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 mgcrea/mcp-appstore-connect --skill appstore-release-prepgit clone --depth 1 https://github.com/mgcrea/mcp-appstore-connectWrote 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/mgcrea/mcp-appstore-connect/appstore-release-prep)<a href="https://agentmods.dev/skills/mgcrea/mcp-appstore-connect/appstore-release-prep"><img src="https://agentmods.dev/badge/skills/mgcrea/mcp-appstore-connect/appstore-release-prep/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/mgcrea/mcp-appstore-connect/appstore-release-prep"><img src="https://agentmods.dev/badge/skills/mgcrea/mcp-appstore-connect/appstore-release-prep.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00277 | $0.06230 |
| Opus 5 | $0.00138 | $0.03115 |
| Sonnet 5 | $0.00055 | $0.01246 |
| Haiku 4.5 | $0.00028 | $0.00623 |
Grade A, and why
appstore-release-prep 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 5d 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 — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store release prep
Turn "what changed since the last release" into two documents that stay in sync: a CHANGELOG entry (for developers, complete) and the App Store Connect fields (for customers, ruthlessly short and hard-limited).
The failure modes here are boring and specific, and they are why this skill exists: people guess the version, miss features that shipped without ever being written down, and blow a 4,000-character limit they never measured. Run the audit first — it answers all three deterministically — then spend your judgment on the copy.
1. Audit before writing anything
python3 ${CLAUDE_SKILL_DIR}/scripts/audit_release.py --repo <repo> # add --json for machine output
It reports: the shipping version and the last documented one, the release boundary commit and everything since it, commits that shipped in the last release but were never announced, every store field measured against Apple's limit, em dashes in prose, and screenshot-config drift. It exits non-zero if a field is over or missing, so it can gate a release.
The source is auto-detected: a metadata tree wins, else APPSTORE.md, STORES.md
and friends. The tree is found from its .listing.json wherever that sits, falling
back to fastlane/metadata/ or Listing/; pass --metadata-root <path> for a tree
that was moved and has no sidecar, or when the repo holds more than one. Pass --fields-file <path>
to force a document, or --locale to audit a locale other than the primary one.
Check the source it reports — the header says which file or directory the numbers
came from.
If it reports "file does not exist" for a project that plainly has store copy, you
pointed it at the wrong place; do not take that as license to write every field from
scratch, or you will replace live copy with a rewrite nobody asked for.
Pull the live listing first when an App Store Connect MCP is available
The script never makes network calls: it gates releases, so it stays offline and deterministic. That leaves one failure it structurally cannot see — someone edits the listing in App Store Connect's web UI, nobody backports it, and the local copy quietly falls behind what customers are reading. The local files are the draft; the live listing is what shipped. Neither is automatically right.
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.
- 5d ago Changed · +55 lines 5b8840413966
- 6d ago Changed · +13 lines 1984abd5b44b
- 10d ago First seen · 395 lines · 277 tokens per session scan A d0ca386259aa
appstore-release-prep is a skill published in the GitHub repository mgcrea/mcp-appstore-connect (1 stars, last pushed 3d ago), licensed MIT. It adds 277 tokens to every session and 6,230 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…