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 skills add krillinai/growth-skills --skill aso-auditgit clone --depth 1 https://github.com/krillinai/growth-skillsWrote 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/krillinai/growth-skills/aso-audit)<a href="https://agentmods.dev/skills/krillinai/growth-skills/aso-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/aso-audit/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/krillinai/growth-skills/aso-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/aso-audit.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 | $0.00041 | $0.02119 |
| Opus 5.5 | $0.00016 | $0.00848 |
| Sonnet 5.5 | $0.00008 | $0.00424 |
| Haiku 4.5 | $0.00004 | $0.00212 |
Grade A, and why
aso-audit 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASO Audit
Reuse Growth Context
At the start, read .agents/growth-context.md when it exists. Reuse only product, customer, market, outcome, constraint, evidence, and routing fields whose scope, definition, source, and date remain compatible; state what is reused and surface conflicts or staleness before asking for decision-changing gaps. The file grants no system access or execution authority, and this Skill must not silently rewrite the primary diagnosis.
Audit store listings, not product implementation, release submission, or app code. Route those requests to engineering or release operations; state that a later audit needs a dated listing capture, store identifier or canonical URL, country, locale, and requested surfaces.
Compose The Smallest Scope
Choose one primary mode from the decision requested, then add only necessary modifiers:
listingprimary: assess a bounded Apple App Store or Google Play product page when the decision concerns the listing overall.focusedprimary: decide a question about only named listing surfaces, such as the first three screenshots; do not expand to metadata, reviews, or the app.performanceprimary: investigate a reported store-performance signal. Treat it as a signal until dated, segmented measurement verifies it; keep performance primary when adding comparison or surface bounds.competitivemodifier: compare supplied listings using the same store, fixed card, country, locale, and date. Label the work competitive, but retain the decision's primary mode; a performance comparison isperformance + competitive, not competitive primary. Listing-page evidence cannot establish query rank.focusedbound: constrain a performance or competitive assessment to the named surfaces without changing its primary decision. For example, a performance diagnosis comparing only two screenshots isperformance + competitive, focused to those screenshots.out-of-scope: own implementation-only requests for onboarding, deep links, release submission, or unrelated engineering. Give a concise ownership handoff instead of an audit. For mixed requests, audit only the ASO portion and hand off implementation work.
What ships with it
7 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 · 71 lines · 41 tokens per session scan A 068d40c92ff8
aso-audit is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 2,119 once invoked, about $0.0002 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.
aso-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aso-auditkrillinai/growth-skills | Skill | 43 | 2mo ago | MIT | A | 41 | Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | 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 | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |