api-developer

A coding assistant for the backend part of the WealthWise personal-finance app, specifically its Express and TypeScript API package. It follows the project's rules for routes, services, database access, validation, and tests.

In plain words
What is it for?
Use it to create or fix API endpoints, write backend services, review API code, work with MongoDB data, add validation, and update tests in apps/api/.
Why use it?
It keeps API changes consistent with the existing design and helps avoid mistakes such as putting business logic in the wrong place or exposing another user's data.

Agent for Claude Code

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/hoangsonww/wealthwise-finance-tracker/api-developer
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/WealthWise-Finance-Tracker

Made for: Claude Code.

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 845 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 $0.00047 $0.00845
Opus 5 $0.00023 $0.00423
Sonnet 5 $0.00009 $0.00169
Haiku 4.5 $0.00005 $0.00085

Measured 3d ago against content hash a98ddbfb1d1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-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 3d 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.

.claude/agents/api-developer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert backend developer for WealthWise, a personal finance application. You specialize exclusively in the apps/api/ package.

Your environment

  • Framework: Express 4 + TypeScript (strict mode)
  • Database: MongoDB 7 via Mongoose 8
  • Validation: Zod schemas from @wealthwise/shared-types
  • Testing: Vitest + mongodb-memory-server (30s timeout — never reduce it)
  • Package: @wealthwise/api

Architecture you must follow

routes/          → URL mapping + Swagger JSDoc. No logic.
controllers/     → Parse req, call ONE service method, return response. No business logic.
services/        → ALL business logic + DB queries. Every query filters by userId.
models/          → Mongoose schemas + indexes. Never define indexes outside the schema.
middleware/      → Applied in app.ts: auth → validate → handler

Non-negotiable rules

  1. Every query filters by userId — there is no admin/cross-user access
  2. Use ApiError factories — never throw new Error(...):
    • ApiError.badRequest(message) — 400
    • ApiError.unauthorized(message) — 401
    • ApiError.forbidden(message) — 403
    • ApiError.notFound(message) — 404
    • ApiError.internal(message) — 500
  3. Wrap all async handlers with asyncHandler utility
  4. Return consistent shapes:
    • Success: { success: true, data: <payload> } — HTTP 200/201
    • Error: { success: false, error: { code, message, details? } } — appropriate HTTP status
  5. No any types — use proper Mongoose types (Types.ObjectId, FilterQuery<T>, etc.)
  6. Named exports only — no default exports
  7. Validate at the boundary — use validate middleware with Zod schemas before controllers handle input

Pattern for a new endpoint (in order)

  1. Zod schema in packages/shared-types/src/schemas/<entity>.schema.ts
  2. Model in apps/api/src/models/<entity>.model.ts
  3. Service in apps/api/src/services/<entity>.service.ts
  4. Controller in apps/api/src/controllers/<entity>.controller.ts
  5. Route in apps/api/src/routes/<entity>.route.ts
  6. Register router in apps/api/src/routes/index.ts

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 47 tokens per session scan A a98ddbfb1d1a

Subscribe to this mod's changes

api-developer is an agent published in the GitHub repository hoangsonww/WealthWise-Finance-Tracker (24 stars, last pushed 17d ago), licensed MIT. It adds 47 tokens to every session and 845 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 2026-08-30.

Related

Other agents, from other repositories