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.
npx skills add vignesh2027/AI-AGENT-SKILLS --skill backend-engineeringgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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.
[](https://agentmods.dev/skills/vignesh2027/ai-agent-skills/backend-engineering)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
/reviewworkflow 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
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.
- 9d ago First seen · 60 lines · 17 tokens per session scan A 60d4816e8811
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.
Other skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
api-verification
An API verification workflow that creates both an .http request file and a .cjs JavaScript file, then runs an automation script to test them. An API is an interface through which software exchanges requests and responses.
api-contract-architecture
An architecture guide for public APIs, including HTTP services, software-development kits, command-line tools, schemas, types, errors, pagination, filtering, and compatibility.
backend-domain-architecture
A review guide for backend and business-domain design. It examines business rules, workflows, permissions, APIs, transactions, consistency, repeated requests, compatibility, data boundaries, and service responsibilities.
distributed-systems-architecture
An architecture guide for distributed systems—software split across services that communicate over networks.
external-integration-architecture
A guide for designing connections to outside services such as web APIs, webhooks, and OAuth sign-ins. It focuses on keeping those connections separate and planning for failures.