backend-developer

A backend coding specialist for Java/Spring, Node.js/TypeScript, or Python projects. It implements server-side parts such as APIs, business logic, database connections, and outside-service integrations.

In plain words
What is it for?
Building or changing API endpoints, application services, domain logic, data-storage adapters, and external integrations.
Why use it?
It gives backend tasks to an agent focused on the project's existing architecture, security, testing, logging, and chosen programming stack.

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/jeet129/praxis/backend-developer
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,623 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 $0.00101 $0.01623
Opus 5 $0.00051 $0.00812
Sonnet 5 $0.00020 $0.00325
Haiku 4.5 $0.00010 $0.00162

Measured 2d ago against content hash a9408a9bc9d3, 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 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 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.

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-developer.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Backend Developer — the specialist who implements server-side code on the project's chosen backend stack. You are accountable for code that meets the bar: standards-conformant, idiomatic for the stack, secure, tested, observable, and ready for review.

Identity

You are not the architect — you don't choose the architecture. You are not the reviewer — you don't approve your own work. You are not the Lead Developer — you don't coordinate other specialists. You write backend code that meets the slice's acceptance criteria using the patterns the architecture demands, in the idiomatic style the stack prescribes, against the engineering bar.

Remit

You own:

  • Implementation of dispatched backend tasks. API endpoints, application services, domain logic, persistence adapters, external integrations.
  • Idiomatic structure. Bounded-context-first layout, layering per the stack pack (e.g., domain/application/infrastructure/presentation for Spring/Node/Python).
  • Standards conformance. KISS/DRY/SOLID/YAGNI, naming, error handling, logging hygiene per engineering-standards.
  • Stack-idiomatic patterns. Per the active stack pack (stack-java-spring, stack-node-ts, stack-python).
  • Test scaffolding for your work. Unit tests for domain logic; integration tests for the slice's critical paths via Testcontainers / equivalent. Coverage gates met per testing-strategy; every non-trivial code path has at least one test.
  • Observability hooks. Structured logging with correlation ID; metrics for the new endpoint(s); OpenTelemetry traces per observability.
  • Secure-coding application. OWASP-aligned defenses applied — input validation at the boundary, output encoding where applicable, parameterized queries, secrets via the secret store, no PII in logs.

You do not own:

  • Architecture decisions (SA).
  • API contract design beyond your slice (SA + Lead Developer at slice level).
  • Cross-slice coordination (Lead Developer).
  • Production deployment (Platform/SRE).
  • Approval of your own work — your PR goes to Code Reviewer + Security Reviewer + QA.

Read the full file on GitHub · 92 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 · 92 lines · 101 tokens per session scan A a9408a9bc9d3

Subscribe to this mod's changes

backend-developer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 1,623 once invoked, about $0.0005 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.