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 liuyi0808/android-review --skill play-storegit clone --depth 1 https://github.com/liuyi0808/android-reviewWrote 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/liuyi0808/android-review/play-store)<a href="https://agentmods.dev/skills/liuyi0808/android-review/play-store"><img src="https://agentmods.dev/badge/skills/liuyi0808/android-review/play-store/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/liuyi0808/android-review/play-store"><img src="https://agentmods.dev/badge/skills/liuyi0808/android-review/play-store.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 339 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00125 | $0.07319 |
| Opus 5 | $0.00063 | $0.03660 |
| Sonnet 5 | $0.00025 | $0.01464 |
| Haiku 4.5 | $0.00013 | $0.00732 |
Grade A, and why
play-store 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 9d 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Play Compliance & Launch Checklist
Comprehensive pre-submission audit and compliance verification for Google Play Store publishing. Includes 2025-2026 policy updates with special sections for financial/loan apps.
Policy effective date: March 4, 2026 (unless otherwise stated per section).
Execution Contract (MUST read before starting)
This skill has 14 reference files. A full audit MUST load all 14. "Progressive disclosure" does NOT mean "skip files you think you know" — it means load each file before you make a claim against it, then cite the specific section.
The Six Rules
-
All 14 references MUST be loaded. If a reference does not apply to the target app (e.g., App has no store listing assets yet), the auditor MUST explicitly mark it "Not Applicable" with a one-line reason in the Coverage Report. Silent skipping is forbidden.
-
Parallel execution is the default. Spawn 5 Task subagents in a single message so they run concurrently. See "Parallel Execution Pattern" below for the exact grouping. The main agent merges findings and produces the final report.
-
Every finding MUST cite its reference. Output format is not optional — see "Output Format" below. A finding without both
Reference:andPolicy Source:is invalid and must be rejected. -
The Reference Coverage Report is mandatory. Before the audit report is complete, emit a Coverage table with 14 rows. No Coverage table → the report is incomplete.
-
No conclusions from memory. If you cannot cite the reference file section you relied on, you do not have the finding. "I remember Personal Loans policy says X" is not acceptable — you must have actually loaded
loan-harassment.mdin this session before claiming a Personal Loans violation. -
Judge outcome against policy. Never prescribe implementation as policy. Every finding must answer two structural questions, with both answers visible in the Output Format:
- Declaration gate: Does Google provide a declaration channel for this policy (Permissions Declaration, Data Safety, Financial Declaration)? If yes and the developer's declaration status is unknown to the auditor, severity is NEEDS_CONFIRMATION — never BLOCKER/WARNING. If no channel exists (e.g., DexClassLoader, hidden functionality, using SMS data for credit underwriting), the policy is absolute and direct judgment is allowed.
What ships with it
15 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.
- references/build-and-signing.md 5.3 KB
- references/code-audit.md 8.4 KB
- references/consent-flow.md 9.6 KB
- references/data-privacy.md 11 KB
- references/deceptive-behavior.md 8.3 KB
- references/deployment.md 4.5 KB
- references/device-abuse.md 8.3 KB
- references/financial-declaration.md 10 KB
- references/intellectual-property.md 5.2 KB
- references/loan-harassment.md 8.3 KB
- references/permissions.md 25 KB
- references/restricted-content.md 6.8 KB
- references/spyware-policy.md 18 KB
- references/store-listing.md 3.0 KB
- scripts/audit.sh 11 KB runs code
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.
- 9d ago First seen · 419 lines · 125 tokens per session scan A 3f43ab518912
play-store is a skill published in the GitHub repository liuyi0808/android-review (11 stars, last pushed 13d ago), licensed MIT. It adds 125 tokens to every session and 7,319 once invoked, about $0.0006 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
play-policy-insights
Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures across Permissions and…
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.
app-store-review
Evaluates code against Apple's App Store Review Guidelines. Use this skill when reviewing iOS, macOS, tvOS, watchOS, or visionOS app code (Swift, Objective-C, React Native, or Expo) to identify potential App Store rejection issues before submission. Triggers on tasks involving app review preparation, compliance…
account-deletion
Generates an Apple-compliant account deletion flow with multi-step confirmation UI, optional data export, configurable grace period, Keychain cleanup, and server-side deletion request. Use when user needs account deletion, right-to-delete, or Apple App Review compliance for account removal.
consent-flow
Generates GDPR/CCPA/DPDP privacy consent flows with granular category preferences, consent state persistence, audit logging, and ATT (App Tracking Transparency) integration. Use when user needs privacy consent UI, cookie/tracking consent, or compliance management.
appstore-review-checker
Audit iOS/macOS apps against App Store Review Guidelines before submission, with evidence-backed verdicts and fixes. Don't use for Google Play, general code review, or rejection appeals.