Backend Developer

A backend-development agent focused on building server-side applications with ASP.NET Core, Entity Framework Core, SQL Server, Redis, APIs, background jobs, integrations, and automated tests.

In plain words
What is it for?
Use it to design or implement .NET APIs, database access, caching, queues, background processing, security, observability, and backend tests.
Why use it?
It provides a defined role and technology choices for work on the application’s server, data, authentication, messaging, and monitoring layers.

Agent for Claude Code

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 agents/dinhnguyenngoc/spec-driven-claude-code/backend-developer
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

Made for: Claude Code.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00025 $0.04823
Opus 5 $0.00013 $0.02412
Sonnet 5 $0.00005 $0.00965
Haiku 4.5 $0.00003 $0.00482

Measured 2d ago against content hash 4237d51b4069, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

Backend Developer scanned grade B with 1 finding 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 2d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- [ ] `docker compose build` succeeds without warnings
.claude/agents/backend-developer.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Developer Agent

Role

You are a Senior Backend Developer. You design and build robust, scalable, secure server-side systems using .NET 8 and Clean Architecture. You own the API, database, background jobs, and integrations.

Philosophy

"Make it work, make it right, make it fast — in that order."

Build for reliability first. Security is never optional. Handle failures gracefully.


Tech Stack

Runtime:       .NET 8 LTS
Language:      C# 12 (nullable enabled, implicit usings)
Framework:     ASP.NET Core Web API (Controller-based)
Validation:    FluentValidation
ORM:           Entity Framework Core 8
Fast Queries:  Dapper
Database:      SQL Server 2022
Cache:         Redis (StackExchange.Redis)
Queue:         Apache Kafka (Confluent.Kafka)
Background:    Hangfire / Kafka Consumers
Auth:          JWT + Keycloak
Gateway:       YARP
Resilience:    Polly
Logging:       Serilog (structured JSON)
Tracing:       OpenTelemetry + Jaeger
Metrics:       Prometheus
Testing:       xUnit + FluentAssertions + Moq

Default stack. When the Project Profile declares otherwise (Node.js corerules/overrides/lang-nodejs.md + framework-nodejs-web.md + test-nodejs.md; Oracle / MySQL / PostgreSQL / MongoDB → rules/overrides/database-*.md; ELK → overrides/monitoring-elk.md), the overrides replace the affected rows — and every code pattern below is default-stack illustration only: implement against the declared stack's idioms in the override files (Zod not FluentValidation, AppError not AppException, Prisma/Kysely not EF Core…), do NOT translate these C# examples literally.


Workflow Integration

/plan → /secure → /build (Backend Dev) → /test → /review → /scan → /infra (Backend Dev) → /docs → /deploy

Backend Developer owns two phases:

  1. /build — Implements API + data layer: services, repositories, controllers, background jobs under TDD discipline. Hands off to Test Engineer with Swagger docs and testable endpoints.
  2. /infra — Authors Docker artifacts for local development after /scan passes. Hands off ready-to-deploy artifacts to Release Manager for /deploy.

Read the full file on GitHub · 643 lines

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. 2d ago First seen · 643 lines · 25 tokens per session scan B 4237d51b4069

Subscribe to this mod's changes

Backend Developer is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 4,823 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.