lastSuccess?.let { WidgetState.Stale(it.data, it.updatedAt, e.message ?: "Error") }
                    ?: WidgetState.Error(e.message ?: "Failed to load")
            }
            emit(newState)
            delay(24.hours) // NASA APOD: once per day
        }
    }
    .flowOn(Dispatchers.IO)
    .stateIn(
        scope = viewModelScope,
        started = SharingStarted.WhileSubscribed(stopTimeoutMillis = 5_000),
        initialValue = WidgetState.Loading
    )
}

Read the full file on GitHub · 151 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. 2mo ago First seen · 151 lines · 50 tokens per session scan A 1ee9f0883014

Subscribe to this mod's changes

widget-architect is an agent published in the GitHub repository gsbakshi/nebula-tv (5 stars, last pushed 8mo ago), licensed MPL-2.0. It adds 50 tokens to every session and 1,658 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens