macos-app-scaffold-enhance

macos-app-scaffold-enhance is a skill for Claude Code from XueshiQiao/macos-app-scaffold. It costs 36 tokens per session (6,901 once invoked), scanned B, original, MIT.

A workflow for adding release and development features to an existing macOS app.

In plain words
What is it for?
Use it to add CI/CD, automatic updates, logging, SwiftLint, localization, Launch at Login, or other supported features.
Why use it?
It examines what the project already contains and adds only the selected missing pieces.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/generate_keys.

Part of the macos-app-scaffold plugin — 3 skills shipped together

Good fit Use it to add CI/CD, automatic updates, logging, SwiftLint, localization, Launch at Login, or other supported features.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/XueshiQiao/macos-app-scaffold
agentmods
npx agentmods add skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance

Made for: Claude Code.

Or install macos-app-scaffold, the plugin that ships this one along with the rest of its 3 skills.

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 macos-app-scaffold-enhance

README.md
[![agentmods](https://agentmods.dev/badge/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance/github.svg)](https://agentmods.dev/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance)
Your own site
<a href="https://agentmods.dev/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance"><img src="https://agentmods.dev/badge/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance/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 macos-app-scaffold-enhance

Your own site · 80×15
<a href="https://agentmods.dev/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance"><img src="https://agentmods.dev/badge/skills/xueshiqiao/macos-app-scaffold/macos-app-scaffold-enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,901 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. 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 $0.00036 $0.06901
Opus 5 $0.00018 $0.03451
Sonnet 5 $0.00007 $0.01380
Haiku 4.5 $0.00004 $0.00690

Measured 12d ago against content hash d0644e15969d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

macos-app-scaffold-enhance scanned grade B with 2 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 12d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Daemon: `sudo launchctl kickstart -k system/<HelperBundleID>`

Makes network callslowCapability

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

curl -sL -o "$RUNNER_TEMP/sparkle.tar.xz" \
skills/macos-app-scaffold-enhance/SKILL.md · 599 lines

How it starts

The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enhance Existing macOS App

Add production-ready features to an existing macOS project. This skill analyzes the current project, shows what's already in place, and surgically adds only the new pieces.

Companion to /new-macos-app (which scaffolds from scratch).

Arguments

  • $ARGUMENTS = Optional feature name to add directly (e.g., ci-cd, auto-update, logging)

If no argument given, run the full analysis and let the user pick.


Step 1: Analyze Existing Project

Before asking anything, scan the current directory for:

Check for:
├── project.yml              → XcodeGen?
├── *.xcodeproj/             → Xcode project exists?
├── Package.swift            → SPM package?
├── .github/workflows/*.yml  → CI/CD?
├── .swiftlint.yml           → SwiftLint?
├── .gitignore               → Git initialized?
├── AGENTS.md / CLAUDE.md    → Agent config?
├── LICENSE                  → License file?
├── README.md                → README?
├── Casks/*.rb               → Homebrew Cask?
├── **/Sources/**App.swift   → App entry point?
├── **/*.entitlements        → Entitlements?
├── **/Info.plist            → App metadata?
└── **/*.xcstrings or *.strings → Localization?

Also read project.yml (or .pbxproj info) to determine:

  • App name, bundle ID, deployment target
  • Current SPM dependencies
  • Sandbox status
  • Whether it's a menu bar app (LSUIElement)
  • Current version numbers

Step 2: Show Status Dashboard

Present a clear dashboard of what exists vs what can be added:

## Project: {{AppName}} ({{BundleID}})

### Already in place
 ✓ XcodeGen (project.yml)
 ✓ Git initialized
 ✓ GitHub Actions CI/CD
 ✓ Entitlements (no sandbox)

### Available to add
 1. Auto-update mechanism (GitHub API polling / Sparkle)
 2. File-based logging
 3. SwiftLint config
 4. Unit test target
 5. Launch at Login
 6. Accessibility permission gate
 7. Screen Recording permission flow
 8. Localization
 9. Settings/Preferences window
 10. Analytics (Aptabase)
 11. Onboarding/Welcome window
 12. Homebrew Cask formula
 13. README.md with badges
 14. License file
 15. AGENTS.md + CLAUDE.md symlink

Which features would you like to add? (comma-separated numbers, or "all")

Read the full file on GitHub · 599 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. 12d ago First seen · 599 lines · 36 tokens per session scan B d0644e15969d

Subscribe to this mod's changes

macos-app-scaffold-enhance is a skill published in the GitHub repository XueshiQiao/macos-app-scaffold (46 stars, last pushed 26d ago), licensed MIT. It adds 36 tokens to every session and 6,901 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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

axiom-shipping

Use when preparing ANY app for submission, handling App Store rejections, writing appeals, or managing App Store Connect. Covers submission checklists, rejection troubleshooting, metadata requirements, privacy manifests, age ratings, export compliance.

CharlesWiltgen/Axiom · 48 tokens

mobiai-create-pr

YOU MUST use this before ANY git push, branch push to remote, merge, or PR creation — regardless of phrasing or language. Covers all irreversible integration actions (committing, pushing, opening a PR, shipping finished work). Also triggers proactively after a fix when the user signals completion (still ask before…

ArisGuimera/MobiAI-Core · 75 tokens

mobiai-mobile-finishing-branch

You MUST use this once mobile implementation is finished and you are about to integrate the work — merging, pushing, opening a PR, or cleaning up the branch. Do not improvise the wrap-up; this skill gates verification, presents integration options, and handles cleanup.

ArisGuimera/MobiAI-Core · 61 tokens

mobiai-mobile-worktrees

You MUST use this before starting mobile work that needs isolation from the current workspace — new feature branches, parallel efforts, or any plan execution that should not contaminate the active tree. Do not create worktrees ad hoc; this skill enforces safe directory selection and verification.

ArisGuimera/MobiAI-Core · 60 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

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