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.
/plugin marketplace add aospbooks/aosp-internal-booknpx agentmods add plugins/aospbooks/aosp-internal-book/claudegit clone --depth 1 https://github.com/aospbooks/aosp-internal-bookWrote 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/plugins/aospbooks/aosp-internal-book/claude)<a href="https://agentmods.dev/plugins/aospbooks/aosp-internal-book/claude"><img src="https://agentmods.dev/badge/plugins/aospbooks/aosp-internal-book/claude.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
claude 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 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.
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.
What it actually says
{
"name": "aosp-internals",
"version": "2026.06.24",
"description": "AOSP Internals book content (67 chapters + 4 appendices) packaged as 16 Part-skills.",
"homepage": "https://aospbooks.github.io/aosp-internal-book/",
"repository": "https://github.com/aospbooks/aosp-internal-book"
}
What it installs
The manifest is a name and a version. 16 skills travel with it, and installing the plugin installs all of them — 2,048 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill aosp-framework-services A 212 tokens
- Skill aosp-connectivity A 173 tokens
- Skill aosp-device-support A 139 tokens
- Skill aosp-framework-core A 156 tokens
- Skill aosp-infrastructure A 139 tokens
- Skill aosp-native-foundation A 152 tokens
- Skill aosp-native-services-and-media A 149 tokens
- Skill aosp-security A 134 tokens
- Skill aosp-ai-and-devices A 107 tokens
- Skill aosp-appendices A 132 tokens
- Skill aosp-getting-started A 100 tokens
- Skill aosp-kernel-and-boot A 114 tokens
- Skill aosp-ui-framework A 108 tokens
- Skill aosp-runtime A 80 tokens
- Skill aosp-system-apps A 85 tokens
- Skill aosp-practical A 68 tokens
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 · 8 lines scan A d93257a9bde7
claude is a plugin published in the GitHub repository aospbooks/aosp-internal-book (130 stars, last pushed 5d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
swift-study-skills
Swift/iOS learning skills - Socratic tutoring, adaptive quizzes, and note-taking.
robotactions
Teach your coding agent to test real mobile apps and websites on the Robot Actions device cloud: connect, drive devices reliably, and record/replay regression flows.
ios
iOS plugin.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
toefl-prep
TOEFL 집중 학습 플러그인 — 4주 로드맵(7/158/12) + 로컬 LLM(Ollama) 기반 Reading/Listening/Speaking/Writing 4개 영역 오프라인 채점 + whisper.cpp 스피킹 평가. 목표 점수 90 (Georgia Tech OMSCS 2027 Spring). 사용자가 '토플', '스피킹 연습', '라이팅 채점', '리딩 문제', '모의고사', '어떤 주차' 등을 요청하면 이 스킬을 사용한다.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.