agentmods.dev

lpm: Skill for Claude Code

.claude/skills/app-store-release/SKILL.md

app-store-release is a skill for Claude Code from gug007/lpm. It costs 117 tokens per session (783 once invoked), scanned A, original, MIT.

An iOS release workflow that publishes a new app build through App Store Connect, Apple's service for submitting and managing iPhone and iPad apps. It first prepares release notes for approval, then handles the build and store listing steps.

In plain words
What is it for?
Use it to prepare What's New text, upload an iOS build when needed, create or update the App Store version, attach the build, and update screenshots.
Why use it?
It separates user-visible release notes from the upload process and avoids publishing those notes before they are approved. It also checks whether the current build is the one ready to release.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is gug007/lpm's own configuration. It tells Claude Code how to work on lpm 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 lpm configures →

not rated 145repo +10 today A scan 117 tokens original MIT
View source ↗ gug007/lpm lpm.cx
Reuse

Borrowing it

Nothing to install: this file belongs to gug007/lpm. 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/gug007/lpm/main/.claude/skills/app-store-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gug007/lpm

Made for: Claude Code.

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 app-store-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/gug007/lpm/app-store-release/github.svg)](https://agentmods.dev/skills/gug007/lpm/app-store-release)
Your own site
<a href="https://agentmods.dev/skills/gug007/lpm/app-store-release"><img src="https://agentmods.dev/badge/skills/gug007/lpm/app-store-release/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 app-store-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/gug007/lpm/app-store-release"><img src="https://agentmods.dev/badge/skills/gug007/lpm/app-store-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 783 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00117 $0.00783
Opus 5.5 $0.00047 $0.00313
Sonnet 5.5 $0.00023 $0.00157
Haiku 4.5 $0.00012 $0.00078

Measured 5d ago against content hash 0d1ce10b09fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

app-store-release scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Live version: `curl -s 'https://itunes.apple.com/lookup?bundleId=cx.lpm.mobile'` → `results[0].version`. The lookup can lag a few hours after a release; if App Store Connect later shows a newer live version, redraft.
.claude/skills/app-store-release/SKILL.md · 25 lines

What it actually says

  1. What's New first. Before opening Chrome or uploading anything, draft the release notes:

    • Live version: curl -s 'https://itunes.apple.com/lookup?bundleId=cx.lpm.mobile' → results[0].version. The lookup can lag a few hours after a release; if App Store Connect later shows a newer live version, redraft.
    • The commit that set it: git log --reverse --format=%h -S'MARKETING_VERSION: "<live>"' -- '*project.yml' | head -1 (the * matters: project.yml moved from mobile/ to mobile/ios/).
    • Changes since then: git log --oneline <commit>..HEAD -- mobile ':!mobile/android' ':!mobile/parity'.

    Write 3–6 short bullets of user-visible changes with no commit jargon and no mention of Tailscale. Show them to the user and wait for their OK or edits before going on.

Then use Claude in Chrome on the user's logged-in Chrome, starting at https://appstoreconnect.apple.com/apps → lpm Link.

  1. Build. Open TestFlight and find the newest build. If it isn't from the current mobile/ios code, or the user passed --upload, run mobile/ios/deploy.sh. It bumps MARKETING_VERSION in project.yml (tell the user to commit that change), archives the app and uploads it. Reload until the build is no longer Processing, which takes about 5–15 minutes.
  2. Version. On the Distribution tab, click + next to iOS App and enter the build's version. If a draft version already exists, use it instead.
  3. What's New. Paste the text the user approved in step 1. If new user-visible commits landed since the draft, show the extra bullets first.
  4. Screenshots. If the screens changed or the user passed --screenshots, run the app-store-screenshots skill and upload the images as its "After a run" step says. Otherwise keep the screenshots from the previous version.
  5. Build + review info. In the Build section, pick the build from step 2. If pairing or the main flows changed or the user passed --video, run app-review-video and update App Review Information → Notes with the new version, build and video link. Keep Release set to the user's earlier choice. Leave everything else as it was.
  6. Submit. Ask for the user's OK, then click Add for Review → Submit to App Review. Confirm the status reads "Waiting for Review". Report the version, build, What's New text and status.

Traps: ITSAppUsesNonExemptEncryption is false, so no export compliance question should come up. If one does, ask the user. Never press Release or change pricing or availability without the user's explicit request.

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. 5d ago First seen · 25 lines · 117 tokens per session scan A 0d1ce10b09fd

Subscribe to this mod's changes

app-store-release is a skill published in the GitHub repository gug007/lpm (145 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 783 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.

Claude CodeGit and workflowMobileReleasesagentic-codingai-agentscodexdeveloper-toolsterminal
Related

Other skills, from other repositories

release

Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.

Yeachan-Heo/oh-my-claudecode · 27 tokens

axiom-shipping

Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy manifests, age ratings, export compliance.

CharlesWiltgen/Axiom · 56 tokens

release-new-version

Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).

niki914/zafiro · 54 tokens

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

app-release

End-to-end pipeline for releasing an iOS / watchOS app to TestFlight and the App Store. Use when the user wants to publish, ship, or release an iOS/watchOS app, get a build onto TestFlight, archive and upload via xcodebuild, deploy a CloudKit schema to Production, set App Privacy or export compliance, mint a…

glebis/claude-skills · 166 tokens

testflight-release

Ship a new TestFlight build of the iOS companion (TermioMobile) — resolve the next build number against App Store Connect, archive, sign, export, upload, write the What to Test notes, and distribute. Invoke when the user says 'ship a testflight build', 'update testflight', 'upload to testflight', 'new beta build'…

termio-sh/termio · 102 tokens