subwave: Skill for Claude Code

.claude/skills/subwave-app-ota-update/SKILL.md

subwave-app-ota-update is a skill for Claude Code from perminder-klair/subwave. It costs 283 tokens per session (2,544 once invoked), scanned A, original, MIT.

A release tool for sending JavaScript or TypeScript changes to installed SUB/WAVE mobile apps through EAS Update, without creating a new app build.

In plain words
What is it for?
Use it to check whether a change is suitable for an over-the-air update, publish it to the correct channel, and verify which installed builds will receive it.
Why use it?
It lets eligible interface, copy, styling, and logic changes reach matching installed builds without going through TestFlight or an app-store review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is perminder-klair/subwave's own configuration. It tells Claude Code how to work on subwave 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 subwave configures →

About the project

Subwave is an internet radio station where an AI DJ selects music and speaks between tracks for every listener at once. Listeners can request music in plain language, while operators manage the queue, schedule, DJ personas, and station activity. Its catalogue entries define skills and workflows for operating the station.

perminder-klair/subwave · 1,314 stars · on GitHub · getsubwave.com

Reuse

Borrowing it

Nothing to install: this file belongs to perminder-klair/subwave. 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/perminder-klair/subwave/develop/.claude/skills/subwave-app-ota-update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/perminder-klair/subwave

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 subwave-app-ota-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-app-ota-update/github.svg)](https://agentmods.dev/skills/perminder-klair/subwave/subwave-app-ota-update)
Your own site
<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-app-ota-update"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-app-ota-update/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 subwave-app-ota-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-app-ota-update"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-app-ota-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 283 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,544 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 60
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium MCP Rug Pull · line 60
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00283 $0.02544
Opus 5 $0.00142 $0.01272
Sonnet 5 $0.00057 $0.00509
Haiku 4.5 $0.00028 $0.00254

Measured 10d ago against content hash 4b1dee6dfecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

subwave-app-ota-update 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ota-delivery-check.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/subwave-app-ota-update/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SUB/WAVE app — OTA update (EAS Update)

Push a JS/TS-only change to the app binaries already on people's phones, without building or submitting anything. The app ships expo-updates; an eas update bundles the current JS + Metro assets and serves them to matching installs, who pick them up on next launch. Most changes (UI, hooks, copy, logic, styles) go out this way in ~1 minute instead of a 15-min build + store round-trip.

This skill covers the whole OTA loop: decide if the change is even OTA-eligible, publish it to the right channel, and confirm which installed builds will actually receive it (the question that always comes up — "will my TestFlight build get this?").

The authoritative reference with the full decision table and fingerprint debugging is app/docs/RELEASE.md. This skill is the hands-on OTA path; for a binary build read the release skills instead (see "When you actually need a build" below).

Fixed facts

Derive the repo root; don't hardcode paths. eas.json + app.json live in app/, and every eas command must run from there.

REPO=$(git -C "<this skill's base directory>" rev-parse --show-toplevel)
APP="$REPO/app"   # cd here before any eas command
Thing Value
EAS project @pinku1/subwave (Expo account pinku1)
Updates URL https://u.expo.dev/b834b64c-f694-4f45-b3fa-0f2c0a4df5ba (in app.json)
Channels preview (tester builds) and production (TestFlight / Play)
Runtime version fingerprint policy — an OTA only reaches builds whose native fingerprint matches (see below)
Apply behaviour checkAutomatically: ON_LOAD + fallbackToCacheTimeout: 0 — fetches in background, applies on the next cold start

The one decision: can this go OTA, or does it need a build?

An OTA can only carry JS, TS, and Metro-bundled assets. It cannot carry native code. EAS enforces this with the fingerprint runtime policy: it hashes the native inputs, and an update only installs on a binary whose hash matches — so you physically can't ship mismatched native code, but you also can't sneak a native change out via OTA.

Read the full file on GitHub · 198 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 198 lines · 283 tokens per session scan A 4b1dee6dfecd

Subscribe to this mod's changes

subwave-app-ota-update is a skill published in the GitHub repository perminder-klair/subwave (1,314 stars, last pushed today), licensed MIT. It adds 283 tokens to every session and 2,544 once invoked, about $0.0014 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 2026-08-30.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens

android-pentest

A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.

Netw0rkNoob/VulnClaw · 32 tokens