markstream-vue is a family of Markdown renderers that display AI-generated text while it is still arriving, including unfinished formatting, code blocks, diagrams, and mathematical notation. It is for AI chat interfaces built with Vue and other supported frameworks, with markstream-vue targeting Vue 3, Nuxt, and VitePress. The catalogue entries provide agent guidance for using the renderer family.
Borrowing it
Nothing to install: this file belongs to Simon-He95/markstream-vue. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Simon-He95/markstream-vue/main/.agents/skills/markstream-react/SKILL.mdgit clone --depth 1 https://github.com/Simon-He95/markstream-vueWrote 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/simon-he95/markstream-vue/markstream-react)<a href="https://agentmods.dev/skills/simon-he95/markstream-vue/markstream-react"><img src="https://agentmods.dev/badge/skills/simon-he95/markstream-vue/markstream-react/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/simon-he95/markstream-vue/markstream-react"><img src="https://agentmods.dev/badge/skills/simon-he95/markstream-vue/markstream-react.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.01050 |
| Opus 5.5 | $0.00038 | $0.00420 |
| Sonnet 5.5 | $0.00019 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
markstream-react 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markstream React
Use this skill when the host app is React or Next and the task is to wire Markstream safely.
Workflow
- Confirm the repo is React 18+ or a compatible Next host and accepts a beta renderer API.
- Install
markstream-reactplus only the requested optional peers. - Import
markstream-react/index.cssfrom the app shell or client entry. - Choose the entrypoint that matches the rendering boundary.
- Use
markstream-reactfor the normal client renderer. - Use
markstream-react/nextfor the Next-specific component surface. - Use
markstream-react/serverfor server rendering without client hooks.
- Use
- Start with
content.- For streaming or high-frequency AI output, keep
contentand use built-in smooth streaming first.smoothStreaming="auto"is the default and activates whentypewriter={true}ormaxLiveNodes <= 0.typewriteronly controls the blinking cursor and defaults tofalse.fadecontrols node enter and streamed-text fade animations and defaults totrue.
- Streaming vs recovering history: in chat UIs the same renderer starts streaming and later switches to history when
final={true}.- Streaming:
smoothStreaming="auto",fade={false},typewriter={true}. This is a conservative visual/performance choice, not an API incompatibility. This adapter has not adopted Vue 3's bounded append fades, so verify its animation behavior before enabling both. - Recovering history:
smoothStreaming={false},fade={true},typewriter={false}. Content is already complete — pacing would slow it down, but fade gives a polished entry animation. - Dynamic switch:
smoothStreaming={isStreaming ? 'auto' : false},fade={!isStreaming}.
- Streaming:
- Move to
nodes+finalonly for worker-preparsed content, shared AST stores, or custom AST control. - Remember that
htmlPolicynow defaults tosafe, and Mermaid strict mode is on by default throughmermaidProps.
- For streaming or high-frequency AI output, keep
- Respect SSR boundaries in Next.
- Prefer
use client, dynamic imports withssr: false, or other client-only boundaries when browser-only peers are involved.
- Prefer
- Use renderer-local components before custom parser work.
streamingComponentsreceives parser-backedNodeComponentProps, supports incomplete custom tags, and automatically contributes its keys to the effectivecustomHtmlTagslist.htmlComponentsreceives sanitized HTML attributes pluschildren; it does not receive the parser node/loading contract.- Prefer
defineStreamingComponents(...)anddefineHtmlComponents(...)for typed maps. - Keep scoped
setCustomComponentsfor built-in node overrides or shared compatibility registration. - Use
parseOptionstransforms only when migration requires token or AST changes.
- Validate with the smallest useful dev, build, or typecheck command.
What ships with it
1 file 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.
- 1mo ago Changed 1c528154044f
- 2mo ago First seen · 61 lines · 94 tokens per session scan A 37305730b16a
markstream-react is a skill published in the GitHub repository Simon-He95/markstream-vue (3,051 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,050 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 2026-08-30.
markstream-react compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| markstream-reactSimon-He95/markstream-vue | Skill | 3.1k | yesterday | MIT | A | 94 | Codex |
| astrosickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 28 | Claude Code |
| streamdownvercel/streamdown | Skill | 5.7k | yesterday | none | A | 164 | Claude Code, Codex |
| pdf-presskdcube/kdcube | Skill | 27 | today | MIT | A | 74 | Claude Code |
| png-presskdcube/kdcube | Skill | 27 | today | MIT | A | 36 | Claude Code |
| mk:markdown-readerngocsangyem/MeowKit | Skill | 15 | 5d ago | MIT | A | 81 | Claude Code |
| mermaid-lintellmos-ai/skills | Skill | 9 | 3d ago | MIT | A | 61 | Claude Code, Codex |