Backend Module Standards logo

Backend Module Standards

OrganizationPopular
siteboon
backend-module-standards

Enforce this repository's TypeScript backend module architecture standards. Use whenever creating, modifying, refactoring, or reviewing backend code under `server/`, including routes, services, modules, repositories, shared backend code, and backend tests. Do not apply these rules to frontend code or non-backend scaffolding.

Overview

Publishersiteboon
Repositoryclaudecodeui
Skill namebackend-module-standards
Stars
14.3K
Forks
2.1K
Bundled files
1
LicenseAGPL-3.0
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 siteboon on GitHub. Read the source before you install it.

Installation

Install the Backend Module Standards 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.
    https://github.com/siteboon/claudecodeui/tree/main/.agents/skills/backend-module-standards
  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/siteboon/claudecodeui.git /tmp/claudecodeui
mkdir -p .claude/skills
cp -r /tmp/claudecodeui/.agents/skills/backend-module-standards .claude/skills/backend-module-standards
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Backend Module Standards 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 Backend Module Standards 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 Backend Module Standards 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.

Backend Module Standards

Apply these rules after the repository's basic scaffolding is in place. Limit them to backend code under server/. Preserve the requested task scope: make touched and newly generated backend code compliant without performing an unrelated repository-wide migration.

Inspect before editing

  1. Identify the owning feature module and its existing barrel, services, routes, and tests.
  2. Search for existing shared types, interfaces, and utilities before adding any definition.
  3. Search for every consumer before changing a module's public exports.

Organize backend modules

  • Place each feature in server/modules/<feature>/.
  • Use TypeScript for every file inside server/modules/. Do not add JavaScript backend module files.
  • When touched JavaScript utilities belong to the work, migrate them to TypeScript. Place a one-use utility in its sole component; place a utility used in at least two locations in server/shared/utils.ts.
  • Give every feature module an index.ts barrel that exposes only its required public API.
  • Import another feature module only through that module's index.ts. Never deep-import another module's routes, services, repositories, adapters, or internal files.
  • Treat server/shared/ as the shared module. Keep shared definitions in server/shared/types.ts, server/shared/interfaces.ts, and server/shared/utils.ts, and expose only required cross-module members through its barrel.
  • Do not create module-local types.ts, interfaces.ts, or utils.ts files.
  • Keep module-private implementation details unexported.

Place types, interfaces, and utilities

  • Use type by default. Use interface only for a contract that a class is intended to implement.
  • Use export type for type exports and import type for type-only imports.
  • Define a type, interface, or utility directly in its component file when it is used in only that location.
  • Move a type or interface used in two or more locations to server/shared/types.ts or server/shared/interfaces.ts as appropriate.
  • Move a utility used in two or more locations to server/shared/utils.ts.
  • Do not duplicate an existing shared definition to avoid importing it.
  • Give every shared type, interface, and utility a detailed doc comment explaining its behavior, valid usage, and important constraints.
  • Keep related shared definitions adjacent. Introduce each group with //----------------- DESCRIPTION OF GROUP ------------ and separate unrelated groups with // ---------------------------.

Design exports deliberately

  • Export a function or variable at its declaration, such as export function loadSession(). Do not collect ordinary exports at the end of an implementation file.
  • The preceding rule does not apply to index.ts barrel exports.
  • For every exported component, add a brief comment at its definition naming the consuming module or modules and explaining why they use it. Update the comment when consumers change.
  • Do not export speculative helpers, implementation details, or symbols that have no cross-file consumer.
  • Use clear, specific names for functions and variables. Add a concise comment anywhere intent, ordering, invariants, or edge cases could be confusing.

Keep routes thin

  • Parse and validate transport input in the route, convert it to the service's expected typed input, call one or more services, and translate the result to the response.
  • Keep business logic, persistence, filesystem work, subprocess execution, and orchestration out of routes.
  • Allow a service to call other services. Access another module's services through that module's public barrel contract.

Test within the module

  • Put feature tests in server/modules/<feature>/tests/.
  • Add or update unit tests for changed service behavior and route parsing.

Verify the result

Before finishing:

  1. Confirm all cross-module imports use index.ts barrels and all public exports are necessary and documented.
  2. Confirm shared definitions follow the one-use versus multiple-use placement rule and grouping-comment format.
  3. Confirm routes only parse, call services, and format responses.
  4. Run the narrow relevant tests, then npm run build, npm run typecheck, and npm run lint when the task scope and environment permit.

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 Backend Module Standards AI skill do?

Enforce this repository's TypeScript backend module architecture standards. Use whenever creating, modifying, refactoring, or reviewing backend code under `server/`, including routes, services, modules, repositories, shared backend code, and backend tests. Do not apply these rules to frontend code or non-backend scaffolding.

Why use Backend Module Standards on TypingMind?

Because you install it once and use it with any model. Backend Module Standards 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 Backend Module Standards in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/siteboon/claudecodeui/tree/main/.agents/skills/backend-module-standards. 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 Backend Module Standards?

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 Backend Module Standards?

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

Is the Backend Module Standards AI skill free?

Yes. It is published on GitHub by siteboon under the AGPL-3.0 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 👇