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-version-diff/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-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/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-version-diff"><img src="https://agentmods.dev/badge/skills/aospbooks/aosp-internal-book/aosp-version-diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00173 | $0.01965 |
| Opus 5.5 | $0.00069 | $0.00786 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (144 stars, last pushed 23d ago), licensed Apache-2.0. It adds 173 tokens to every session and 1,965 once invoked, about $0.0007 per session on Opus 5.5. 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.
aosp-version-diff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aosp-version-diffaospbooks/aosp-internal-book | Skill | 144 | 23d ago | Apache-2.0 | A | 173 | Claude Code |
| orca-emulator-androidstablyai/orca | Skill | 118k | today | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | today | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | today | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | today | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 894 | today | MIT | A | 50 | Claude Code, Codex |