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 screen-by-screengit 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/screen-by-screen)<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/screen-by-screen"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/screen-by-screen/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/screen-by-screen"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/screen-by-screen.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 | $0.00061 | $0.01704 |
| Opus 5 | $0.00030 | $0.00852 |
| Sonnet 5 | $0.00012 | $0.00341 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
screen-by-screen 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 9d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen by Screen
The core build loop. Pick a screen. Describe it. Build it. Review it. Move on.
When to Use
- Scaffolding is complete and committed
- You're ready to give each screen real content and functionality
- You're working in Conductor with parallel workspaces
- Any time you need to build or rebuild a specific screen
The Loop
1. Pick a screen
2. Open a Conductor workspace (or Claude Code session)
3. Describe what the screen needs
4. Claude Code builds it
5. Review in simulator
6. Give feedback (2-3 rounds max)
7. Commit and merge
8. Pick next screen
The Prompt Template
You don't need to paste code snippets. You don't need to reference Apple docs. You don't need to say "use SwiftUI." Your CLAUDE.md handles all of that. Just describe what the screen does.
Structure
Build out [Screen Name]. Here's what it needs:
[2-5 sentences describing what the user sees and what they can do]
[Any specific interaction details that aren't obvious]
[Edge cases: empty state, error state, loading state]
Example: Projects Home
Build out the Projects home screen. It's a scrollable list of the
user's active projects using LazyVStack. Each row shows the project
name in headline weight, a small circular progress ring showing
percent complete, and the yarn color as a small swatch circle.
Long press on any row opens a context menu with Edit, Duplicate,
Archive, and Delete. Delete should have a destructive role.
The plus button in the top right toolbar opens the New Project sheet.
When there are no projects, show a centered empty state with a short
message like "No projects yet" and a prominent button that also opens
the New Project sheet.
Example: Settings
Build out the Settings main screen. Standard iOS grouped list pattern
with the following sections:
Account section: Profile row showing user name and avatar placeholder.
Preferences section: Default units (metric/imperial picker), color
theme toggle, notification preferences (pushes to sub-page).
About section: Version number, Terms of Service link, Privacy Policy
link, rate the app link.
Support section: Send Feedback (opens mail compose), Help Center
(opens Safari).
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.
- 9d ago First seen · 202 lines · 61 tokens per session scan A 3dff0eaa259d
screen-by-screen is a skill published in the GitHub repository troyjthomas/ios-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,704 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
apple-design
Apple's fluid-interface craft on the web: spring damping and response, velocity handoff, momentum projection on a flick, rubber-banding at a boundary, interruptible motion the user can grab mid-flight, translucent materials and backdrop blur, letter-spacing and leading by size. Use for iOS-grade feel, sheets and drag.
UIKit Horizontal-First Layouting
Horizontal-first slicing methodology with mandatory ASCII preview for UIKit layout design.
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…
ss-copy
Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone.
ss-lint
Quick automated lint — detects common design system violations in seconds.