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 evoelsewhere/evoflux --skill intelligent-uigit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/intelligent-ui)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/intelligent-ui"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/intelligent-ui/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/evoelsewhere/evoflux/intelligent-ui"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/intelligent-ui.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 | $0.00090 | $0.01250 |
| Opus 5.5 | $0.00036 | $0.00500 |
| Sonnet 5.5 | $0.00018 | $0.00250 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
intelligent-ui 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 today.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intelligent UI
ui_block renders compact native controls in chat. visual_artifact opens a
dashboard, motion explainer, or 3D view in the EvoFlux Workbench. This Skill is
the selection policy: use a visual only when it makes the user's next step
clearer or easier.
Choose from the task, not its vocabulary
Infer the outcome the user needs and the answer shape that would help. Words such as “plan,” “compare,” “chart,” “process,” or “calculate” do not select a tool by themselves. Prefer prose when it communicates the answer more directly. Use the smallest useful interaction, with controls that change an input, reveal a relationship, support inspection, or let the user act.
When a user asks to explain something visually or choose a useful format, apply this Skill even if they do not name a UI type. Do not treat “visual” as a request for a PDF: use PDF when the user asks for a printable or portable document, or when that format clearly serves the task.
- Use
ui_blockfor compact calculations, structured inputs, checklists, comparisons, and progress the user can update in chat. - Use a
chartormermaidMarkdown fence for a standalone chart or diagram. - Use a dashboard when a richer view helps inspect supplied or retrieved data;
read external sources first and label unverified sample figures illustrative.
Use
scene3donly when spatial structure benefits from rotation or inspection. - Use motion under the gate below. A timeline, plan, or long source is not by itself a reason to make a video.
Motion gate and context size
Choose visual_artifact with kind="motion" when the user explicitly asks
for video or animation, or when understanding depends on seeing how one state
changes into another or why one stage enables the next. For a process, ask
whether the learner needs to understand what changes at each stage and why the
next stage depends on the previous one. If yes, motion can be the right choice
even when a static flowchart could list the same steps. Use a static diagram,
checklist, or document when the steps are mainly for lookup, comparison, or
printing, or when their order does not carry the explanation. Do not infer
motion from prompt length, detail, or topic words alone.
What ships with it
6 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.
- today First seen · 98 lines · 90 tokens per session scan A d17b16f44e0b
intelligent-ui is a skill published in the GitHub repository evoelsewhere/evoflux (11 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 1,250 once invoked, about $0.0004 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 2026-10-20.
Other skills, from other repositories
dashboard
Update the agent's Control Center. Use when the user says "update my Control Center", "update my dashboard", "redesign my home", or "/dashboard".
product-ux-expert
Product interaction and UX expert. Use when reviewing UI/UX, conducting heuristic evaluations, designing user journeys, applying cognitive psychology principles, or ensuring WCAG 2.2 accessibility compliance.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
app-ui-design
Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.
app-user-story-qa
End-to-end app feature inventory and user-story testing workflow with a canonical tracker. Use when the user asks to audit every feature, derive expected behavior from code, test user journeys, or explicitly fix and retest documented UX or logistical defects.
figma-to-code
Extract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy. Use when a user provides a Figma URL or asks to convert Figma designs to code.