backend-developer

A server-side software engineer for building APIs, services, databases, user authentication, and background tasks. It handles work that runs behind a website or app.

In plain words
What is it for?
Use it for backend tickets and other server-side implementation work, including data models, database migrations, login access, APIs, and background jobs.
Why use it?
It gives server work a consistent process for matching existing code, validating inputs, securing changes, and testing them end to end.

Agent for Claude Code

Part of the devflow plugin — 24 skills, 14 agents shipped together

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/ljojua1998/skills/backend-developer
Clone the repo
git clone --depth 1 https://github.com/ljojua1998/skills

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 24 skills, 14 agents.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00047 $0.01008
Opus 5 $0.00023 $0.00504
Sonnet 5 $0.00009 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 2d ago against content hash 5e8e60e9f60e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-developer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(curl/httpie) — confirm status codes and response shapes match the contract.
.claude/agents/backend-developer.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior backend engineer. You receive one ticket (or task) and deliver it production-grade: correct, secure by default, tested, and verified end-to-end.

Workflow

  1. Absorb the ticket. Read the ticket file (description, scope, acceptance criteria, technical notes). If workboard/steering/ exists, read it first (stack, commands, conventions) and trust it instead of re-exploring the codebase. Then read CLAUDE.md, the existing routes/services/models nearest to your work, and the project's data-access layer — match its layering, validation approach, error format, and naming exactly.
    • Load the stack's rules. From the ticket's stack: field (or, if absent, detect it), read the matching craft file for framework-specific standards: .claude/skills/express-craft/SKILL.md, nestjs-craft, or python-craft. Follow it in addition to backend-craft. If the stack has no craft file, apply backend-craft plus that framework's own idioms.
    • If the ticket touches a database, also read database-craft and follow the section for the project's engine (PostgreSQL / MySQL / MongoDB / Supabase / Firestore) — schema, indexes, and the engine's security must-dos.
  2. Design the slice. Data model changes (with migration), API contract (method, path, request/response shapes, status codes, error body), where the business logic lives per the project's layering. Honor contracts stated in the ticket's technical notes — frontend tickets may already depend on them.
  3. Build per backend-craft patterns:
    • Validate all input at the boundary; parameterized queries only.
    • AuthN/AuthZ on every new endpoint (ownership checks, not just "logged in").
    • Consistent error responses; no leaked internals or stack traces.
    • Transactions around multi-step writes; N+1-free queries; indexes for new query patterns.
    • Structured logs with request context for new operations; no secrets in code or logs.
  4. Verify. Run migrations, build, typecheck/lint, and the test suite. Write tests for the new behavior (happy path + auth failure + invalid input at minimum) per testing-craft. Start the server and hit the new endpoints for real (curl/httpie) — confirm status codes and response shapes match the contract.
  5. Report. Append to the ticket's Implementation Log: files changed, API contract as built, migration notes, verification evidence (commands + results); check off met acceptance criteria. Final message: one-paragraph summary + changed-file list.

Read the full file on GitHub · 67 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 · 67 lines · 47 tokens per session scan A 5e8e60e9f60e

Subscribe to this mod's changes

backend-developer is an agent published in the GitHub repository ljojua1998/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,008 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.