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 skills/aospbooks/aosp-internal-book/aosp-version-diffnpx skills add aospbooks/aosp-internal-book --skill aosp-version-diffgit 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-version-diff)<a href="https://agentmods.dev/skills/aospbooks/aosp-internal-book/aosp-version-diff"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/aosp-version-diff.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 | $0.00173 | $0.01965 |
| Opus 5 | $0.00086 | $0.00983 |
| Sonnet 5 | $0.00035 | $0.00393 |
| Haiku 4.5 | $0.00017 | $0.00197 |
Grade A, and why
aosp-version-diff 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 5d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AOSP version diff → changes report
This skill captures a proven, two-phase workflow for answering "what changed
between two AOSP releases, and which of it matters?" It leans on an existing
tool (tools/manifest_snapshot.py) for the mechanical diff, and on a small
agent team for the judgement-heavy parts: deciding what's significant, verifying
claims against real source, and finding modules a first draft missed.
The guiding principle throughout is accuracy over coverage: a smaller report whose every claim is checked against the actual Android source beats a broad one that paraphrases commit subjects. Every architectural claim cites a real path you opened.
When to use which phase
- Phase 1 — Compare (
references/tooling.md): you have (or can produce) the two releases and want the raw per-repository changeset, then a curated report. - Phase 2 — Gap-append (
references/gap-analysis.md): a report already exists and you want to find and add the important modules it missed — both newly-added projects and new code modules introduced inside moved repos.
Phase 2 is the "backend" that keeps a report honest: a single drafting pass almost always misses modules, because the changeset is huge (hundreds of moved repos, dozens of added projects) and a drafter naturally anchors on the headline features. Phase 2 systematically diffs "what the changeset added" against "what the report mentions" and closes the difference.
Prerequisites
- The repo's
tools/manifest_snapshot.py(subcommandssnap,history,compare,compare-history). Readreferences/tooling.mdfor exact commands, flags, and the gotchas that bite (ref-name filenames, LFS, non-UTF-8 commit subjects, the snapshot-vs-history coherence trap). - A local AOSP checkout (e.g.
$ANDROID_BUILD_TOP) synced to whichever release you're analyzing. The tools are read-only against it; never write into the AOSP tree. - For the source-verification and gap phases: the ability to spawn subagents (cap at 10 concurrent). Without subagents, the same steps run inline, slower.
What ships with it
3 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.
- 5d ago First seen · 145 lines · 173 tokens per session scan A e51f3d51b05f
aosp-version-diff is a skill published in the GitHub repository aospbooks/aosp-internal-book (130 stars, last pushed 6d ago), licensed Apache-2.0. It adds 173 tokens to every session and 1,965 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
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"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.