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 catch-the-wave/fullstack-ios-claude-skills --skill ui-architecture-reviewgit clone --depth 1 https://github.com/catch-the-wave/fullstack-ios-claude-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/catch-the-wave/fullstack-ios-claude-skills/ui-architecture-review)<a href="https://agentmods.dev/skills/catch-the-wave/fullstack-ios-claude-skills/ui-architecture-review"><img src="https://agentmods.dev/badge/skills/catch-the-wave/fullstack-ios-claude-skills/ui-architecture-review/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/catch-the-wave/fullstack-ios-claude-skills/ui-architecture-review"><img src="https://agentmods.dev/badge/skills/catch-the-wave/fullstack-ios-claude-skills/ui-architecture-review.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 | $0.00115 | $0.01211 |
| Opus 5.5 | $0.00046 | $0.00484 |
| Sonnet 5.5 | $0.00023 | $0.00242 |
| Haiku 4.5 | $0.00012 | $0.00121 |
Grade A, and why
ui-architecture-review 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
Structure precedes style. If the information architecture is wrong, no amount of typography, haptics, or spring animations will fix it. This skill challenges logical structure before anyone touches pixels.
Every element must justify its existence. "Who needs this, how often, and what breaks if I remove it?" Elements that can't answer all three get killed or moved.
Concerns don't mix. Content creation, organization, media attachment, and mode switching are different concerns. Putting them in one flat menu creates a junk drawer, not a toolbar.
Reference apps are evidence, not inspiration. When Apple Notes, Things, Bear, Linear, and Notion all separate a concern the same way, that's a discovered pattern, not a style choice. </essential_principles>
This is the design equivalent of code review — challenge architecture, not aesthetics.
<quick_start> Given a component (code, screenshot, or description), run in this order:
- Element justification — For each interactive element: who uses it, how often, what if removed? → KEEP / MOVE / MERGE / KILL
- Concern separation — Are different concerns (creation, organization, attachment, destruction) mixed in one surface?
- Cognitive friction — Apply CDN: viscosity, premature commitment, hidden dependencies, role expressiveness, diffuseness
- Action hierarchy — Is there exactly ONE primary action? Are secondary actions same-concern? Are tertiary actions hidden?
- UX laws — Apply relevant laws to quantify user cost: Hick's (choice count), Fitts's (target distance), Miller's (working memory load), Gestalt (false groupings), Doherty (latency perception)
- Reference check — How do best-in-class apps solve this? What pattern emerges?
- Synthesis — Recommended restructuring with rationale. Hand contradictions to TRIZ.
Read references/ for detailed frameworks on each step.
</quick_start>
<reference_index>
Domain knowledge in references/:
| File | Content | Load when |
|---|---|---|
| cognitive-dimensions.md | CDN framework — 9 dimensions with scoring rubric | Analyzing interaction friction |
| action-hierarchy.md | Primary/secondary/tertiary patterns + reference app evidence | Auditing control placement and menu structure |
| ia-anti-patterns.md | Junk drawer, false peers, concern mixing, premature surfacing + fixes | Diagnosing structural problems |
| element-justification.md | Frequency-adoption matrix, kill criteria, Bastien-Scapin grouping rules | Deciding what should exist and what groups together |
| ux-laws.md | Fitts, Hick, Miller, Gestalt, Jakob's, Doherty, Peak-End — quantifiable user cost | Measuring user cost of structural decisions |
| </reference_index> |
<output_format>
## IA Critique: [Component Name]
### Element Justification
| Element | Who | Frequency | If removed? | Verdict |
|---------|-----|-----------|-------------|---------|
### Concern Map
[Which concerns are present? Are any mixed in one surface?]
### Cognitive Friction (CDN)
[FRICTION and BROKEN dimensions only — skip OK ones]
### Hierarchy Violations
[Primary/secondary/tertiary misplacements]
### UX Law Violations
| Law | Evidence | Cost |
|-----|----------|------|
[Only laws that are violated — skip compliant ones]
### Reference Comparison
[How 2-3 best-in-class apps solve this differently]
### Recommended Architecture
[Proposed restructuring with rationale]
### Open Contradictions
[Trade-offs that need /triz-product-architect]
</output_format>
What ships with it
5 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.
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 · 104 lines · 115 tokens per session scan A 9371af415940
ui-architecture-review is a skill published in the GitHub repository catch-the-wave/fullstack-ios-claude-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,211 once invoked, about $0.0005 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 2026-09-19.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.