frogo-sdk: Skill for Claude Code

.agents/skills/camerax/SKILL.md

camerax is a skill for Claude Code, Codex from frogobox/frogo-sdk. It costs 47 tokens per session (1,400 once invoked), scanned A, a copy of camerax, Apache-2.0.

Technical guidance for building Android camera features with CameraX, a modern Android camera library. It covers recording lifecycles, low-level camera settings, and connections to ML Kit or Media3 effects.

In plain words
What is it for?
Use it when implementing photo or video capture, enabling recording audio, configuring Camera2 options, or combining CameraX with ML Kit and Media3.
Why use it?
It prevents common implementation mistakes, such as losing settings when an immutable configuration object is not reassigned. It also explains patterns for moving older camera code to CameraX.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is frogobox/frogo-sdk's own configuration. It tells Claude Code and Codex how to work on frogo-sdk 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 frogo-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to frogobox/frogo-sdk. 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/frogobox/frogo-sdk/master/.agents/skills/camerax/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/frogobox/frogo-sdk

Made for: Claude Code, Codex.

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 camerax

README.md
[![agentmods](https://agentmods.dev/badge/skills/frogobox/frogo-sdk/camerax.svg)](https://agentmods.dev/skills/frogobox/frogo-sdk/camerax)
Your own site
<a href="https://agentmods.dev/skills/frogobox/frogo-sdk/camerax"><img src="https://agentmods.dev/badge/skills/frogobox/frogo-sdk/camerax.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00047 $0.01400
Opus 5 $0.00023 $0.00700
Sonnet 5 $0.00009 $0.00280
Haiku 4.5 $0.00005 $0.00140

Measured 6d ago against content hash 750852f6d780, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

camerax 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 6d 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.

Origin

This is a copy

94% identical to camerax — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/camerax/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill provides procedural guidance and standard patterns for building camera applications on Android, with a focus on CameraX, including its Camera2Interop utilities, and Media3 integrations.

Core workflows

Handling immutable API patterns

Various Android camera and media APIs, especially CameraX VideoCapture, use a fluent, immutable builder-like pattern where methods return a new instance. Failing to reassign these results in settings, such as audio, being ignored.

Pattern: Reassignment is required

// WRONG
run {
  val pending = recorder.prepareRecording(context, opts)
  pending.withAudioEnabled() // This returns a new instance which is ignored
  val active = pending.start(exec, listener)
}

// CORRECT
run {
  val pending = recorder.prepareRecording(context, opts)
      .withAudioEnabled() // Chaining works
  val active = pending.start(exec, listener)
}

// ALSO CORRECT
run {
  var pending = recorder.prepareRecording(context, opts)
  pending = pending.withAudioEnabled() // Reassignment
  val active = pending.start(exec, listener)
}

See immutability for a list of affected classes.

Migrating to CameraX

When migrating legacy camera codebases to the CameraX Jetpack library:

  • Camera1 to CameraX : For migrating legacy android.hardware.Camera implementations, surface handling, and manual lifecycles, see the Camera1 migration guide.
  • Camera2 to CameraX : For migrating more recent but verbose android.hardware.camera2 implementations, session state callbacks, and interop patterns, see the Camera2 migration guide.

Comprehensive feature blueprinting

For multi-step features that involve multiple files and hardware-level wiring, follow the Structural Blueprinting approach to avoid system timeouts. Such complex features include:

  • Manual controls : Break down into the ViewModel state, the controller layer, and the Camera2Interop wiring in the session.
  • RAW capture: Separate JPEG and RAW output configurations into discrete build steps.
  • Custom effects : Prefer Media3Effect or SurfaceProcessor over manual OpenGL pipelines unless absolute performance is required.
  • Low-light : See low-light for Night Mode and LLB guidance.
  • Foldables : See foldables for handling dynamic postures and hinge states.
  • XR, AR, and VR : See xr for spatial tracking, passthrough synchronization, and latency guardrails.
  • Thermals and power : See thermals for managing StreamUseCase optimizations and PowerManager thermal states.
  • Testing and mocking : See testing for using FakeCameraConfig, handling asynchronous lifecycles, and validating analysis pipelines.
  • ML Kit spatial analysis : See mlkit-spatial for coordinate mapping, rotation logic, and mirrored lens handling.
  • Wear OS camera remote : See wear-os for circular UI constraints, Data Layer API syncing, and remote trigger logic.

Read the full file on GitHub · 133 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. 6d ago First seen · 133 lines · 47 tokens per session scan A 750852f6d780

Subscribe to this mod's changes

camerax is a skill published in the GitHub repository frogobox/frogo-sdk (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to camerax, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

sceneview

Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…

sceneview/sceneview · 156 tokens

sceneview-ios

Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…

sceneview/sceneview · 148 tokens

compose-animations

Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.

chrisbanes/skills · 64 tokens

compose-focus-navigation

Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.

chrisbanes/skills · 41 tokens

kotlin-tooling-agp9-migration

Migrates Kotlin Multiplatform (KMP) projects to Android Gradle Plugin 9.0+. Handles plugin replacement (com.android.kotlin.multiplatform.library), module splitting, DSL migration, and the new default project structure. Use when upgrading AGP, when build fails due to KMP+AGP incompatibility, or when the user mentions…

Kotlin/kotlin-agent-skills · 105 tokens

ksafe

Use for persisting sensitive data from Kotlin/Compose Multiplatform shared code into one Keystore/Keychain-backed store across Android, iOS, macOS, JVM Desktop, and web: tokens, passwords, PINs, a database passphrase, encrypted preferences, Compose state. KSafe (:ksafe, :ksafe-compose, :ksafe-biometrics) is the…

ioannisa/KSafe · 251 tokens