app-store-connect-mcp: Skill for Claude Code

.claude/skills/heimdall-contrib/SKILL.md

heimdall-contrib is a skill for Claude Code from erayendes/app-store-connect-mcp. It costs 111 tokens per session (1,704 once invoked), scanned A, original, MIT.

A maintenance guide for the Heimdall repository, which is the source code for an App Store Connect MCP server. It explains which files are authoritative, how generated files are produced, and which checks must pass.

In plain words
What is it for?
Use it when changing tool descriptions or profiles, updating Apple’s API specification, adding macros, regenerating source files, or checking tests and types.
Why use it?
It prevents developers from editing generated output that will later be overwritten and helps keep specification changes visible in tests.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is erayendes/app-store-connect-mcp's own configuration. It tells Claude Code how to work on app-store-connect-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything app-store-connect-mcp configures →

Part of the heimdall plugin — 2 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to erayendes/app-store-connect-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/erayendes/app-store-connect-mcp/main/.claude/skills/heimdall-contrib/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/erayendes/app-store-connect-mcp

Made for: Claude Code.

Or install heimdall, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

agentmods badge for heimdall-contrib

README.md
[![agentmods](https://agentmods.dev/badge/skills/erayendes/app-store-connect-mcp/heimdall-contrib/github.svg)](https://agentmods.dev/skills/erayendes/app-store-connect-mcp/heimdall-contrib)
Your own site
<a href="https://agentmods.dev/skills/erayendes/app-store-connect-mcp/heimdall-contrib"><img src="https://agentmods.dev/badge/skills/erayendes/app-store-connect-mcp/heimdall-contrib/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.

agentmods 80×15 button for heimdall-contrib

Your own site · 80×15
<a href="https://agentmods.dev/skills/erayendes/app-store-connect-mcp/heimdall-contrib"><img src="https://agentmods.dev/badge/skills/erayendes/app-store-connect-mcp/heimdall-contrib.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.01704
Opus 5 $0.00056 $0.00852
Sonnet 5 $0.00022 $0.00341
Haiku 4.5 $0.00011 $0.00170

Measured 11d ago against content hash 4245536130e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

heimdall-contrib 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 11d 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.

.claude/skills/heimdall-contrib/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Two files are the source of truth and nothing else is: spec/openapi.json (Apple's, fetched) and spec/profiles.csv (hand-curated, the owner's spreadsheet). Everything in src/generated/ is output.

Never edit src/generated/

Change the generator instead — scripts/generate.ts for operations and descriptions, scripts/generate-profiles.ts for membership — then:

npm run generate

and commit the result. npm test and npm run typecheck must pass. A hand edit under src/generated/ survives exactly until the next spec bump, and disappears without a diff anyone will notice.

The one step that is easy to skip

When you improve an axis, lower its ceiling in tests/ax-audit.test.ts.

That file's own comment calls this "the whole maintenance burden", which is another way of saying it is the step that gets forgotten. The ceilings are ratchets: debt may shrink freely and may never grow, so a spec bump that adds forty endpoints carrying Apple's one-line summaries announces itself instead of landing quietly. Leaving a ceiling high after a real improvement does not fail anything — it silently converts the win into permanent slack, and the next regression hides inside it.

Read the current numbers with:

npm run ax:report

Curating a description is the highest-leverage change here

Descriptions are what a model reads when choosing among 982 tools, and roughly 700 are still Apple's own one-line summary. Add entries to CURATED in scripts/describe.ts. What earns the space is what comes back, what narrows it, and which neighbouring tool this one is not.

Two traps, both of which have actually happened and are recorded inline:

  • Search matches tokens of three or more characters as substrings. A clause written to say what a tool is not can hand it queries meant for something else — ping inside "stopping", out and release inside "outside normal App Store releases". Name a neighbour by describing it, not by writing its tool name: app_screenshots__create inside a description made that tool the top hit for "create certificate".
  • Longer is not safer. Apple's short summaries are dense with the words someone actually searches for. A more helpful sentence on app_store_versions.build.set diluted that and dropped the tool out of the top three for "select build for app store version"; it is deliberately uncurated now.

Read the full file on GitHub · 143 lines

Changes

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.

  1. 11d ago First seen · 143 lines · 111 tokens per session scan A 4245536130e4

Subscribe to this mod's changes

heimdall-contrib is a skill published in the GitHub repository erayendes/app-store-connect-mcp (48 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 1,704 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.

Related

Other skills, from other repositories

asc-ad-hoc-distribution

Prepare, publish, resume, and verify private iOS release-testing installs with asc distribute. Use when distributing an IPA to registered devices outside TestFlight, reconciling ad hoc profiles, publishing through caller-owned S3-compatible storage, or diagnosing a resumable private distribution run.

rorkai/app-store-connect-cli-skills · 62 tokens

merge-check

Xcode-specific pre-merge gate — archive build (catches strict-concurrency/MainActor errors debug builds miss), app-extension Info.plist check, SwiftLint — spawned in parallel. Trigger on Apple/Xcode merge intent specifically ("merge this iOS branch", "archive check before merge", "is this ready for TestFlight"); a…

markdavidgan/apple-dev-skills · 96 tokens

apple-app-delivery

Upload builds, distribute on TestFlight, manage metadata, submit for Beta/App Review, and release on the App Store using Apple's official CLIs and the App Store Connect API. Default stable delivery to APPSTORE so one build can be tested in TestFlight and later submitted to the App Store; choose TESTFLIGHTINTERNALONLY…

moritouch/apple-app-delivery · 125 tokens

apple-release-ops

The mechanics of shipping Apple apps. Use for ANY code signing error ("no signing certificate", "provisioning profile doesn't include...", "revoked certificate"), provisioning profiles, certificates, entitlements, capabilities, TestFlight (groups, expiry, feedback), App Store Connect, uploading builds, xcodebuild…

Dev869/swift-tothemax · 215 tokens

asc-workflow

Define, validate, and run repo-local multi-step automations with asc workflow and .asc/workflow.json. Use when migrating from lane tools, wiring CI pipelines, or orchestrating repeatable asc + shell release flows with hooks, conditionals, and sub-workflows.

JordanCoin/ios-skills-collection · 62 tokens

app-store-changelog

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

JordanCoin/ios-skills-collection · 62 tokens