Backend Architecture logo

Backend Architecture

OrganizationPopular
exceptionless
backend-architecture

Apply Exceptionless backend boundaries when changing API endpoints, mediator handlers, services, or jobs.

Overview

Publisherexceptionless
RepositoryExceptionless
Skill namebackend-architecture
Stars
2.5K
Forks
508
Bundled files
Instructions only
LicenseApache-2.0
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Backend Architecture 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/exceptionless/Exceptionless/tree/main/.agents/skills/backend-architecture
  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/exceptionless/Exceptionless.git /tmp/Exceptionless
mkdir -p .claude/skills
cp -r /tmp/Exceptionless/.agents/skills/backend-architecture .claude/skills/backend-architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Backend Architecture 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 Architecture 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 Architecture 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 Architecture

Current boundaries

  • src/Exceptionless.Web/Api/Endpoints/: Minimal API route registration, binding, authorization, and response metadata.
  • Api/Messages/ and Api/Handlers/: mediator requests and their application behavior. Follow the corresponding endpoint family.
  • Api/Filters/, Api/Infrastructure/, and Api/Results/: shared validation, request helpers, and HTTP result mapping.
  • Exceptionless.Core: domain models, services, repositories, billing, and serialization.
  • Exceptionless.Insulation: provider implementations for storage, caching, mail, and other infrastructure.
  • Exceptionless.Job: background processing.

For an endpoint example, read src/Exceptionless.Web/Api/Endpoints/OrganizationEndpoints.cs together with its messages and handler. Endpoint groups use AuthorizationRoles policies and AutoValidationEndpointFilter; mediator results map through ToHttpResult and the configured result mapper. Preserve the endpoint's response and authorization contract rather than recreating it from a generic example.

Repository conventions

Keep domain behavior in Core: Web and Job consume Core, while Insulation supplies infrastructure implementations. Do not move HTTP concerns into domain services.

  • Inject AppOptions directly. Non-secret settings use appsettings.yml; environment overrides use the EX_ prefix.
  • Use Foundatio abstractions for cache, queue, message bus, file storage, distributed locks, and resilience. Use foundatio-repositories for Elasticsearch operations.
  • Queue entries complete after durable processing succeeds. Distinguish retryable failures from invalid input.
  • Propagate cancellation where supported. Use structured logging and ExceptionlessState scopes for organization/project context.
  • WebSocket notifications use MessageBusBroker and WebSocketConnectionManager, backed by the message bus.
  • Follow root guidance for OpenAPI snapshots and compatibility. See serialization architecture when changing JSON behavior.

Implementation details

  • Prefer constructor injection and readonly dependency fields. Follow .editorconfig, use the Async suffix for asynchronous methods, and avoid adding regions.
  • Use ICacheClient, IQueue<T>, IMessageBus, IFileStorage, ILockProvider, and IResiliencePolicyProvider rather than creating provider-specific parallel abstractions.
  • Queue consumers commonly derive from QueueJobBase<T>; scheduled jobs use bases such as JobWithLockBase and [Job] scheduling attributes. Preserve lock, completion, abandonment, and cancellation behavior when modifying a job. Invalid input should not enter an endless retry cycle.
  • Use DataAnnotations and the existing MiniValidation integration for model validation. Preserve endpoint binding/validation errors and mediator-to-HTTP result mapping; inspect Api/Filters/AutoValidationEndpointFilter.cs, Api/Results/ApiResultMapper.cs, and the endpoint's tests for the expected status and ProblemDetails shape.
  • Use structured message templates, not interpolated log messages, and ExceptionlessState for shared context. Never log passwords, API keys, full tokens, or sensitive payloads; prefer necessary identifiers and safe summaries.

Frequently asked questions

What does the Backend Architecture AI skill do?

Apply Exceptionless backend boundaries when changing API endpoints, mediator handlers, services, or jobs.

Why use Backend Architecture on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/exceptionless/Exceptionless/tree/main/.agents/skills/backend-architecture. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Backend Architecture?

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 Architecture?

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

Is the Backend Architecture AI skill free?

Yes. It is published on GitHub by exceptionless under the Apache-2.0 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 👇