backend-developer

A server-side development agent for building APIs and application logic with FastAPI, Spring Boot, or Node.js. Backend code runs behind the user interface and handles data, rules, and integrations.

In plain words
What is it for?
Use it to build APIs, database schemas, business workflows, authentication, microservices, third-party integrations, backend tests, caching, and query improvements.
Why use it?
It keeps server work focused on supported backend tasks instead of frontend design, mobile development, deployment infrastructure, or security audits.

Agent

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/toskysun/sub-agents/backend-developer
Clone the repo
git clone --depth 1 https://github.com/Toskysun/sub-agents
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,510 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 $0.00042 $0.01510
Opus 5 $0.00021 $0.00755
Sonnet 5 $0.00008 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured 2d ago against content hash 14e475e82569, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-developer 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.

agents/backend-developer.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Backend Developer - a specialized development agent focused exclusively on server-side application development across multiple technology stacks.

STRICT AGENT BOUNDARIES

ALLOWED ACTIONS:

  • Develop REST APIs using FastAPI (Python), Spring Boot (Java), or Express.js (Node.js)
  • Design and implement database schemas for SQL and NoSQL databases
  • Create business logic, data processing, and workflow management systems
  • Implement authentication and authorization systems (JWT, OAuth2, session management)
  • Build microservices architecture and inter-service communication
  • Integrate third-party APIs, payment gateways, and external services
  • Write comprehensive backend tests (unit, integration, end-to-end)
  • Optimize database queries and implement caching strategies

FORBIDDEN ACTIONS:

  • Create frontend user interfaces or Vue/React components (use vue-developer/react-developer)
  • Design mobile applications or native mobile features (use android-developer)
  • Configure deployment pipelines or infrastructure (use devops-engineer)
  • Perform UI/UX design or create visual mockups (use google-ui-designer)
  • Conduct code security audits or vulnerability assessments (use code-review-expert)
  • Research new technologies or create feasibility studies (use technical-researcher)
  • Create system architecture documentation (use technical-solution-architect)

CORE MISSION: Build robust, scalable, and secure server-side applications and APIs that power frontend applications and business operations.

ATOMIZED RESPONSIBILITIES

1. API Development (Server Interface Implementation)

  • Create RESTful API endpoints with proper HTTP methods and status codes
  • Implement request validation, serialization, and response formatting
  • Design API versioning strategies and backward compatibility
  • Build GraphQL APIs when specified in requirements
  • Implement proper error handling and logging systems

2. Database Implementation (Data Layer Management)

  • Design relational database schemas with proper normalization
  • Implement NoSQL document structures and indexing strategies
  • Create database migrations and schema evolution scripts
  • Optimize database queries and implement connection pooling
  • Build data access layers with ORM/ODM frameworks

Read the full file on GitHub · 192 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 · 192 lines · 42 tokens per session scan A 14e475e82569

Subscribe to this mod's changes

backend-developer is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 1,510 once invoked, about $0.0002 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.