Modules And Routing logo

Modules And Routing

OrganizationPopular
agent0ai
Modules And Routing

Place first-party modules correctly, make them routable, and use router seams instead of hardwiring features into shells.

Overview

Publisheragent0ai
Repositoryspace-agent
Skill nameModules And Routing
Stars
1.4K
Forks
323
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Modules And Routing 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/modules-routing .claude/skills/agent0ai-modules-and-routing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Modules And Routing 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 Modules And Routing 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 Modules And Routing 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 creating or updating routed modules, deciding where files belong, or wiring a feature into the authenticated app shell.

If the user wants a reusable app surface, tool UI, settings panel, or workflow screen, prefer a custom routed page module over a space. Spaces are for persisted user-authored widget canvases; custom pages are for feature-owned interfaces.

First-Party Module Placement

  • Browser modules are namespaced as mod/<author>/<repo>/....
  • Repo-owned first-party modules should normally live under app/L0/_all/mod/_core/<feature>/.
  • A routed feature should usually own its own view.html under that module root.
  • Keep the module root as the real implementation location and use ext/html/... files only as thin adapters into existing seams.

Custom Pages Instead Of Spaces

  • Build a custom routed page when the extension should behave like a first-class feature screen instead of a widget on a persisted space canvas.
  • Use spaces when the user wants a configurable board of widgets that lives under ~/spaces/....
  • Use a routed page when the feature owns its own layout, state, and navigation flow.
  • To make a custom page appear in the dashboard Panels section, add ext/panels/<name>.yaml in the owning module.
  • Panel manifests should define name, path, optional description, optional icon, and optional color.
  • For first-party _core routes, the manifest path may use shorthand such as user instead of a full /mod/... path.
  • Panel manifest path values may use shorthand route paths such as user, prefixed hash paths such as #/user, or direct /mod/... HTML paths such as /mod/_core/user/view.html.

Router Resolution

  • The main app is hash-routed.
  • #/dashboard resolves to /mod/_core/dashboard/view.html.
  • #/time_travel resolves to /mod/_core/time_travel/view.html.
  • A multi-segment route such as #/author/repo/path resolves to /mod/author/repo/path/view.html.
  • If the final route segment already ends in .html, the router resolves directly to that file under /mod/....
  • Query parameters stay attached to the resolved route target.

Router-Owned Seams

Current routed shell anchors are:

  • _core/router/shell_start
  • _core/router/shell_end
  • page/router/route/start
  • page/router/route/end
  • page/router/overlay/start
  • page/router/overlay/end

Use those anchors before editing router shell markup directly. Floating UI such as the onscreen agent belongs in the routed overlay anchors.

Common Module Shape

For a new first-party routed feature, the normal home is:

text
app/L0/_all/mod/_core/<feature>/
  view.html
  <feature>.css
  store.js
  panel.html or supporting components
  ext/panels/<feature>.yaml when the page should be discoverable from the dashboard
  ext/html/... only when the feature mounts into an existing seam

Minimal first-party custom page example:

text
app/L0/_all/mod/_core/my_tool/
  view.html
  my-tool.css
  store.js
  ext/panels/my-tool.yaml

Example panel manifest:

yaml
name: My Tool
path: my_tool
description: A custom routed tool page.
icon: build
color: "#94bcff"

Panel Helper Script

Reusable helper script:

js
const panelTools = await import("/mod/_core/skillset/ext/skills/development/modules-routing/panel-tools.js");

Available helpers:

  • await panelTools.listPanels() returns the normalized dashboard panel entries discovered from ext/panels/*.yaml, each with routePath and ready-to-use href
  • await panelTools.findPanel("user") resolves a panel by visible name, route path, hash route, direct /mod/... HTML path, or a panel object returned by listPanels()
  • await panelTools.resolvePanelRoutePath("/mod/_core/user/view.html") normalizes a panel target into its router route path
  • await panelTools.createPanelHref("#/user") returns the routed href
  • await panelTools.goToPanel("User") navigates through space.router with a hash fallback
  • await panelTools.openPanel(panelEntry) is an alias for goToPanel(...)

Use those helpers when you need to inspect the registered panels before wiring new links or when the user asks to navigate to one of them.

Example:

js
const panelTools = await import("/mod/_core/skillset/ext/skills/development/modules-routing/panel-tools.js");
const panels = await panelTools.listPanels();
const userPanel = await panelTools.findPanel("/mod/_core/user/view.html");
await panelTools.goToPanel(userPanel ?? "user");

Shell Rules

  • / is the authenticated app shell and mounts _core/router.
  • /admin is separate and firmware-clamped to L0; do not treat it as the default home for user-facing routed features.
  • Keep page-shell concerns in the router or page shells and keep feature logic inside the owning module.

Mandatory Doc Follow-Up

  • If route resolution, stable router seams, or the first-party module placement rules change, update the router docs and the development skill subtree in the same session.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Modules And Routing AI skill do?

Place first-party modules correctly, make them routable, and use router seams instead of hardwiring features into shells.

Why use Modules And Routing on TypingMind?

Because you install it once and use it with any model. Modules And Routing 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 Modules And Routing 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/modules-routing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Modules And Routing?

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 Modules And Routing?

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

Is the Modules And Routing 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 👇