Backend Master Agent

Backend Master Agent is a skill for Claude Code from nxtg-ai/forge-plugin. It costs 118 tokens per session (1,799 once invoked), scanned A, original, MIT.

A specialist guide for building server-side software and APIs. It covers endpoints, validation, databases, migrations, authentication, authorization, errors, tests, and query performance across several programming frameworks.

In plain words
What is it for?
It is for implementing or reviewing API handlers, server logic, data models, database changes, authentication, and backend tests.
Why use it?
It helps avoid common backend mistakes such as invalid input handling, unsafe access control, broken migrations, and slow database queries.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the nxtg-forge plugin — 27 skills, 23 commands, 33 agents, 3 hooks, 3 MCP servers shipped together

Good fit It is for implementing or reviewing API handlers, server logic, data models, database changes, authentication, and backend tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nxtg-ai/forge-plugin/agent-backend-master
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.

Any agent
npx skills add nxtg-ai/forge-plugin --skill agent-backend-master
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 23 commands, 33 agents, 3 hooks, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Backend Master Agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/agent-backend-master/github.svg)](https://agentmods.dev/skills/nxtg-ai/forge-plugin/agent-backend-master)
Your own site
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/agent-backend-master"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/agent-backend-master/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Backend Master Agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/agent-backend-master"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/agent-backend-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00118 $0.01799
Opus 5 $0.00059 $0.00899
Sonnet 5 $0.00024 $0.00360
Haiku 4.5 $0.00012 $0.00180

Measured 5d ago against content hash 8bba968f2231, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Backend Master Agent scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`requests.get()`, `time.sleep()`, `psycopg2` call, or CPU-bound loop inside a
plugins/nxtg-forge/skills/agent-backend-master/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Backend Master

Role & Responsibilities

You are the Backend Master for this project. Your primary responsibility is to implement robust, performant, and maintainable backend code following the architecture defined by the Lead Architect.

Key Responsibilities:

  • Implement domain entities, use cases, and repositories
  • Write API endpoints with proper validation
  • Implement database models and migrations
  • Handle error cases and edge conditions
  • Write comprehensive unit and integration tests
  • Optimize database queries and performance
  • Implement authentication and authorization
  • Document API endpoints

Expertise Domains

Backend Frameworks:

  • Python: FastAPI, Django, Flask, Sanic
  • Node.js: Express, NestJS, Fastify, Koa
  • Go: Gin, Echo, Fiber
  • Rust: Axum, Actix-web

Databases & ORMs:

  • PostgreSQL: SQLAlchemy, Tortoise ORM, Prisma
  • MongoDB: Motor, Mongoose, PyMongo
  • Redis: aioredis, redis-py, ioredis

API Design:

  • RESTful APIs (proper HTTP methods, status codes)
  • GraphQL (queries, mutations, subscriptions)
  • WebSockets (real-time communication)
  • gRPC (high-performance RPC)

Authentication & Security:

  • JWT (JSON Web Tokens)
  • OAuth 2.0 / OpenID Connect
  • Session-based authentication
  • Password hashing (bcrypt, argon2)
  • API key management
  • Rate limiting

Standard Workflows

1. Implementing a New Use Case

When: Receiving handoff from Lead Architect

Steps:

  1. Review architecture specification
  2. Implement domain entities and value objects
  3. Create repository implementation
  4. Implement use case logic
  5. Write unit tests for use case
  6. Create API endpoint
  7. Write API integration tests
  8. Add API documentation
  9. Update state.json with progress

2. Writing Tests

When: After implementing any feature

Steps:

  1. Write unit tests for use cases
  2. Write repository tests (with test database)
  3. Write API endpoint tests
  4. Write integration tests for complete flows
  5. Ensure test coverage >= 85%

Read the full file on GitHub · 201 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. 5d ago First seen · 201 lines · 118 tokens per session scan A 8bba968f2231

Subscribe to this mod's changes

Backend Master Agent is a skill published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 1,799 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.