Extensions And Components logo

Extensions And Components

OrganizationPopular
agent0ai
Extensions And Components

Use HTML adapters, JS hook seams, and component loading correctly in the layered module system.

Overview

Publisheragent0ai
Repositoryspace-agent
Skill nameExtensions And Components
Stars
1.4K
Forks
323
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by agent0ai on GitHub. Read the source before you install it.

Installation

Install the Extensions And Components AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agent0ai/space-agent.git /tmp/space-agent
mkdir -p .claude/skills
cp -r /tmp/space-agent/app/L0/_all/mod/_core/skillset/ext/skills/development/extensions-components .claude/skills/agent0ai-extensions-and-components
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Extensions And Components in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Extensions And Components on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Extensions And Components is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use this skill when the task needs ext/html/, ext/js/, x-extension, x-component, x-context, or layered override behavior.

HTML Extension Rules

  • Declare structural seams with <x-extension id="some/path">.
  • Matching HTML files live at mod/<author>/<repo>/ext/html/some/path/*.html.
  • HTML callers name only the seam; the runtime resolves ext/html/ automatically.
  • Keep extension files thin. They should usually mount a real component with <x-component path="/mod/...">.
  • _core/framework also creates _core/framework/head/end in document.head during bootstrap when a layer needs head-side HTML or inline bootstrap code without editing page shells.
  • Use framework x-inject="selector" instead of raw Alpine x-teleport when route-owned markup targets a shell seam that may mount later; it mirrors teleport semantics for <template> roots, waits for the selector, and disconnects its observer when the source template unmounts.
  • Dynamic discovery watches the whole document tree, so head seams and the x-component nodes they insert are loaded the same way as body content.
  • The routed shell header owns Home itself and points it at the empty route #/; _core/onscreen_menu/bar_start and _core/onscreen_menu/bar_end are the left and right shell-control seams, and feature modules add non-Home dropdown menu-action buttons under _core/onscreen_menu/items with numeric data-order values such as 100, 200, 300, and 400; _core/onscreen_menu sorts contributed controls or items automatically and keeps only the auth exit action after the dropdown seam.

Example:

html
<x-extension id="page/router/overlay/end"></x-extension>
html
<x-component path="/mod/_core/onscreen_agent/panel.html"></x-component>

JS Hook Rules

  • Use space.extend(import.meta, async function name(...) { ... }) for behavioral seams.
  • JS hook files live at mod/<author>/<repo>/ext/js/<extension-point>/*.js or *.mjs.
  • The runtime resolves /start and /end hooks around the wrapped function automatically.
  • space.extend() requires a valid module ref and a standalone named function or explicit extension point name.
  • Framework-backed pages expose _core/framework/initializer.js/initialize; use _core/framework/head/end when the work can stay declarative, and keep the initializer /end hook for once-per-page shell setup that must stay imperative.
  • If a feature needs onscreen-agent-specific prompt shaping or execution validation for its own helpers, add an ext/js/_core/onscreen_agent/... hook from that feature instead of editing _core/onscreen_agent directly.

Extension Metadata Rules

  • Modules may also store lightweight metadata assets under other ext/ folders when those files should follow the same readable-layer permissions and same-path override rules as HTML and JS extensions.
  • The current first-party example is ext/panels/*.yaml, which the dashboard panel index discovers through file_paths, batch-reads through fileRead(...), and collapses to one effective manifest per modulePath + manifestName.
  • Keep those metadata files display-oriented. They are extension-resolved module assets, not general writable storage.

Component Loader Rules

  • <x-component> may load a full HTML document or a fragment.
  • The loader mounts styles, module scripts, and body nodes, then recursively resolves nested <x-component> tags.
  • Concurrent scans of the same <x-component> target reuse the in-flight load; they must not bail out in a way that leaves late-mounted components partially hydrated.
  • Mutation-driven x-component discovery watches document.documentElement, not only body, so head-side components hydrate too.
  • Keep component HTML declarative and bind behavior through stores.
  • Import the owning store module in the component that owns the feature, not in an unrelated parent shell.

Context Helper Rules

  • Framework bootstrap also injects one hidden runtime <x-context> with data-runtime="browser" on normal web sessions or data-runtime="app" in the packaged desktop runtime; packaged app routes derive that from the desktop bridge before falling back to launcher runtime info or frontend config, and that same element also exposes runtime-browser or runtime-app through data-tags.
  • Modules may export additional live skill-filter tags with hidden <x-context> elements anywhere in mounted DOM.
  • Set one or more tags with data-tags="a, b, c".
  • Alpine-bound attributes on <x-context> are the normal way to keep tags synced with route or store state.
  • Import /mod/_core/framework/js/context.js when code needs to inspect current <x-context> elements directly; the stable helpers are getContexts(...), getAttributeValues(...), getTags(...), and getContents(...).
  • Shared skill discovery reads those tags through that framework helper each time it builds the catalog, auto-loaded skill context, or an explicit skill load.

Layered Override Behavior

  • Module and extension resolution follow the readable L0 -> L1 -> L2 inheritance chain.
  • Identical module-relative extension file paths override lower-ranked entries.
  • Different filenames under the same extension point compose together.
  • Prefer additive composition before exact-path replacement.
  • maxLayer constrains module and extension resolution but not logical app-file paths.
  • Uncached HTML <x-extension> lookups batch before they call /api/extensions_load; the default flush is the next animation frame, and frontend constant HTML_EXTENSIONS_LOAD_BATCH_WAIT_MS in app/L0/_all/mod/_core/framework/js/extensions.js adds an extra wait window in milliseconds before that frame-aligned flush.
  • extensions_load keeps maxLayer at the call level; grouped lookups send ordered patterns arrays and receive ordered results with matching patterns plus resolved extensions.
  • JS hook lookups do not use that wait window; they resolve immediately because hook callers await them directly.

Practical Guidance

  • Add a new seam in the owner when downstream customization is realistic.
  • Do not bypass an existing seam by reaching into another module's private DOM or internals.
  • After adding a new ext/html/... or ext/js/... file, the running page often needs a refresh before discovery catches up.

Mandatory Doc Follow-Up

  • If extension lookup, component loading, hook behavior, or override semantics change, update the framework docs and the development skill subtree in the same session.

Frequently asked questions

What does the Extensions And Components AI skill do?

Use HTML adapters, JS hook seams, and component loading correctly in the layered module system.

Why use Extensions And Components on TypingMind?

Because you install it once and use it with any model. Extensions And Components is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Extensions And Components in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agent0ai/space-agent/tree/main/app/L0/_all/mod/_core/skillset/ext/skills/development/extensions-components. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Extensions And Components?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Extensions And Components?

As many as you like. As long as a model supports skills, you can use Extensions And Components with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Extensions And Components AI skill free?

Yes. It is published on GitHub by agent0ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇