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/raydeveloperf/app-store-connect-release-kit/asc-metadatanpx skills add raydeveloperF/App-Store-Connect-release-kit --skill asc-metadatagit clone --depth 1 https://github.com/raydeveloperF/App-Store-Connect-release-kitWrote 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/raydeveloperf/app-store-connect-release-kit/asc-metadata)<a href="https://agentmods.dev/skills/raydeveloperf/app-store-connect-release-kit/asc-metadata"><img src="https://agentmods.dev/badge/skills/raydeveloperf/app-store-connect-release-kit/asc-metadata.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 | $0.00070 | $0.01105 |
| Opus 5 | $0.00035 | $0.00553 |
| Sonnet 5 | $0.00014 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
asc-metadata 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 3d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASC Metadata
Use this skill to write localized App Store Connect copy for these fields only:
SubtitlePromotional TextApp Description
Do not generate keywords, screenshot headlines, release notes, privacy copy, or pricing copy unless the user separately asks for them.
Required Inputs
The only input that cannot be inferred: target locales (e.g. en-US, zh-Hans).
If target locales are missing and were not provided by the caller, ask once and stop.
Writing style defaults to 平静内敛 when not specified. Do not ask for it.
Project Context First
Before writing specific metadata, gather enough context to understand the app. If a local project or workspace is available, inspect relevant files read-only unless the user asks for edits:
- README, product docs, planning docs, marketing copy, or existing App Store metadata.
- App entry points, main screens, feature modules, localization files, and screenshots if available.
- Existing title, subtitle, keywords, screenshots, and product positioning, if present.
Build a short working brief before drafting:
- App name, platform, category, and target audience.
- Core user job and the 3-5 strongest implemented features.
- Main emotional promise or practical value.
- Constraints from existing brand voice, screenshots, title, or keywords.
- Locale-specific wording risks, cultural fit, and product differences.
If the available project context is too thin, ask focused follow-up questions or label the output as a context-limited draft. Do not invent unsupported features, claims, awards, integrations, subscription terms, privacy guarantees, or medical/legal/financial promises.
Field Rules
Use current App Store Connect limits unless the user provides different constraints:
- Subtitle: at most 30 characters.
- Promotional Text: at most 170 characters.
- App Description: at most 4000 characters, plain text, line breaks allowed, no HTML.
For every locale:
- Write in the target language, not merely translated English.
- Preserve the requested writing style.
- Keep claims grounded in the inspected project.
- Avoid duplicate wording between subtitle and the first line of the description when possible.
- Prefer concrete value over generic praise.
- Avoid filler like "best", "ultimate", "revolutionary", and unsupported superlatives.
- Do not mention Apple, iPhone, iOS, App Store, or platform terms as selling points unless directly relevant and allowed.
What ships with it
1 file 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.
- 3d ago First seen · 140 lines · 70 tokens per session scan A 813a9d2335c4
asc-metadata is a skill published in the GitHub repository raydeveloperF/App-Store-Connect-release-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,105 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
localization
When the user wants to localize their App Store listing for international markets. Also use when the user mentions "localization", "translate my app", "international markets", "expand to new countries", "localize metadata", or "which countries should I target". For keyword research in specific markets, see…
appstore-ppp-pricing
Bulk-sets App Store in-app purchase and subscription prices across 175+ countries by purchasing power parity, using the appstore-ppp-prices CLI. Use whenever the user wants to localize, bulk-update, lower, raise or review regional App Store pricing — "set regional prices", "PPP pricing", "make my app cheaper in…
app-store-screenshots
End-to-end playbook for producing localized, caption-framed App Store screenshots (iPhone + iPad) from real simulator captures, then replacing them on App Store Connect. Use when asked to create, localize, redesign, or upload App Store screenshots for an iOS app. Covers capture automation via the accessibility tree…
querying-terminology-service
Call a user-supplied FHIR terminology server ($validate-code, $expand, $lookup, $translate) to validate and expand clinical codes without bundling restricted vocabulary (SNOMED CT, RxNorm, LOINC, ICD-10) into OpenMed. Covers a thin local client, ValueSet $expand with filters/ECL, CodeSystem $lookup, ConceptMap…
aso-router
Single entry point that routes any ASO, App Store, Google Play, app marketing, paid UA, monetization, retention, reviews, ratings, market-intel, or app-analytics question to the correct specialist skill in this library. Use FIRST whenever the user mentions an app, App Store, Play Store, keywords, ranking, downloads…
app-rejection-recovery
When the user's app or update was rejected by Apple App Review or Google Play Review and they need to diagnose why, fix it, and resubmit fast. Use when the user mentions "app rejected", "App Review rejection", "guideline violation", "Apple rejected my app", "Google Play rejected", "Play policy violation", "Resolution…