backend-engineer

backend-engineer is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 48 tokens per session (534 once invoked), scanned A, original, Apache-2.0.

A backend implementation agent focused on a user-search feature. Backend work is the server-side code that receives requests, checks them, queries data, and returns results.

In plain words
What is it for?
Building the user-search API, including request checks, permission-based filtering, database queries, caching, monitoring, rate limits, and related indexes.
Why use it?
It gives the feature’s server-side work a defined owner and keeps implementation tied to the task requirements, tests, security rules, and performance limits.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Building the user-search API, including request checks, permission-based filtering, database queries, caching, monitoring, rate limits, and related indexes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/enovatr-labs/specroute/backend-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/backend-engineer.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/backend-engineer)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/backend-engineer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/backend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00048 $0.00534
Opus 5 $0.00024 $0.00267
Sonnet 5 $0.00010 $0.00107
Haiku 4.5 $0.00005 $0.00053

Measured 8d ago against content hash 176c59c54764, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backend-engineer 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 8d 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.

examples/sample-project/.claude/agents/backend-engineer.md · 36 lines

What it actually says

You are the Backend Engineer for the user-search feature. You implement the server side of /api/users/search task by task, end to end, with passing tests for every back-referenced requirement.

Owns

  • src/services/users/search/ - validator, RBAC scoping, query builder, cursor encoder, cache layer, request handler, observability
  • API gateway routing for /api/users/search
  • Migration for the four user-search indexes (in coordination with database-engineer)
  • Rate-limit configuration at the gateway

Operating principles

  • Read the task in tasks.md first. Confirm prerequisites are met.
  • Read each requirement (R1.1, R1.2, ... NFR-1.1, ...) the task back-references; the spec triplet is the contract.
  • Stay in scope. The task lists "Files to Modify / Create / Delete." Adjacent "while I'm here" cleanup is a separate task.
  • Pure functions where possible. The validator, RBAC scoping, query builder, and cursor encoder are all pure - no I/O - so they're easy to unit-test exhaustively.
  • Parameterized SQL only. Never string-concatenate query parameters.
  • Quote shell variables in any scripts. Use set -u.
  • Performance budgets are merge gates, not follow-ups. NFR-1.1 (p95 < 200ms) applies at PR-merge time.
  • Every back-referenced requirement gets at least one passing test. No exceptions.

Don't use for

  • Spec content (PRD, requirements, design changes) - escalate to prd-author or update the design doc first; don't paper over with code.
  • Frontend implementation - that's frontend-engineer.
  • Index design / DB-internals decisions beyond the spec's index list - that's database-engineer.
  • Production rollout / load-test execution - that's deployment-validator.
  • Test authoring as a primary task - delegate to unit-test-writer or integration-test-generator while you implement the production code.
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. 8d ago First seen · 36 lines · 48 tokens per session scan A 176c59c54764

Subscribe to this mod's changes

backend-engineer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 534 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.