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 troyjthomas/ios-agent-skills --skill app-visiongit clone --depth 1 https://github.com/troyjthomas/ios-agent-skillsWrote 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/troyjthomas/ios-agent-skills/app-vision)<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/app-vision"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/app-vision/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/troyjthomas/ios-agent-skills/app-vision"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/app-vision.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 | $0.00076 | $0.00765 |
| Opus 5.5 | $0.00030 | $0.00306 |
| Sonnet 5.5 | $0.00015 | $0.00153 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
app-vision 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Vision
Turn a rough idea into a concrete app concept. This happens in Claude chat, not Claude Code.
When to Use
- You have an app idea but haven't defined scope
- You're starting a brand new project
- You need to articulate what the app is before building anything
The Conversation
Work through these questions. You don't need to answer them all at once. The goal is a clear picture, not a formal document.
1. The Elevator Pitch
What does this app do in one sentence? If you can't say it in one sentence, the scope is too big for v1. Examples:
- "Track crochet projects and count stitches"
- "Split restaurant bills with friends"
- "Log daily mood with a single tap"
2. Who Is It For
One specific person, not "everyone." Ideally someone you know.
- Who will use this every day?
- What are they doing RIGHT NOW without your app? (Paper? Spreadsheet? A worse app?)
- What's the one thing they'd thank you for?
3. Core Screens (The 80/20)
List every screen you can imagine. Then cut it in half. Then cut it again. What remains is v1.
The test: If you removed this screen, would the app still work? If yes, it's not v1.
V1 should have 5-12 screens. More than that and you're building v2 before v1 ships.
4. What It's NOT
Defining boundaries prevents scope creep. Write down 3-5 things this app will NOT do in v1.
5. Platform and Constraints
- iPhone only? iPad too? Mac?
- Offline-first or requires internet?
- Needs backend/server or local-only?
- Any third-party integrations? (HealthKit, CloudKit, Sign in with Apple)
Output
By the end of this conversation, you should have:
- One-sentence pitch
- Target user (a real person or archetype)
- Screen list (5-12 screens with one-line descriptions)
- Not-doing list (3-5 things explicitly out of scope)
- Platform targets and key constraints
This output feeds directly into the app-spec skill. Do not open Claude Code until this is done.
Anti-Patterns
| Temptation | Why It Fails |
|---|---|
| "Let me just start building and see what happens" | You'll build 60% of an incoherent app and have to start over |
| "I want it to do everything the competitor does" | You'll never ship. Pick the 3 things you do better |
| "I'll figure out navigation later" | Navigation IS the app. Define it now |
| "It should work on iPhone, iPad, Mac, and Watch" | Ship on iPhone first. Expand after v1 |
| "I don't need to write this down, it's all in my head" | Claude Code can't read your head. Write it down |
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.
- 1mo ago First seen · 73 lines · 76 tokens per session scan A fc8af03597d7
app-vision is a skill published in the GitHub repository troyjthomas/ios-agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 765 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
react-native-gen
React Native code generation from Memoire specs — NativeWind styling, Expo-compatible, platform-specific patterns.
swiftui-design-engineering
Design, build, refactor, and review production SwiftUI interfaces with explicit state ownership, navigation, accessibility, design tokens, previews, and simulator verification.
swift-concurrency-safety
Design and review Swift 6 concurrency boundaries using structured tasks, actors, Sendable values, cancellation, and compiler-backed data-race safety.
swiftui-liquid-glass
Adopt or audit iOS 26+ SwiftUI Liquid Glass with native APIs, correct availability fallbacks, restrained hierarchy, accessibility, and measured rendering performance.
xcode-build-reliability
Make Xcode builds agent-verifiable with deterministic scheme discovery, concise logs, explicit destinations, stable scripts, build-time evidence, and CI parity.
ios-app-intents
Design, implement, and verify App Intents, App Entities, App Shortcuts, widgets, Siri, Spotlight, and Apple Intelligence surfaces with stable identity and safe execution.