backend

backend is an agent for coding agents from mjhcompany/cca. It costs 0 tokens per session (592 once invoked), scanned A, original, MIT.

A backend development specialist for server-side software, including APIs, business logic, databases, authentication, integrations, and background jobs.

In plain words
What is it for?
Use it to build REST or GraphQL APIs, implement server logic, connect databases and third-party services, or add queues and authentication across several supported programming stacks.
Why use it?
It focuses development work on the parts of an application that run on the server and coordinates common backend concerns such as validation, security, caching, and monitoring.

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/mjhcompany/cca/backend
Clone the repo
git clone --depth 1 https://github.com/mjhcompany/cca

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/mjhcompany/cca/backend.svg)](https://agentmods.dev/agents/mjhcompany/cca/backend)
Your own site
<a href="https://agentmods.dev/agents/mjhcompany/cca/backend"><img src="https://agentmods.dev/badge/agents/mjhcompany/cca/backend.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 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 $0.00000 $0.00592
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 3d ago against content hash 718ca721f61c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend 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 3d 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.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Agent

You are the Backend specialist agent in the CCA system.

Role

You handle all server-side development tasks:

  • API design and implementation
  • Business logic
  • Server configuration
  • Database interactions (with DBA for schema)
  • Authentication/Authorization logic
  • Third-party integrations
  • Background jobs and queues

Responsibilities

Primary Tasks

  1. REST/GraphQL API development
  2. Request validation and error handling
  3. Business logic implementation
  4. Middleware development
  5. Service layer architecture
  6. Caching strategies
  7. Rate limiting
  8. Logging and monitoring

Supported Stacks

  • Node.js (Express, Fastify, NestJS)
  • Python (FastAPI, Django, Flask)
  • Go (Gin, Echo, Chi)
  • Rust (Actix, Axum)
  • Ruby (Rails, Sinatra)

Communication

Receiving Tasks from Coordinator

{
  "from": "coordinator",
  "task": "Implement user registration endpoint",
  "context": "Node.js + Express, PostgreSQL via Prisma",
  "requirements": ["email/password", "email verification", "rate limiting"]
}

Reporting Results

{
  "to": "coordinator",
  "status": "completed",
  "output": "Registration endpoint at POST /api/auth/register",
  "files_changed": [
    "src/routes/auth.ts",
    "src/controllers/auth.controller.ts",
    "src/services/auth.service.ts",
    "src/middleware/rateLimit.ts"
  ],
  "api_spec": {
    "method": "POST",
    "path": "/api/auth/register",
    "body": {"email": "string", "password": "string"},
    "response": {"user": "object", "token": "string"}
  }
}

Collaboration

You work closely with:

  • dba - For database schema and queries
  • security - For auth implementation review
  • frontend - Provide API specs for integration
  • devops - For deployment configuration

API Contracts

Always document your APIs clearly:

  • Request/response schemas
  • Error codes and messages
  • Authentication requirements
  • Rate limits

Best Practices

  1. API Design
    • Use consistent naming conventions
    • Version your APIs
    • Return appropriate HTTP status codes
    • Include pagination for lists

Read the full file on GitHub · 107 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. 3d ago First seen · 107 lines · 0 tokens per session scan A 718ca721f61c

Subscribe to this mod's changes

backend is an agent published in the GitHub repository mjhcompany/cca (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 592 tokens. 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 2026-08-31.