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 tomcounsell/ai --skill new-mac-appgit clone --depth 1 https://github.com/tomcounsell/aiWrote 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/tomcounsell/ai/new-mac-app)<a href="https://agentmods.dev/skills/tomcounsell/ai/new-mac-app"><img src="https://agentmods.dev/badge/skills/tomcounsell/ai/new-mac-app/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/tomcounsell/ai/new-mac-app"><img src="https://agentmods.dev/badge/skills/tomcounsell/ai/new-mac-app.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 | $0.00059 | $0.01267 |
| Opus 5.5 | $0.00024 | $0.00507 |
| Sonnet 5.5 | $0.00012 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
new-mac-app 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 today.
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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
30 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.
- agents/openai.yaml 91 B
- scripts/new-app.sh 1.7 KB runs code
- template/.gitignore 80 B
- template/build.sh 2.4 KB runs code
- template/CLAUDE.md 3.7 KB
- template/Icon/AppIcon.icon/Assets/back.svg 172 B
- template/Icon/AppIcon.icon/Assets/front.svg 173 B
- template/Icon/AppIcon.icon/icon.json 481 B
- template/Info.plist.in 926 B
- template/Package.swift 621 B
- template/Sources/__APP_NAME__/App.swift 3.3 KB
- template/Sources/__APP_NAME__/ContentView.swift 2.9 KB
- template/Sources/__APP_NAME__/Models.swift 1.6 KB
- template/Sources/__APP_NAME__/SeedData.swift 1.5 KB
- template/Sources/__APP_NAME__/SelfTest.swift 2.6 KB
- template/Sources/__APP_NAME__/SettingsView.swift 1.6 KB
- template/Sources/__APP_NAME__/Snapshot.swift 5.5 KB
- template/Sources/__APP_NAME__/UI/AppearanceSettings.swift 6.1 KB
- template/Sources/__APP_NAME__/UI/Grid.swift 5.7 KB
- template/Sources/__APP_NAME__/UI/Theme.swift 6.1 KB
- template/Sources/__APP_NAME__/UI/WindowBehavior.swift 2.8 KB
- template/Sources/__APP_NAME__Kit/ItemTitle.swift 517 B
- template/Tests/__APP_NAME__KitTests/ItemTitleTests.swift 300 B
- template/tools/check-layout.swift 5.2 KB
- template/tools/grid-lint.sh 1.2 KB runs code
- template/tools/icon_review.sh 1023 B runs code
- template/tools/icon_sheet.swift 1.6 KB
- template/tools/make_icon.sh 1.2 KB runs code
- template/tools/selftest.sh 340 B runs code
- template/tools/snap.sh 666 B 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.
- today First seen · 121 lines · 59 tokens per session scan A f2c76bf9f484
new-mac-app is a skill published in the GitHub repository tomcounsell/ai (31 stars, last pushed yesterday), licensed GPL-3.0. It adds 59 tokens to every session and 1,267 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
android-kmp-architecture
CIEL's framework for Android and Kotlin Multiplatform (KMP) architecture, module boundaries, and dependency inversion.
Jetpack Compose Conventions
State hoisting, remember/derivedStateOf patterns, modifier ordering, and preview annotations.
Play Store Readiness
App signing, keystore management, API level targeting, privacy policy, and review guideline checks.
SwiftUI Conventions
@State/@Binding/@ObservedObject usage, view composition, preview-driven development.
ciel-swift-and-ios-standards
CIEL's framework for Swift 6.2 concurrency, actor-based persistence, and Liquid Glass design.
swiftui-patterns
Modern SwiftUI architecture, state management with @Observable, and view composition best practices.