backend-engineering

backend-engineering is a skill for Claude Code, Codex from vignesh2027/AI-AGENT-SKILLS. It costs 17 tokens per session (489 once invoked), scanned A, original, MIT.

A guide for designing backend services—the server-side programs that handle data, business rules, and requests from apps. It covers reliability, monitoring, security, and maintainability.

In plain words
What is it for?
Use it when creating or significantly changing a service, fixing reliability, performance, or security problems, or reviewing backend code.
Why use it?
It helps prevent services from breaking when dependencies fail or users send invalid or harmful data. It also makes expected behavior and error handling clear before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating or significantly changing a service, fixing reliability, performance, or security problems, or reviewing backend code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/ai-agent-skills/backend-engineering
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 vignesh2027/AI-AGENT-SKILLS --skill backend-engineering
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLS

Made for: Claude Code, Codex.

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-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/backend-engineering/github.svg)](https://agentmods.dev/skills/vignesh2027/ai-agent-skills/backend-engineering)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/backend-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/backend-engineering/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-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/backend-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/backend-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00017 $0.00489
Opus 5 $0.00009 $0.00244
Sonnet 5 $0.00003 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 9d ago against content hash 60d4816e8811, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

backend-engineering 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 9d 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.

skills/backend-engineering/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Backend services are the load-bearing walls of software systems. They must be reliable under partial failure, observable in production, and secure against malicious input. This skill applies the engineering discipline required for production-grade services.

When to Use

  • Before implementing a new service or significant backend feature
  • When a service has reliability, performance, or security issues
  • As part of the /review workflow for backend PRs

Process

Step 1: Define the contract

Document: endpoints/methods, request/response schemas, error codes, authentication requirements, rate limits. No implementation before the contract is defined.

Step 2: Design for failure

Every outbound call must have: timeout, retry with backoff, circuit breaker, fallback. Services that don't handle dependency failures will fail when their dependencies fail.

Step 3: Input validation at the boundary

Validate all incoming data before processing: types, required fields, length limits, format constraints. Reject invalid input — don't try to fix it.

Step 4: Idempotency for mutations

All write operations should be idempotent where possible. Use idempotency keys for payment and other sensitive operations.

Step 5: Database access

  • No N+1 queries
  • Transactions for operations that must be atomic
  • Read replicas for read-heavy workloads
  • Connection pooling configured

Step 6: Logging and observability

Implement structured logging, metrics (four golden signals), and distributed tracing. See observability-and-monitoring.

Step 7: Security

  • Authenticate every request
  • Authorize every resource access
  • Validate all inputs
  • No secrets in logs or responses See security-and-hardening.

Step 8: Graceful shutdown

Handle: SIGTERM, drain in-flight requests, close database connections, flush logs. Services that don't handle graceful shutdown cause errors during deployments.

Verification Requirements

  • Contract documented before implementation
  • All outbound calls have timeout and retry
  • Input validation at the service boundary
  • No N+1 queries
  • Authentication and authorization on every request/resource
  • Graceful shutdown implemented
  • Four golden signals instrumented

Read the full file on GitHub · 60 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. 9d ago First seen · 60 lines · 17 tokens per session scan A 60d4816e8811

Subscribe to this mod's changes

backend-engineering is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 11d ago), licensed MIT. It adds 17 tokens to every session and 489 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 2026-08-31.