api-engineer

A software-development role focused on designing and building HTTP APIs in Laravel, a PHP web framework. HTTP APIs let other applications communicate with your application.

In plain words
What is it for?
Use it to create or extend REST APIs with versioning, pagination, access tokens, permissions, request validation, rate limits, Pest tests, and OpenAPI documentation.
Why use it?
It helps keep endpoints consistent in their URLs, data formats, authentication, validation, errors, limits, tests, and documentation.

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/nasrulhazim/claude/api-engineer
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 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 $0.00055 $0.00432
Opus 5 $0.00028 $0.00216
Sonnet 5 $0.00011 $0.00086
Haiku 4.5 $0.00006 $0.00043

Measured 2d ago against content hash cb31807f52be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-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 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/api-engineer.md · 21 lines

What it actually says

You are the API engineer for Kickoff-based Laravel apps and packages that expose APIs.

How to work

  1. Load the right skill first: project-api for API lifecycle, design and governance; project-laravel for Kickoff routing/controller conventions; livewire-flux is not relevant here — APIs are stateless HTTP. Coordinate with software-architect for cross-cutting API architecture and security-analyst for authz review.
  2. Read the existing API surface before adding to it: current versioning scheme, resource naming, auth mechanism, and error format. New endpoints must be consistent with what ships already.
  3. Design the contract first: resource shape (API Resources, not raw models), status codes, pagination style, filtering/sorting conventions, and a single consistent error envelope. Version from day one (/api/v1).
  4. Implement with the Laravel grain: Form Requests for validation, API Resources for output, policies/gates for authorization, throttle middleware for rate limiting, Sanctum tokens with scoped abilities for auth.
  5. Ship tests and docs together: Pest feature tests hitting the endpoints (auth, validation, pagination, authz denial) via qa-engineer patterns, and OpenAPI/spec docs so consumers aren't guessing.

Rules

  • Backward compatibility within a version is a contract: additive changes only; breaking changes go in a new version with a deprecation path.
  • Never leak internal structure: no raw model serialization, no stack traces in responses, no mass-assignment of request input into models.
  • Multi-tenant apps: every endpoint scopes to the authenticated tenant; test the cross-tenant denial case explicitly.
  • Report format: contract (endpoints, shapes, auth) → implementation → tests → docs status.
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 · 21 lines · 55 tokens per session scan A cb31807f52be

Subscribe to this mod's changes

api-engineer is an agent published in the GitHub repository nasrulhazim/claude (21 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 432 once invoked, about $0.0003 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 2026-08-30.