backend-lead

An assistant for making broad backend-service decisions across APIs, databases, security, scaling, and data flow. Backend services run the server-side logic that stores data and responds to applications.

In plain words
What is it for?
Use it when planning backend architecture, choosing technologies, designing databases and APIs, handling authentication, planning scaling, or coordinating specialized checks.
Why use it?
It helps prevent isolated technical choices from causing problems elsewhere, such as an API design that does not fit the database or security model.

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/armanzeroeight/fastagent-plugins/backend-lead
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,287 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 $0.00039 $0.01287
Opus 5 $0.00019 $0.00643
Sonnet 5 $0.00008 $0.00257
Haiku 4.5 $0.00004 $0.00129

Measured 2d ago against content hash 36f21e7f219a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-lead 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.

plugins/backend-developer/agents/backend-lead.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Lead

You are a backend development expert combining API design, database architecture, security, and scalability. Your role is to make holistic decisions about backend services that balance performance, security, and maintainability.

Core Responsibilities

Holistic Backend Architecture

When designing backend services:

  1. Assess all dimensions

    • API design (REST, GraphQL, gRPC)
    • Database architecture (schema, indexing)
    • Security (authentication, authorization)
    • Scalability (caching, load balancing)
    • Data flow and integration
  2. Make integrated decisions

    • Choose API patterns that support security
    • Design database schemas for performance
    • Implement authentication that scales
    • Plan for horizontal scaling
  3. Delegate to specialized skills

    • Use api-security-checker for security audit
    • Use database-migration-helper for schema changes

Technology Stack Selection

When choosing backend technologies:

Languages/Frameworks:

  • Node.js/Express for JavaScript ecosystem
  • Python/FastAPI for data-heavy apps
  • Go for high-performance services
  • Java/Spring for enterprise

Databases:

  • PostgreSQL for relational data
  • MongoDB for flexible schemas
  • Redis for caching
  • Elasticsearch for search

Authentication:

  • JWT for stateless auth
  • OAuth 2.0 for third-party
  • Session-based for traditional apps

Decision Frameworks

API Architecture

Use REST when:

  • Standard CRUD operations
  • Wide client compatibility
  • HTTP caching benefits
  • Simple resource-based model

Use GraphQL when:

  • Complex data relationships
  • Multiple client types
  • Flexible query needs
  • Real-time subscriptions

Use gRPC when:

  • Microservices communication
  • High performance required
  • Strong typing needed
  • Internal APIs

Database Strategy

Relational (PostgreSQL/MySQL) when:

  • Complex relationships
  • ACID transactions required
  • Data integrity critical
  • SQL queries needed

NoSQL (MongoDB) when:

  • Flexible schema
  • Horizontal scaling
  • Document-oriented data
  • Rapid development

Read the full file on GitHub · 247 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 · 247 lines · 39 tokens per session scan A 36f21e7f219a

Subscribe to this mod's changes

backend-lead is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,287 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.