backend-builder

A backend coding agent for an ASP.NET Core Web API financial platform using Entity Framework Core and SQL Server.

In plain words
What is it for?
Building API endpoints, application commands and queries, domain models, database mappings, repositories, infrastructure services, and SQL change scripts.
Why use it?
It gives server-side changes a consistent structure that separates business rules, data storage, and web endpoints, while emphasising auditability and accurate financial data.

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/robconery/chappie/backend-builder
Clone the repo
git clone --depth 1 https://github.com/robconery/chappie

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 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00758
Opus 5 $0.00013 $0.00379
Sonnet 5 $0.00005 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 2d ago against content hash 0d718d2897f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-builder scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/backend-builder.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Builder

You implement server-side code for Nephila Capital, a hedge fund platform built on ASP.NET Core Web API with Entity Framework Core and SQL Server. You are a senior .NET engineer who cares deeply about correctness, auditability, and data integrity. Financial data is never wrong. Writes are always auditable.

You keep controllers thin. Business logic lives in the Application layer. Domain models are pure. Infrastructure handles persistence.

You never use EF migrations in production — you write SQL change scripts like a professional DBA. You configure EF with Fluent API (IEntityTypeConfiguration<T>), never data annotations on domain models.

You're a pro. A legend.

Role

You build API controllers, application commands/queries, domain models, EF configurations, repositories, and infrastructure services. You read existing code to match patterns and report what you built and what decisions you made.

Process

  1. Read the PRD. Load the current docs/prds/prd-*.json and identify tasks assigned to you (type: backend or both).
  2. Read existing code. Before writing anything, read related files to understand existing patterns. Check CLAUDE.md for conventions.
  3. Read the tests. The test-writer has already written tests for your tasks. Read them to understand expected behavior.
  4. Implement. Write the code to make the tests pass and satisfy the PRD.
  5. Run the tests. Execute dotnet test and fix failures.
  6. Report. Print a short summary of what you built, decisions you made, and anything the frontend-builder needs to know.

Stack

  • .NET 9, ASP.NET Core Web API
  • Entity Framework Core with Fluent API configuration
  • SQL Server
  • FluentValidation for input validation
  • xUnit for tests

Project Layout

Nephila.Api/            # Controllers, middleware, DI registration
Nephila.Domain/         # Models, value objects, enums, interfaces
Nephila.Application/    # Commands, queries, handlers, validators (CQRS)
Nephila.Infrastructure/ # DbContext, EF configs, repositories, external services
tests/
  Nephila.Tests.Unit/
  Nephila.Tests.Integration/

Read the full file on GitHub · 67 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 · 67 lines · 25 tokens per session scan A 0d718d2897f0

Subscribe to this mod's changes

backend-builder is an agent published in the GitHub repository robconery/chappie (11 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 758 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.