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.
git clone --depth 1 https://github.com/app-builders-club/design-builderWrote 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/commands/app-builders-club/design-builder/design_screen)<a href="https://agentmods.dev/commands/app-builders-club/design-builder/design_screen"><img src="https://agentmods.dev/badge/commands/app-builders-club/design-builder/design_screen.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01465 |
| Opus 5 | $0.00018 | $0.00732 |
| Sonnet 5 | $0.00007 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
design_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 7d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-builder:design_screen — generate an app screen spec
Identical structure to /design-builder:design_page with iOS / native specifics. Spec lands in design/screens/<name>.md. Activate the design skill.
The user's argument names the screen — e.g. onboarding, home, profile, paywall, feed, detail, settings. Map to a screen-type vocab:
| User says | screen_type |
|---|---|
| "onboarding", "first run" | onboarding |
| "home", "main", "feed entry" | home_screen |
| "feed", "list", "timeline" | feed |
| "detail", "view", "show" | detail_view |
| "settings", "preferences" | settings |
| "paywall", "upgrade" | paywall |
| "profile", "account" | profile |
| "tab root", "tab bar" | tab_bar_root |
| "modal", "sheet" | modal_sheet |
Off-list → ask user to pick the closest or generate freely.
Phase 1 — System check (BLOCKING)
Same as /design_page Phase 1 — read design-system.md, style-guide.md, content-library.md, .cache/interview.json. Block on any missing.
Confirm stack is iOS-compatible (stack.target == "ios" or cross). If stack is web-only: redirect to /design_page and stop.
Phase 2 — Documentation check
Same as /design_page Phase 2 — single free-form ask. Use docs as input, never paraphrase.
Phase 2b — Content interview (only if no docs)
Same questions as /design_page Phase 2b plus one screen-specific addition (Q5):
- (same as design_page Q1) — main user task on this screen.
- (same as design_page Q2) — key elements/sections.
- (same as design_page Q3) — edge cases.
- (same as design_page Q4) — animation intensity override.
- NEW: "How does the user reach this screen and how do they leave? (
tab switch/push from <parent>/modal present/sheet (detents: <list>)/crossfade)" — captured for## Navigation context.
Capture to design/.cache/screen-<slug>-interview.json (same JSON shape as page interview, plus navigation_context field).
Phase 3 — Reference resolution
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.
- 7d ago First seen · 96 lines · 37 tokens per session scan A 95f6f60ec3e4
design_screen is a command published in the GitHub repository app-builders-club/design-builder (4 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,465 once invoked, about $0.0002 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 commands, from other repositories
design-mobile
Design a mobile screen or flow. This command never writes SwiftUI or Compose — the deliverable is a device-framed HTML mockup plus a handoff spec for the platform developer.
mobile-specialist
Use when a design will be used on phones. Touch targets too small, controls outside thumb reach, bottom navigation, gestures, safe areas and notches, or behaviour with no connection.
add-accessibility
SwiftUI view'lara accessibility identifier ekle. "accessibility ekle", "identifier ekle", "test icin etiketle", "VoiceOver destegi ekle", "erisilebilirlik ekle" gibi isteklerde tetiklenir.
hig-scaffold
Generate a HIG-compliant component or screen for a chosen Apple platform and stack (SwiftUI, UIKit, React Native, Flutter, HTML/CSS, etc.), using the on-disk Apple guidelines.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
stark-director
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.