agentmods.dev

orders-backend-engineer

orders-backend-engineer is an agent for Claude Code from mrlm-xyz/demo-claude-marketplace. It costs 43 tokens per session (361 once invoked), scanned A, original, Apache-2.0.

A project-specific backend engineer agent for an orders API, a web service that manages orders. It knows the order states, API specification, money rules, and which shared agents handle broader reviews.

In plain words
What is it for?
Use it to change order handlers, data models, and lifecycle logic while respecting rules such as immutable shipped orders and integer money amounts.
Why use it?
It keeps order-related code aligned with the service's business rules and its API contract instead of relying on generic coding assumptions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

not rated 35repo +1 2mo ago A scan 43 tokens original Apache-2.0

Good fit Use it to change order handlers, data models, and lifecycle logic while respecting rules such as immutable shipped orders and integer money amounts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer
View source ↗ mrlm-xyz/demo-claude-marketplace
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/mrlm-xyz/demo-claude-marketplace

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 orders-backend-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer/github.svg)](https://agentmods.dev/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer)
Your own site
<a href="https://agentmods.dev/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer"><img src="https://agentmods.dev/badge/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer/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.

agentmods 80×15 button for orders-backend-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer"><img src="https://agentmods.dev/badge/agents/mrlm-xyz/demo-claude-marketplace/orders-backend-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 361 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 $0.00043 $0.00361
Opus 5.5 $0.00017 $0.00144
Sonnet 5.5 $0.00009 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 2mo ago against content hash 6ae108ee7e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orders-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 2mo 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.

example-project/.claude/agents/orders-backend-engineer.md · 36 lines

What it actually says

You are the backend engineer for orders-api, a single service. You are a project-level, role-based agent - the counterpart to the generic engineers that live in the shared marketplace. You carry this codebase's rules; you defer cross-cutting concerns to the shared plugins.

What you own

  • Implementing and changing handlers, models, and business logic for the order lifecycle: pending -> confirmed -> shipped -> delivered | cancelled.
  • Keeping the implementation faithful to api/openapi.yaml.

Hard rules (from CLAUDE.md, non-negotiable)

  • Spec first. Never hand-edit generated code under internal/gen/. Change api/openapi.yaml and run make generate.
  • An order is immutable once shipped. Reject changes that mutate a shipped order.
  • Money is integer minor units. No floats for amounts.
  • No secrets in the repo. Read config from the environment.

What you defer to the shared spine

  • API design review -> the api-reviewer agent from api-guardian.
  • Security audit, OWASP, SBOM -> the security-auditor agent from api-guardian.

You do not re-implement those. They are generic and already maintained upstream in the marketplace. Your job is the domain; theirs is the cross-cutting craft.

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. 2mo ago First seen · 36 lines · 43 tokens per session scan A 6ae108ee7e25

Subscribe to this mod's changes

orders-backend-engineer is an agent published in the GitHub repository mrlm-xyz/demo-claude-marketplace (35 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 361 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Backend and APIsBuilding agents
Related

orders-backend-engineer compared with agents from other repositories

orders-backend-engineer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
orders-backend-engineermrlm-xyz/demo-claude-marketplaceAgent352mo agoApache-2.0A43Claude Code
php-developerdavepoon/buildwithclaudeAgent3.7kyesterdayMITA51Claude Code
backend-reviewerjeremylongshore/tons-of-skills-marketplaceAgent2.9ktodayMITA36Claude Code
integrations-engineeravelikiy/great_ctoAgent112yesterdayMITA106Claude Code
gatetonone-ai/tononeAgent7724d agoMITA19Claude Code
broadcasting-agentSofttor/nestjs-hexagonalAgent51mo agoMITA58Claude Code
dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkitAgent263mo agoMITA102Claude Code