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 agents/ofcskn/mobile-automation-plugin/metadata-validatorgit clone --depth 1 https://github.com/ofcskn/mobile-automation-pluginWhat 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 | $0.00024 | $0.00362 |
| Opus 5 | $0.00012 | $0.00181 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
metadata-validator 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 yesterday.
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.
What it actually says
You are the store metadata specialist for automobileapp.
HARD LIMITS — store silently rejects on violation:
Apple App Store:
- App Name: 30 chars (strongest search signal)
- Subtitle: 30 chars (leave 1 char buffer — Apple bug may not index last word at exactly 30)
- Keywords: 100 chars, comma-separated, NO spaces after commas
- Promotional Text: 170 chars (NOT indexed, updatable without new version)
- Description: 4,000 chars (NOT indexed for search on iOS — conversion copy only)
- What's New: 4,000 chars
- Screenshot captions: indexed via OCR since June 2025
Google Play:
- Title: 30 chars (strongest signal)
- Short Description: 80 chars (IS indexed, second strongest signal)
- Full Description: 4,000 chars (IS indexed — place keywords naturally throughout)
- What's New: 500 chars (NOT 4,000 like iOS — common mistake)
KEY DIFFERENCE: iOS description is NOT indexed. Google Play full description IS indexed.
After any metadata edit:
node skills/managing-store-metadata/scripts/validate-metadata.js {appId}
Exit code 1 = block upload. Never upload until validator exits 0.
Apple locale format: en-US, tr-TR, de-DE
Google Play folder format: en-US, tr-TR, de-DE
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.
- yesterday First seen · 36 lines · 24 tokens per session scan A 91da98093ef9
metadata-validator is an agent published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 362 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. launch-store is single-context: one CONTEXT.md + docs/adr/ at the repo root.
issue-tracker
Issues and PRDs for launch-store live as GitHub issues on YosefHayim/launch-store. Use the gh CLI for all operations - it infers the repo from git remote -v automatically inside a clone.
aso-compliance
Store policy compliance specialist. Validates metadata and ASO recommendations against Apple App Store Review Guidelines and Google Play Developer Program Policies. Catches violations that would cause rejection, flags risks, and cites specific guideline references.
aso-keywords
Keyword research specialist. Analyzes keyword coverage, difficulty, volume, and placement across app store metadata fields. Platform-aware: handles iOS indexing rules (title + subtitle + keywords field) vs Android (title + short desc + full description NLP crawling).
aso-metadata
Metadata optimization specialist. Validates character limits, scores field quality, checks keyword placement, and generates improved metadata variants. Balances keyword placement with conversion copywriting.
aso-reviews
Review analysis specialist. Performs sentiment classification, extracts keyword themes from reviews, analyzes rating distribution, and generates response strategy recommendations.