Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sunnat629/android-media-pack/claude-mdgit clone --depth 1 https://github.com/sunnat629/android-media-packWrote 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.
[](https://agentmods.dev/instructions/sunnat629/android-media-pack/claude-md)<a href="https://agentmods.dev/instructions/sunnat629/android-media-pack/claude-md"><img src="https://agentmods.dev/badge/instructions/sunnat629/android-media-pack/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01293 | $0.01293 |
| Opus 5 | $0.00647 | $0.00647 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
android-media-pack CLAUDE.md 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 4d 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.
- `scripts/install-media-skills.sh` — one-line curl installer with the same flattening logic. How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
android-media-pack — a pack of 31 AndroidX Media3 skills (Markdown SKILL.md files) for AI coding agents, plus an installer CLI and a Compose demo app. The product is the Markdown itself: skills are documentation artifacts pinned to a specific Media3 version (see MEDIA3_VERSION, currently 1.10.1), not compiled code.
.skills/media/<area>/<skill-name>/SKILL.md— source of truth for all skills, organized by area (playback/,streaming/,ui/,migration/,delivery/,protection/,ads-analytics/,background/,processing/,inspector/,testing/, plus the top-levelstreaming-media-architecture).bin/android-media-skill— bash CLI (install/update/list/doctor) that downloads the repo tarball and flattens.skills/media/**into a target project's.agents/skills/<skill-name>/(override destination withMEDIA_SKILLS_DEST).scripts/install-media-skills.sh— one-line curl installer with the same flattening logic.sampleApp/— standalone Gradle project (single:appmodule, oneMainActivity.kt) demonstrating Media3 Compose playback with HLS/DASH streams.llms.txtandREADME.md— discovery surfaces; the skill tables in both must stay in sync with.skills/media/..agent/skills/— third-party skills installed into this repo for the local agent; not part of the shipped pack. Do not edit or ship these.
Commands
# Validate skill body sizes (CI-enforced hard ceiling 20,000 chars; soft 700–6,000)
./scripts/check-skill-size.sh
# Markdown lint (config in .markdownlint-cli2.jsonc)
npx markdownlint-cli2 "**/*.md"
# Shell script lint
shellcheck bin/android-media-skill scripts/*.sh run-sample-app.sh
# Build, install, and launch the sample app on a connected device/emulator
./run-sample-app.sh --serial <device-serial>
./run-sample-app.sh --clean --no-launch # build+install only
# Sample app Gradle directly
cd sampleApp && ./gradlew assembleDebug
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.
- 4d ago First seen · 73 lines · 1,293 tokens per session scan A af9a7334fb56
android-media-pack CLAUDE.md is an instructions file published in the GitHub repository sunnat629/android-media-pack (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,293 tokens to every session, about $0.0065 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
AndroidAutoX AGENTS.md
AGENTS.md instructions for Xiddoc/AndroidAutoX, covering agents.md, project overview, tech stack, repository layout and autox virtual-display subsystem.
sceneview copilot-instructions.md
Copilot instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
SeekerClaw CLAUDE.md
Claude Code instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.
sceneview CLAUDE.md
Claude Code instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
androidbible CLAUDE.md
Claude Code instructions for yukuku/androidbible, covering claude.md, project overview, branches, build commands and debug apk (open-source build, works out of the box).
debroid AGENTS.md
Instructions for PatilShreyas/debroid, covering ai agent contributor guide 🤖, 🎯 intention & motivation, 🏗️ architecture & layers, 1. the core layer (jdi & adb orchestration) and 2. the cli layer (daemon & client).