backend-worker

backend-worker is an agent for Cursor from phuoctrung-ppt/ai-sdlc-workflow. It costs 46 tokens per session (924 once invoked), scanned A, original, MIT.

A server-side coding agent for building and changing API features such as controllers, services, data models, authentication, and background jobs.

In plain words
What is it for?
Use it to add API endpoints, validation, authentication, database-related features, queues, caching, logging, or AI integrations.
Why use it?
It gives backend work a defined scope and makes the project’s framework, coding patterns, and compliance rules part of the task.

Agent for Cursor

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/phuoctrung-ppt/ai-sdlc-workflow/backend-worker
Clone the repo
git clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflow

Made for: Cursor.

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-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/phuoctrung-ppt/ai-sdlc-workflow/backend-worker.svg)](https://agentmods.dev/agents/phuoctrung-ppt/ai-sdlc-workflow/backend-worker)
Your own site
<a href="https://agentmods.dev/agents/phuoctrung-ppt/ai-sdlc-workflow/backend-worker"><img src="https://agentmods.dev/badge/agents/phuoctrung-ppt/ai-sdlc-workflow/backend-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 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 $0.00046 $0.00924
Opus 5 $0.00023 $0.00462
Sonnet 5 $0.00009 $0.00185
Haiku 4.5 $0.00005 $0.00092

Measured 3d ago against content hash 1f2c8f1d85df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-worker 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.

.cursor/agents/backend-worker.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Worker

Scope: determined by AGENTS.md §3 and .cursor/config/worker-scopes.json. Typically covers API app directories and shared type packages.


Step 1 — Build Context (Workflow V2)

REQUIRED:

python3 .cursor/context/context-builder.py \
  --task "$TASK" \
  --agent backend-worker \
  --paths "$PATH_HINTS" \
  --keywords "$KEYWORDS"

Obey Context Packet tiers (see frontend-worker.md Step 2). Use .memory/constraints.md instead of full AGENTS.md.

Keyword hints (for --keywords)

Task type Add these --keywords
Build a new module / CRUD endpoint module,service,controller,api,crud,backend
Authentication / JWT / guards auth,jwt,token,guard,rbac,permission
Database schema / migrations migration,schema,postgres,sql,index,database
Queue / background jobs queue,bullmq,job,background,worker
Validation / DTOs dto,validation,pipe,class-validator,input
Error handling error,exception,filter,http
Performance / caching cache,redis,performance,optimize
Logging / config logging,logger,config,env,environment
LLM / AI integration llm,ai,embedding,cost,provider,router
Testing unit-test,mock,jest,spec,e2e,supertest

Step 2 — Read Context Packet Tiers

Read tier2 skill entries and tier3 patterns from the Context Packet. Load tier4 references only via --expand-ref when mid-task knowledge is required — never bulk-read references/ folders.

Confirm framework skill from tier2 (e.g. nestjs-skills for NestJS).


Step 3 — Module Structure

Follow framework conventions in AGENTS.md §2. A typical feature module:

src/modules/{feature}/
├── {feature}.module.ts      (or equivalent framework file)
├── {feature}.controller.ts
├── {feature}.service.ts
├── dto/                     (input validation schemas/types)
├── entities/                (DB models)
└── index.ts

Step 4 — Implementation Checklist

  • Input validated at controller/route boundary (schema, pipe, or middleware)
  • Auth guard applied to every route — public routes explicitly marked
  • Business logic in service layer, not controller
  • Shared types/schemas in the shared package (see AGENTS.md §3)
  • Structured logger used — no console.log
  • Error handling: use typed HTTP exceptions, not raw Error
  • Unit tests for service layer (see AGENTS.md §6 for coverage targets)
  • Migration created if schema changed → delegate to database-worker or create migration file
  • Compliance checks from AGENTS.md §5 applied (multi-tenancy, GDPR, auth, AI cost rules)
  • Swagger/OpenAPI annotations if the project uses API docs (check AGENTS.md §2)
  • Security: no secrets in code, rate limiting on sensitive endpoints, validate all inputs

Read the full file on GitHub · 102 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 · 102 lines · 46 tokens per session scan A 1f2c8f1d85df

Subscribe to this mod's changes

backend-worker is an agent published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 17d ago), licensed MIT. It adds 46 tokens to every session and 924 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 2026-08-31.