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.
git clone --depth 1 https://github.com/lidge-jun/ima2-gennpx agentmods add skills/lidge-jun/ima2-gen/ima2-uiuxWrote 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/lidge-jun/ima2-gen/ima2-uiux)<a href="https://agentmods.dev/skills/lidge-jun/ima2-gen/ima2-uiux"><img src="https://agentmods.dev/badge/skills/lidge-jun/ima2-gen/ima2-uiux.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.07300 |
| Opus 5 | $0.00059 | $0.03650 |
| Sonnet 5 | $0.00024 | $0.01460 |
| Haiku 4.5 | $0.00012 | $0.00730 |
Grade A, and why
ima2-uiux 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 8d 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ima2 UI/UX: Intent Discovery, Patterns & Product Vocabulary
Setup
npm install -g ima2-gen # install globally (Node.js >= 20)
ima2 setup # first-time auth (GPT OAuth recommended)
ima2 serve # start local server
ima2 ping # verify
ima2 status # config and OAuth status
Agent bootstrap: ima2 ping first. If unreachable: ima2 serve &. If not
installed: npm install -g ima2-gen && ima2 setup. Use ima2 skill path to
locate skills; read ../ima2-uiux/SKILL.md (this file) for design direction,
../ima2-front/SKILL.md for implementation assets.
Activates by change surface when:
- User's design direction is vague ("깔끔하게", "모던하게", "just make it look good")
- Building onboarding, empty state, error state, or loading state UI
- User references a product aesthetic ("Notion 느낌", "Linear처럼")
- Starting a new design system or generating a color palette
- Choosing layout patterns or navigation architecture
- Setting up favicons, product logos, or brand identity elements
- Handling logo dark mode variants, OG images, or social sharing meta
Read this before style-specific references when the user cannot articulate a clear design direction.
For anti-slop detection and banned patterns, defer to ima2 skill front ref anti-slop, especially the 2026 gradient budget and one-note theme bans.
Emoji ban (stub): no emoji as UI visual elements (STRICT). Canonical rule, scope, and exemptions: ima2-front §5 / ima2 skill front ref anti-slop § Emoji Slop.
Role separation: This skill owns design judgment: intent discovery, information architecture, UX state meaning, typography/color/layout direction, product personality, brand vocabulary, anti-slop pattern judgment, and design-system decisions. ima2-front owns implementation: HTML/CSS/components, responsive mechanics, accessibility wiring, runtime behavior, and rendered verification. After choosing the design direction here, load ima2-front for concrete implementation.
What ships with it
21 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.
- references/anti-slop-judgment.md 1.8 KB
- references/color-system.md 5.4 KB
- references/compositional-patterns.md 17 KB
- references/design-award-sources.md 11 KB
- references/design-isms.md 14 KB
- references/design-read-example.md 1.2 KB
- references/design-system-bootstrap.md 4.2 KB
- references/design-trends.md 12 KB
- references/favicon-logo.md 11 KB
- references/form-patterns.md 3.7 KB
- references/intent-discovery-ladder.md 4.4 KB
- references/korean-design-vocabulary.md 4.0 KB
- references/layout-macrostructures.md 3.2 KB
- references/logo-trust-sections.md 3.4 KB
- references/mobile-native-ux.md 10 KB
- references/product-personalities.md 7.6 KB
- references/responsive-nav.md 3.0 KB
- references/typography-line-breaks.md 8.7 KB
- references/ux-preflight.md 2.9 KB
- references/ux-states.md 9.2 KB
- references/visual-hierarchy.md 4.9 KB
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.
- 8d ago First seen · 494 lines · 118 tokens per session scan A e1912f0b6da8
ima2-uiux is a skill published in the GitHub repository lidge-jun/ima2-gen (749 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 7,300 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
local-image-gen
A local command-line tool for generating or editing images with Codex, Grok, or Gemini/Antigravity accounts and optional API keys.
motion-principles
Decide how something should move before you animate it — durations, easing curves, stagger offsets, weight, anticipation and follow-through, given as numbers ready to paste into a NodeTool timeline animation. Use when motion feels stiff, floaty, robotic or cheap, when picking a duration or an easing for an entrance…
frame-composition
Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave. Use when placing titles, lower thirds, shapes or overlays, when a layout must survive 16:9 and 9:16, when adding a push or a parallax move, or when…
logo-reveal
Animate a brand mark on a NodeTool timeline — stroke draw-on, mask wipe, staggered build, wordmark type, an idle loop, and landing the settle on a sound logo. Use for an intro sting, a sign-off, an end card, a splash, or a loader loop. Not for designing the mark itself.
motion-background
Build an ambient looping backdrop on a NodeTool timeline — gradient beds from shape clips, slow loop animations, layered drift, and a generated video bed — that moves without stealing focus. Use for a title card backdrop, a hero bed behind text, an end card, a lower-third plate, or a loop behind a talking head. Not…
motion-direction
Set the motion language for a piece before anything is animated — one easing family, one timing unit, one transition family, one stagger rhythm — and audit a timeline against it. Use when starting a title pass or a whole cut, when animation feels busy, cheap or inconsistent across shots, or when turning a brand or…