Borrowing it
Nothing to install: this file belongs to aospbooks/aosp-internal-book. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aospbooks/aosp-internal-book/main/.claude/skills/aosp-book-polish/SKILL.mdgit 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/skills/aospbooks/aosp-internal-book/aosp-book-polish)<a href="https://agentmods.dev/skills/aospbooks/aosp-internal-book/aosp-book-polish"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/aosp-book-polish/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.
<a href="https://agentmods.dev/skills/aospbooks/aosp-internal-book/aosp-book-polish"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/aosp-book-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 55 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.1 | $0.00234 | $0.03375 |
| Opus 5 | $0.00117 | $0.01688 |
| Sonnet 5 | $0.00047 | $0.00675 |
| Haiku 4.5 | $0.00023 | $0.00337 |
Grade A, and why
aosp-book-polish 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AOSP Book Polish
Bring the AOSP Internals book into sync with a newer AOSP source tree: deep-rewrite existing chapters for accuracy, append new-feature content where a subsystem changed, and — always — find newly-added modules/projects and make sure the book covers them (fold into an existing chapter first; add a new chapter/Part only when a threshold is met).
This is a large, multi-/goal-run, agent-team job. It is built to be
resumable and convergent: each chapter is rewritten then reviewed until
two consecutive clean rounds, and durable state lets a fresh run pick up where
the last stopped.
When to use
- The local AOSP checkout (its path supplied to you as a parameter, usually
androidNN-release) was synced to a newer version and the book should reflect it. - The user asks to update/polish the book, deep-rewrite chapters, or specifically to cover newly-added modules (the mandatory Phase C below).
- Pairs with the
aosp-version-diffskill: that skill produces the 16→17 style changeset (manifest-snapshots/_compare/<A>-to-<B>/) this skill consumes.
If there is no changeset yet, run aosp-version-diff first (or
tools/manifest_snapshot.py compare) — the changeset drives prioritization and
the new-module gap analysis.
Inputs
- AOSP source — the AOSP checkout root, supplied as a parameter (e.g. in the task prompt); READ-ONLY. Never write into it, and never hardcode its path.
- Changeset —
manifest-snapshots/_compare/<old>-to-<new>/:report.md(navigator + per-reponew/droppedcounts),changes.txt(per-repo NEW commits — large, grep per repo, never read whole),added-removed.txt(added / removed projects — the seed for Phase C). - Book conventions —
book/CLAUDE.md(the writing rules; these are non-negotiable),.claude/skills/book-writer/SKILL.md(chapter structure + Mermaid syntax),agents/_content/manifest.toml(Part → chapter mapping), existing chapters as style exemplars. - The Android-NN appendix (e.g.
D-appendix-android-17-updates.md) — a curated map of the new version's changes; a per-chapter checklist of what to fold in, and the candidate universe for the Phase C gap analysis.
What ships with it
5 files 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.
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.
- 12d ago First seen · 232 lines · 234 tokens per session scan A f06a47bb9991
aosp-book-polish is a skill published in the GitHub repository aospbooks/aosp-internal-book (131 stars, last pushed 13d ago), licensed Apache-2.0. It adds 234 tokens to every session and 3,375 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.
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"…