agentmods.dev

kimi-widget

kimi-widget is a skill for Claude Code, Codex from serejaris/kimi-skills. It costs 69 tokens per session (778 once invoked), scanned A, original, MIT.

A design system and runtime guide for building compact interactive surfaces inside a conversation, such as diagrams, dashboards, calculators, comparisons, and timelines.

In plain words
What is it for?
Use it when an answer benefits from visual structure, interaction, numeric controls, or a small state-based interface.
Why use it?
It defines when an interactive surface is useful and how it should work within the host interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 6repo 1mo ago A scan 69 tokens original MIT

Good fit Use it when an answer benefits from visual structure, interaction, numeric controls, or a small state-based interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/serejaris/kimi-skills/kimi-widget
View source ↗ serejaris/kimi-skills
Install

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.

Any agent
npx skills add serejaris/kimi-skills --skill kimi-widget
Clone the repo
git clone --depth 1 https://github.com/serejaris/kimi-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kimi-widget

README.md
[![agentmods](https://agentmods.dev/badge/skills/serejaris/kimi-skills/kimi-widget/github.svg)](https://agentmods.dev/skills/serejaris/kimi-skills/kimi-widget)
Your own site
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/kimi-widget"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/kimi-widget/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.

agentmods 80×15 button for kimi-widget

Your own site · 80×15
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/kimi-widget"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/kimi-widget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00778
Opus 5 $0.00034 $0.00389
Sonnet 5 $0.00014 $0.00156
Haiku 4.5 $0.00007 $0.00078

Measured 9d ago against content hash 4935451f5a36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kimi-widget 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 9d 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.

skills/kimi-widget/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi Widget

A widget is a compact visual or interactive surface rendered inline in the conversation: diagrams, dashboards, calculators, sliders, comparisons, timelines, state machines, small simulations. Use one when seeing structure helps the user understand, compare, inspect, or act on the answer better than prose alone.

When to generate a widget

  • The answer has spatial, sequential, systemic, comparative, numeric, or interactive structure.
  • The user does not need to say "show", "visualize", "chart", or "widget" — proactive widgets are expected when the structure is there.
  • If the user gives a compact visual spec without a verb ("REST vs GraphQL table", "checkout state machine", "pricing calculator"), render it as a widget instead of only describing it.

Do not use a widget for: ordinary prose answers, routine line-by-line code explanations, file lists / galleries / final deliverables, blocking input workflows, destructive or native actions, or large long-lived apps.

Runtime contract

The widget runs in a sandboxed iframe with the Kimi design system CSS already loaded. All CSS variables, form-element styles, and SVG classes are available at runtime — reference them, do not redefine them.

  • Allowed: HTML, SVG, CSS, inline JavaScript, native browser APIs.
  • Not allowed: external scripts, modules, stylesheets, images, fonts, CDN libraries, npm packages, fetch, or WebSocket. For charts/diagrams use SVG, Canvas, CSS, or plain DOM.
  • Text goes in your response, visuals go in the widget. All explanatory prose, intros, and summaries live OUTSIDE the widget.
  • After the widget renders, don't narrate it. Once you've called the widget tool and the widget is done, do not re-summarize or repeat what you just did — the visual speaks for itself. Say only what the widget cannot.
  • Sending intent back. An interactive widget may call window.sendPrompt(text) (when the host injects it) to push the user's next intent into the conversation. Write text as a real user message — what the user would actually type — never a robotic confirmation like "I selected option A, please proceed."
  • Never hardcode colors, fonts, or border-radius — always use var(--xxx). Hardcoded values break dark mode and look inconsistent with the host UI.

Read the full file on GitHub · 58 lines

Files

What ships with it

60 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.

Changes

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.

  1. 9d ago First seen · 58 lines · 69 tokens per session scan A 4935451f5a36

Subscribe to this mod's changes

kimi-widget is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 778 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 2026-09-03.

CSS and stylingDesign and UXFrontendagent-skillsai-agentsclaude-skillskimimoonshotskills
Related

Other skills, from other repositories

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.

tobihagemann/turbo · 48 tokens

slop-eval

Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…

fabricioctelles/skills · 142 tokens

theming

Use when building a theme or theming system for an interface. Covers token architecture, dark mode, contrast preservation across themes, and generating a coherent palette from a seed colour.

nimadorostkar/Claude-Skills-collection · 38 tokens

design-systems

Use when building or maintaining a component library and design tokens. Covers token architecture, component API design, variants and states, documentation, and governing adoption across a codebase.

nimadorostkar/Claude-Skills-collection · 38 tokens

liquid-glass

Liquid glass — Apple-style frosted, refracting surfaces. Use when the user asks for glassmorphism, frosted/translucent panels, cards, menus or a glass topbar; when a glass surface looks wrong (gray, flat, invisible, unreadable text); or when another skill needs the glass recipe.

stormaref/LiquidGlassSkill · 69 tokens

color-accessibility

Trigger on: check contrast, WCAG contrast, accessible colors, readable text color, fix low-contrast, dimmed text color, palette accessibility, pastel color, textcolor for background, make this color readable, UI theme contrast, Neovim highlight contrast. Evaluate, fix, and generate accessible fg/bg pairs with the…

tkolleh/skills · 109 tokens