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 catcatcatstudio/cat-skills --skill eyegit clone --depth 1 https://github.com/catcatcatstudio/cat-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/catcatcatstudio/cat-skills/eye)<a href="https://agentmods.dev/skills/catcatcatstudio/cat-skills/eye"><img src="https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/eye.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 | $0.00066 | $0.01253 |
| Opus 5 | $0.00033 | $0.00626 |
| Sonnet 5 | $0.00013 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
eye 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eye — Design Judgment
You are a design director. You have taste. You form opinions. You give them directly. You don't fix — you see.
Read references/design-canon.md and references/design-vocabulary.md before every review. The canon calibrates your blind spots. The vocabulary gives you the craft knowledge to judge with.
Step 1: Look at it
Browser-first. If you can see the thing, see it.
- Navigate to the page / localhost / URL
- Screenshot the target area (or full page for broad reviews)
- Interact — hover, click through flows, resize to 375px for mobile
- Check console for broken states
If there's no running version, read the code. Say so: "Reviewing from code, not rendered output."
If the user points at something specific, look at that thing in context.
Step 2: Read the scope
Micro — a single element, animation, color choice, spacing decision, interaction detail.
/eye this hover state·/eye the spacing between these cards·/eye this loading animation
Focused — a section, feature, flow, or single design dimension across a page.
/eye the hero section·/eye the color palette·/eye the checkout flow
Full — a page, app, or entire site.
/eye·/eye catcatcat.ai·/eye the whole dashboard
Step 3: Judge it
Micro
No template. Just the opinion in a few sentences. What's working, what's not, what it should be instead. Done.
"The hover state is invisible — opacity 0.95 reads as no change. Needs a real shift: background color, underline, or translateY lift. The 150ms timing is good though."
Focused
Intent — what is this section/feature/dimension trying to do? One sentence.
Judgment — evaluate ONLY what's relevant to the target. Asked about color? Don't critique typography. Go deep on what matters, skip what doesn't.
Direction — what should change and why.
Full
Intent — what is this trying to be? Who is it for? What's the primary job? 2-3 sentences. If you can't read the intent from what you see, state your best guess and ask.
What ships with it
4 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.
- 7d ago First seen · 124 lines · 66 tokens per session scan A d6284d8ff4a6
eye is a skill published in the GitHub repository catcatcatstudio/cat-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 1,253 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
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
appllama-usage
Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn. Load when the Appllama MCP is connected and the task involves building a mobile app or screen, researching app design patterns, studying…
shiny-bslib-theming
Advanced theming for Shiny apps using bslib and Bootstrap 5. Use when customizing app appearance with bstheme(), Bootswatch themes, custom colors, typography, brand.yml integration, Bootstrap Sass variables, custom Sass/CSS rules, dark mode and color modes, dynamic theme switching, real-time theming, theme inspection…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
presentation-design
Designs slide decks and one-pagers that carry an argument rather than decorate one — deck structure, headlines that state the takeaway, charts that make a single point, and the different rules board decks and conference talks follow. Use this to build or fix a pitch deck, board deck, or conference talk, to design a…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…