streamdown

streamdown is a skill for Claude Code, Codex from tutur3u/platform. It costs 164 tokens per session (1,607 once invoked), scanned A, original, Apache-2.0.

A React component that displays Markdown, a plain-text format for headings, links, lists, and code, while content is still arriving. It supports code highlighting, Mermaid diagrams, mathematical notation, and Chinese, Japanese, and Korean text through optional plugins.

In plain words
What is it for?
Use it in React applications to render streamed Markdown, AI chat messages, highlighted code, diagrams, formulas, or CJK text.
Why use it?
It lets an interface show incomplete Markdown as it streams in, such as responses from an AI chat, instead of waiting for the full message.

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/tutur3u/platform/streamdown
Any agent
npx skills add tutur3u/platform --skill streamdown
Clone the repo
git clone --depth 1 https://github.com/tutur3u/platform

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 streamdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/tutur3u/platform/streamdown.svg)](https://agentmods.dev/skills/tutur3u/platform/streamdown)
Your own site
<a href="https://agentmods.dev/skills/tutur3u/platform/streamdown"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/streamdown.svg" alt="Measured on agentmods" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,607 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 $0.00164 $0.01607
Opus 5 $0.00082 $0.00804
Sonnet 5 $0.00033 $0.00321
Haiku 4.5 $0.00016 $0.00161

Measured 4d ago against content hash e0f4a595b13c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

streamdown 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 4d 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.

.agents/skills/streamdown/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Streamdown

Streaming-optimized React Markdown renderer. Drop-in replacement for react-markdown with built-in streaming support, security, and interactive controls.

Quick Setup

1. Install

npm install streamdown

Optional plugins (install only what's needed):

npm install @streamdown/code @streamdown/mermaid @streamdown/math @streamdown/cjk

2. Configure Tailwind CSS (Required)

This is the most commonly missed step. Streamdown uses Tailwind for styling and the dist files must be scanned.

Tailwind v4 — add to globals.css:

@source "../node_modules/streamdown/dist/*.js";

Tailwind v3 — add to tailwind.config.js:

module.exports = {
  content: [
    "./app/**/*.{js,ts,jsx,tsx,mdx}",
    "./node_modules/streamdown/dist/*.js",
  ],
};

3. Basic Usage

import { Streamdown } from 'streamdown';

<Streamdown>{markdown}</Streamdown>

4. With AI Streaming (Vercel AI SDK)

'use client';
import { useChat } from '@ai-sdk/react';
import { Streamdown } from 'streamdown';
import { code } from '@streamdown/code';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit, isLoading } = useChat();

  return (
    <>
      {messages.map((msg, i) => (
        <Streamdown
          key={msg.id}
          plugins={{ code }}
          caret="block"
          isAnimating={isLoading && i === messages.length - 1 && msg.role === 'assistant'}
        >
          {msg.content}
        </Streamdown>
      ))}
      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} disabled={isLoading} />
      </form>
    </>
  );
}

5. Static Mode (Blogs, Docs)

<Streamdown mode="static" plugins={{ code }}>
  {content}
</Streamdown>

Key Props

Prop Type Default Purpose
children string Markdown content
mode "streaming" | "static" "streaming" Rendering mode
plugins { code?, mermaid?, math?, cjk? } Feature plugins
isAnimating boolean false Streaming indicator
caret "block" | "circle" Cursor style
components Components Custom element overrides
controls boolean | object true Interactive buttons
linkSafety LinkSafetyConfig { enabled: true } Link confirmation modal
shikiTheme [light, dark] ['github-light', 'github-dark'] Code themes
className string Container class
allowedElements string[] all Tag names to allow
disallowedElements string[] [] Tag names to disallow
allowElement AllowElement Custom element filter
unwrapDisallowed boolean false Keep children of disallowed elements
skipHtml boolean false Ignore raw HTML
urlTransform UrlTransform defaultUrlTransform Transform/sanitize URLs

Read the full file on GitHub · 165 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. 4d ago First seen · 165 lines · 164 tokens per session scan A e0f4a595b13c

Subscribe to this mod's changes

streamdown is a skill published in the GitHub repository tutur3u/platform (53 stars, last pushed today), licensed Apache-2.0. It adds 164 tokens to every session and 1,607 once invoked, about $0.0008 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

frontend-engineer

!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults" !cat .forgewright/codebase-context.md…

buiphucminhtam/forgewright · 55 tokens

client-setup

Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

trpc/trpc · 63 tokens

adapter-express

Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.

trpc/trpc · 67 tokens

trpc-router

Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.

trpc/trpc · 59 tokens

supermemory

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…

supermemoryai/supermemory · 81 tokens

magic-ui

Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.

magicuidesign/magicui · 56 tokens