markstream-custom-components

markstream-custom-components is a skill for Claude Code, Codex from Simon-He95/markstream-vue. It costs 97 tokens per session (841 once invoked), scanned A, original, MIT.

Instructions for changing how Markstream displays Markdown content in Vue, React, Svelte, or Angular applications, including replacing built-in renderers and supporting custom tags.

In plain words
What is it for?
Use them to customize the display of images, links, code blocks, diagrams, inline code, or trusted custom elements.
Why use it?
They help changes stay limited to the intended part of the interface and clarify which integration method fits each framework.

Skill for Claude CodeCodex

About the project

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.

Simon-He95/markstream-vue · 2,986 stars · on GitHub

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/simon-he95/markstream-vue/markstream-custom-components
Any agent
npx skills add Simon-He95/markstream-vue --skill markstream-custom-components
Clone the repo
git clone --depth 1 https://github.com/Simon-He95/markstream-vue

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 markstream-custom-components

README.md
[![agentmods](https://agentmods.dev/badge/skills/simon-he95/markstream-vue/markstream-custom-components.svg)](https://agentmods.dev/skills/simon-he95/markstream-vue/markstream-custom-components)
Your own site
<a href="https://agentmods.dev/skills/simon-he95/markstream-vue/markstream-custom-components"><img src="https://agentmods.dev/badge/skills/simon-he95/markstream-vue/markstream-custom-components.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 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 $0.00097 $0.00841
Opus 5 $0.00048 $0.00420
Sonnet 5 $0.00019 $0.00168
Haiku 4.5 $0.00010 $0.00084

Measured 5d ago against content hash 7206433824f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markstream-custom-components 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 5d 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/markstream-custom-components/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Markstream Custom Components

Use this skill when the task is to change how Markstream renders specific nodes or custom tags.

Read references/patterns.md before choosing an override strategy.

Workflow

  1. Classify the request.
    • built-in override: replace an existing renderer such as image, link, code_block, mermaid, d2, or inline_code.
    • custom tag: support trusted HTML-like tags such as thinking.
    • parser-level: requires token transforms or AST reshaping. Only then should you leave this skill and use low-level parser hooks.
  2. Prefer scoped mappings.
    • Vue, Vue 2, Svelte, and shared Angular registration: use setCustomComponents(customId, mapping) instead of global mappings whenever practical, and pass the same customId / custom-id.
    • React custom tags: prefer renderer-local streamingComponents for parser-backed nodes or htmlComponents for sanitized HTML props plus children. Use defineStreamingComponents(...) / defineHtmlComponents(...) for typed maps. Keep setCustomComponents for built-in node overrides or shared legacy registration.
    • Svelte and Angular can also pass a renderer-local customComponents map when the override should not enter the shared registry.
    • In Vue 3 app/plugin setup, import { VueRendererMarkdown } from markstream-vue and install it with { components } when the override should be scoped to the Vue app instance.
  3. Start with the smallest safe override.
    • Leaf-like nodes (image, link, inline_code, mermaid) are easier than container nodes (heading, paragraph, list_item).
    • If the request only changes Mermaid, use mermaid, not code_block.
  4. Preserve nested Markdown when needed.
    • For trusted custom tags with inner Markdown, render node.content with a nested renderer.
    • Pass the same custom-tag allowlist to nested renderers.
    • Nested renderers inside a smooth-streaming parent are automatically suppressed from double pacing — do not add smooth-streaming to child renderers.
    • In React, streamingComponents automatically contributes its keys to the effective custom-tag list; do not duplicate those keys in customHtmlTags unless another parser path needs them.
  5. Keep props and cleanup intact.
    • Preserve node, loading, indexKey, customId, and isDark.
    • For mermaid and infographic overrides, preserve estimatedPreviewHeightPx so async preview shells keep stable height during remounts.
    • Remove temporary scoped mappings with removeCustomComponents(customId) when the scope is no longer needed.
  6. Validate with the smallest useful check.
    • Prefer a local demo, targeted test, or docs build.
    • Call out whether the implementation is safe for repeated and nested custom tags.

Read the full file on GitHub · 54 lines

Files

What ships with it

2 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. 5d ago First seen · 54 lines · 97 tokens per session scan A 7206433824f8

Subscribe to this mod's changes

markstream-custom-components is a skill published in the GitHub repository Simon-He95/markstream-vue (2,986 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 841 once invoked, about $0.0005 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