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-performance-intelgit 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-performance-intel)<a href="https://agentmods.dev/skills/mgcrea/mcp-appstore-connect/appstore-performance-intel"><img src="https://agentmods.dev/badge/skills/mgcrea/mcp-appstore-connect/appstore-performance-intel/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-performance-intel"><img src="https://agentmods.dev/badge/skills/mgcrea/mcp-appstore-connect/appstore-performance-intel.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 | $0.00264 | $0.06793 |
| Opus 5 | $0.00132 | $0.03397 |
| Sonnet 5 | $0.00053 | $0.01359 |
| Haiku 4.5 | $0.00026 | $0.00679 |
Grade A, and why
appstore-performance-intel 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 2d 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store performance intel
This answers one question with real data: what are the numbers doing, and why? It reads App Store Connect, does the arithmetic in a script rather than by eye, and maintains one living markdown report you can diff against last month's.
Every run has two deliverables, and neither substitutes for the other: the markdown file, and a summary of it in the conversation. A file path alone makes the user open a document to learn whether anything is wrong; a chat-only answer leaves nothing to diff next month. Step 6 specifies the summary — it is not a sign-off line, it is the report's findings rendered for someone who will not open the file.
The failure modes here are specific and they are why the skill exists. People quote a truncated report as a total. They sum a per-unit money column and understate revenue by a hundred times. They add euros to yen. They call a release-day flood of free updates a sales surge. They report a conversion rate without saying which two reports it came from. Every one of those produces a confident number that is simply wrong, and none of them is visible in the output. Run the numbers through the script, label every figure with its source, and spend your judgment on what the movement means.
A second failure mode is subtler: answering from the shape of the question. If the user says "downloads died", the answer is not sympathy and a plausible cause. It is a measurement that either confirms it or doesn't, and quite often doesn't.
What this skill does not do
It does not propose features, read competitors, or judge positioning. When the
run surfaces something that needs a product decision, name it and hand off to
app-market-intel, which has the ledger of what has already been proposed and
rejected. Two skills inventing roadmap independently is how contradictory advice
gets written.
Recommendations here are allowed, expected, and bounded: every one must trace to a number measured in this run. "Search impressions fell 28% while web referrals rose — the keyword set is worth re-checking" is in scope. "Add a widget" is not, no matter how good the idea.
What ships with it
11 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.
- evals/evals.json 12 KB
- evals/fixtures/august-sales-iap.json 908 B
- evals/fixtures/july-sales-iap.json 908 B
- evals/fixtures/june-engagement-truncated.json 52 KB
- evals/fixtures/june-engagement.json 94 KB
- evals/fixtures/june-sales.json 1.3 KB
- evals/fixtures/may-engagement.json 97 KB
- evals/fixtures/may-sales.json 1.3 KB
- references/asc-metrics.md 21 KB
- scripts/report_stats.py 60 KB runs code
- scripts/test_report_stats.py 7.6 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.
- 2d ago Changed · +43 lines 0e6511857678
- 9d ago First seen · 498 lines · 264 tokens per session scan A 051a577f594d
appstore-performance-intel is a skill published in the GitHub repository mgcrea/mcp-appstore-connect (1 stars, last pushed 2d ago), licensed MIT. It adds 264 tokens to every session and 6,793 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
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"…
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.