widgets

A skill for embedding styled HTML panels inside assistant messages. These panels can inherit the dashboard’s theme and display content such as charts, tables, cards, or small interactive examples.

In plain words
What is it for?
Use it to render visual summaries, charts, color-coded tables, styled cards, and simple interactive probes in an assistant response.
Why use it?
It makes structured or interactive information easier to inspect when plain text or Markdown is not enough.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/kirodotdev/kirocrew/widgets
Any agent
npx skills add kirodotdev/KiroCrew --skill widgets
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.02250
Opus 5 $0.00021 $0.01125
Sonnet 5 $0.00008 $0.00450
Haiku 4.5 $0.00004 $0.00225

Measured 2d ago against content hash 9b317de1ee6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

widgets 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 2d 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.

src/kiro_crew/builtin_skills/widgets/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inline widgets (<mcwidget>)

You can embed rich HTML in assistant messages using <mcwidget title="Title">HTML</mcwidget>. The dashboard renders each tag as a sandboxed iframe with Tailwind CSS preloaded. Use this for styled visual content plain markdown cannot express: charts, color-coded tables, styled cards, visual summaries, simple interactive probes.

The iframe CSP allows script-src from three CDNs: cdn.tailwindcss.com (preloaded), cdn.jsdelivr.net, and cdnjs.cloudflare.com. Tailwind is ready without any setup; other libraries (Chart.js, D3, etc.) need a <script src="…"> tag pulling from one of those two CDNs.

When to use

  • Use when styled HTML genuinely helps comprehension — Chart.js graphs, color-coded comparison tables, status cards, before/after previews, small interactive probes.
  • Don't use for content markdown already handles well — plain prose, bullet lists, fenced code, simple tables. Widget iframes carry more overhead than markdown; default to markdown.
  • Save to file for anything large. <mcwidget> bodies fit comfortably up to a few KB; beyond that, write an HTML file and return the absolute path so the dashboard shows a thumbnail / link instead.

Theme-aware styling (critical)

The widget iframe inherits the dashboard's active theme through CSS custom properties injected into each srcdoc. Use these variables instead of hardcoded colors so widgets render correctly on every theme (light, dark, and user-defined custom palettes).

Core palette (use these first):

Variable Role
var(--bg) Page background
var(--text) Foreground text
var(--card) Card / panel background
var(--card-fg) Foreground text on --card
var(--border) Borders and dividers
var(--accent) Primary accent / links
var(--muted) Muted / secondary text
var(--ok) Success state
var(--warn) Warning state
var(--danger) Error / destructive state
var(--info) Info / neutral callout (blue)

Read the full file on GitHub · 198 lines

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. 2d ago First seen · 198 lines · 42 tokens per session scan A 9b317de1ee6c

Subscribe to this mod's changes

widgets is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 2,250 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

reskin

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…

CopilotKit/CopilotKit · 154 tokens

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens

setup-slack-channel

Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…

CopilotKit/CopilotKit · 206 tokens

copilotkit-channels

Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…

CopilotKit/CopilotKit · 112 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens